Interactive learning activity dynamic optimization method and system

Abstract

The invention relates to the technical field of learning activity optimization, and discloses an interactive learning activity dynamic optimization method and system, and the method comprises the steps: obtaining learning data of a user, extracting an interest label and a learning capability label of the user through a preset user behavior analysis model, and generating a user state label; generating a corresponding activity generation path based on the user state tag in combination with a preset course knowledge base; matching a corresponding learning activity according to the activity generation path to obtain an initial learning activity; optimizing the activity generation path by adding a path branch, trimming the path branch or replacing a path node in combination with a real-time learning state of the user to obtain an activity optimization path; optimizing the initial learning activity through the activity optimization path to obtain an optimized learning activity so as to dynamically optimize the interactive learning activity; according to the method, the learning activity can be dynamically optimized, and the state change condition of the user in the learning process can be responded in real time.

Description

Technical Field

[0001] This application relates to the technical field of learning activity optimization, and particularly to an interactive learning activity dynamic optimization method and system. Background Art

[0002] At present, interactive learning activities have become an important learning mode. However, there are many deficiencies in the design and optimization of existing learning activities, and it is impossible to adjust and optimize learning activities in real time according to different users. The formulated learning activities have poor interestingness, resulting in poor learning effects.

[0003] The existing technology has the following problems: adopting fixed course content and learning paths, without fully considering the interest differences and learning ability differences among individual users, resulting in poor learning effects; the learning activity optimization mechanism is relatively single, and it is impossible to dynamically optimize learning activities in real time and comprehensively in combination with the user's real-time learning status; lacking comprehensive consideration of knowledge association and activity difficulty, resulting in lack of coherence and progression in the learning process; to solve at least one of the above problems, the present invention proposes an interactive learning activity dynamic optimization method and system. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the main purpose of the present invention is to provide an interactive learning activity dynamic optimization method and system, which can effectively solve the problems in the background art. The specific technical solutions of the present invention are as follows:

[0005] An interactive learning activity dynamic optimization method includes:

[0006] Obtaining the learning data of the user, extracting the interest label and learning ability label of the user through a preset user behavior analysis model, and generating a user status label;

[0007] Based on the user status label, combining with a preset course knowledge base, generating a corresponding activity generation path;

[0008] According to the activity generation path, matching corresponding learning activities to obtain an initial learning activity;

[0009] Combining with the user's real-time learning status, optimizing the activity generation path by adding path branches, pruning path branches or replacing path nodes to obtain an activity optimization path;

[0010] Through the activity optimization path, optimizing the initial learning activity to obtain an optimized learning activity, so as to dynamically optimize the interactive learning activity.

[0011] Specifically, the obtaining the learning data of the user, extracting the interest label and learning ability label of the user through a preset user behavior analysis model, and generating a user status label includes:

[0012] Collect the user's behavior logs, learning duration, and interaction records to obtain the user's learning data;

[0013] According to the learning data, extract the user's interest tags and learning ability tags through a preset user behavior analysis model;

[0014] Fuse the interest tags and learning ability tags to generate user status tags.

[0015] Specifically, based on the user status tags, combined with a preset course knowledge base, generate a corresponding activity generation path, including:

[0016] Extract the user's interest features and ability features according to the user status tags to construct a user status vector;

[0017] Based on the user status vector, perform matching in the preset course knowledge base to generate an activity generation path.

[0018] Specifically, based on the user status vector, perform matching in the preset course knowledge base to generate an activity generation path, including:

[0019] Based on the preset course knowledge base, use knowledge activities as activity nodes, and establish associations between activity nodes according to knowledge associations and activity difficulty to construct a knowledge graph;

[0020] According to the user status vector, match corresponding learning activities in the knowledge graph to obtain a candidate path set;

[0021] By calculating the matching value between each path in the candidate path set and the user status vector, select the path with the highest matching value in the candidate path set as the activity generation path.

[0022] Specifically, according to the activity generation path, match corresponding learning activities to obtain an initial learning activity, including:

[0023] According to the activity generation path, match corresponding first learning activities for each activity node in the preset activity template library;

[0024] Based on the user status vector, optimize the first learning activity to obtain a second learning activity;

[0025] According to the order of activity nodes in the activity generation path, combine the second learning activities to obtain an initial learning activity.

[0026] Specifically, by combining the user's real-time learning status, optimizing the activity generation path by adding path branches, pruning path branches, or replacing path nodes, to obtain an activity optimization path, including:

[0027] According to the user's real-time learning status, by analyzing the activity node density and dependency relationship in the activity generation path, identifying the path optimization area;

[0028] Optimizing the path optimization area by adding path branches, pruning path branches, or replacing path nodes, to obtain a first optimized path;

[0029] Optimizing the activity generation path according to the first optimized path, to obtain an activity optimization path.

[0030] Specifically, the optimizing the path optimization area by adding path branches, pruning path branches, or replacing path nodes, to obtain a first optimized path, includes:

[0031] According to the user's real-time learning status, analyzing the user's real-time interests and learning activity completion rate;

[0032] According to the real-time interests, adding path branches of corresponding activities in the path optimization area, to obtain a first optimized area;

[0033] When the learning activity completion rate is lower than the preset completion rate threshold, pruning the path branches of the corresponding activities, to obtain a second optimized area;

[0034] By analyzing the matching degree between the real-time learning status and the knowledge graph, replacing the path nodes with a matching degree less than the preset matching degree threshold, to obtain a third optimized area;

[0035] Combining the first optimized area, the second optimized area, and the third optimized area, to obtain a first optimized path.

[0036] Specifically, the optimizing the initial learning activity through the activity optimization path, to obtain an optimized learning activity, for dynamically optimizing the interactive learning activity, includes:

[0037] According to the activity optimization path, hierarchically optimizing the initial learning activity, to obtain a corresponding first optimized activity;

[0038] Combining the first optimized activities, to obtain an optimized learning activity, for dynamically optimizing the interactive learning activity.

[0039] Specifically, the hierarchically optimizing the initial learning activity according to the activity optimization path, to obtain a corresponding first optimized activity, includes:

[0040] According to the optimized activity nodes in the optimized activity path, match the corresponding learning activities in the preset activity template library to obtain optimized activities;

[0041] Replace the corresponding learning activities in the initial learning activities with the optimized activities, and adjust the order and duration of the learning activities to obtain the first optimized activity.

[0042] An interactive learning activity dynamic optimization system for implementing the described interactive learning activity dynamic optimization method, including:

[0043] A user status analysis module, which obtains the learning data of the user, extracts the interest tags and learning ability tags of the user through a preset user behavior analysis model, and generates user status tags;

[0044] An activity generation path formulation module, which generates a corresponding activity generation path based on the user status tags and in combination with a preset course knowledge base;

[0045] A learning activity formulation module, which matches corresponding learning activities according to the activity generation path to obtain initial learning activities;

[0046] An activity generation path optimization module, which optimizes the activity generation path by adding path branches, pruning path branches or replacing path nodes in combination with the real-time learning status of the user to obtain an optimized activity path;

[0047] A learning activity optimization module, which optimizes the initial learning activities through the optimized activity path to obtain optimized learning activities for dynamically optimizing the interactive learning activities.

[0048] Compared with the prior art, the present application has the following beneficial effects:

[0049] The present application analyzes the user status based on the multi-dimensional learning data of the user, matches the corresponding activity generation path in combination with the knowledge graph, optimizes the activity generation path according to the real-time learning status of the user, and performs hierarchical optimization on the initial learning activities based on the optimized path, realizing the dynamic adjustment of the learning activities, being able to respond in real time to the changes in the user's learning process, ensuring that the optimized learning activities are more in line with the user's needs and learning rhythm, and improving the user's learning efficiency and learning effect. Description of the Drawings

[0050] Figure 1 It is a working flow chart of an interactive learning activity dynamic optimization method in Embodiment 1 of the present invention;

[0051] Figure 2 It is a schematic diagram of the activity generation path matching process in Embodiment 1 of the present invention;

[0052] Figure 3Schematic diagram of the optimization process of the path optimization area in Embodiment 1 of the present invention;

[0053] Figure 4 Schematic diagram of the structure of an interactive learning activity dynamic optimization system in Embodiment 2 of the present invention. Detailed implementation manners

[0054] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the detailed implementation manners of the present invention with reference to the accompanying drawings of the specification.

[0055] In the following description, many specific details are set forth to facilitate a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0056] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that excludes other embodiments.

[0057] Embodiment 1:

[0058] This embodiment provides an interactive learning activity dynamic optimization method. As Figure 1 shown, the interactive learning activity dynamic optimization method includes:

[0059] S101. Obtain the learning data of the user, extract the interest label and learning ability label of the user through a preset user behavior analysis model, and generate a user status label;

[0060] S102. Based on the user status label, combined with a preset course knowledge base, generate a corresponding activity generation path;

[0061] S103. According to the activity generation path, match the corresponding learning activity to obtain an initial learning activity;

[0062] S104. Combine the real-time learning status of the user, and optimize the activity generation path by adding path branches, pruning path branches, or replacing path nodes to obtain an activity optimization path;

[0063] S105. Through the activity optimization path, optimize the initial learning activity to obtain an optimized learning activity, so as to dynamically optimize the interactive learning activity.

[0064] In this embodiment, first, the learning status of the user is analyzed based on the user's learning data. Combining the user's learning status and the preset course knowledge base, a corresponding activity generation path is generated, and the corresponding learning activities are matched to formulate learning activities suitable for the user's status. During the user's learning process, according to the changes in the user's real-time learning status, the activity generation path and learning activities are optimized accordingly. By dynamically optimizing the learning activities, the learning content and form are always matched with the user's real-time learning status. Compared with the traditional fixed learning activity mode, this application can prevent the user from wasting time on learning content that is not suitable for themselves, improve learning efficiency, and help the user master knowledge and skills faster.

[0065] In this embodiment, first, the learning data generated during the user's learning process is obtained, and the learning data is analyzed through a preset user behavior analysis model to extract the user's interest tags and learning ability tags, generating user status tags. The preset user behavior analysis model can be a machine learning model or a statistical model. The user behavior analysis model is trained using a large amount of historical data to obtain a pre-trained user behavior analysis model. The user behavior analysis model extracts the knowledge fields that the user is interested in by analyzing the user's preferences for different courses and learning resources, obtaining the corresponding interest tags. The learning ability of the user is evaluated based on data such as the user's learning progress and knowledge mastery level to generate learning ability tags. Integrating the interest tags and learning ability tags into user status tags can reflect the learning characteristics and current status of the user, providing a basis for formulating learning activities that meet the user's needs and improving the matching degree between the learning activities and the user.

[0066] Specifically, according to the analyzed user status tags, a match is made in the preset course knowledge base, and the courses, knowledge points, and learning resources that match the user's interests and learning abilities are screened out and combined in the corresponding logical order to obtain the activity generation path. Generating the activity generation path based on the user status tags can customize the corresponding learning route for the user, making the learning activities fit the user's interests and abilities, helping the user learn knowledge more efficiently, avoiding the learning content being too difficult or too easy, improving the pertinence and effectiveness of learning, and at the same time better meeting the user's personalized learning needs.

[0067] Exemplarily, for user A, the user status tags are: interests include Python programming, data structures and algorithms; the learning ability is relatively strong in programming learning. Resources such as Python Advanced Programming Course, Advanced Data Structures and Algorithms Course, and Python Data Analysis Project Cases are matched in the course knowledge base. According to the user's learning ability and the logical relationship of knowledge, the generated activity generation path is: Python Advanced Programming Course → Advanced Data Structures and Algorithms Course → Python Data Analysis Project Case.

[0068] Specifically, according to the generated activity generation path, corresponding learning activities are matched to obtain the initial learning activities; based on the learning content and sequence determined by the activity generation path, specific learning activity forms are searched in the learning resource library, including video courses, online tests, group discussions, project practices, etc., and the matched learning activities are combined to obtain the corresponding initial learning activities; obtaining the initial learning activities by matching corresponding learning activities through the activity generation path can meet the learning habits and needs of different users, improve the fun and participation of learning, and at the same time ensure that users can comprehensively and deeply master knowledge and skills.

[0069] During the user's learning process, the user's learning status is analyzed in real time, and the activity generation path is optimized according to the user's real-time learning status. By adding path branches to introduce new learning resources or courses to supplement knowledge gaps, pruning path branches to remove unnecessary or inappropriate learning content, and replacing path nodes with more suitable learning resources to replace the original resources, the activity generation path is optimized to obtain the activity optimization path; by optimizing the activity generation path, it can be considered that during the user's learning process, the learning status will change due to reasons such as difficulty in understanding a certain knowledge point, acceleration or deceleration of the learning progress, resulting in the original activity generation path no longer being suitable. Optimizing the activity generation path can respond in a timely manner to the changes during the user's learning process, making the learning activities always match the user's actual needs and learning situation, avoiding learning burnout or learning difficulties caused by inappropriate learning content for the user, improving learning efficiency and learning effect, and realizing the dynamic adaptive adjustment of learning activities.

[0070] Specifically, according to the optimized activity optimization path, the initial learning activities are adjusted and optimized accordingly, replacing inappropriate learning activities, adding new learning activities, and removing unnecessary learning activities to obtain optimized learning activities. By optimizing the learning activities, the learning activities can more accurately meet the user's real-time needs, and the optimized learning activities can better help users overcome learning difficulties, consolidate knowledge, and improve skills, achieving more efficient learning.

[0071] This application analyzes the user status based on the user's multi-dimensional learning data, matches the corresponding activity generation path in combination with the knowledge graph, optimizes the activity generation path according to the user's real-time learning status, and performs hierarchical optimization on the initial learning activities based on the optimized path to achieve the dynamic adjustment of learning activities, which can respond in real time to the changes during the user's learning process, ensure that the optimized learning activities are more in line with the user's needs and learning rhythm, and improve the user's learning efficiency and learning effect.

[0072] Further, for the acquisition of the user's learning data, the user's interest tags and learning ability tags are extracted through a preset user behavior analysis model to generate user status tags, including:

[0073] S201. Obtain the learning data of the user by collecting the user's behavior logs, learning duration, and interaction records.

[0074] S202. According to the learning data, extract the interest tags and learning ability tags of the user through a preset user behavior analysis model.

[0075] S203. Integrate the interest tags and learning ability tags to generate user status tags.

[0076] In this embodiment, first, collect the operation data of the user to obtain the user's behavior logs, learning duration, and interaction records. The behavior logs record the user's access, selection, and operation behaviors on learning resources; the learning duration reflects the time cost invested by the user in learning; the interaction records reflect the interaction situation of the user with learning content, other users, or platform functions. Combine the collected data to obtain the learning data of the user. By collecting multi-dimensional learning data of the user, the learning behavior of the user can be understood from different perspectives, avoiding analysis deviations caused by single data, and providing comprehensive data for analyzing the user's learning status.

[0077] Exemplarily, for an online language learning platform, user B opened the course page of "Basic English Grammar" 3 times in a day, staying for 10 minutes, 15 minutes, and 20 minutes respectively each time; watched the video of "Tense Explanation" with a total duration of 30 minutes and actually watched for 28 minutes; posted a question post about the usage of "Present Perfect Tense" in the course discussion area and received 2 replies.

[0078] Specifically, according to the collected learning data, analyze the user's interests and learning abilities, and extract the interest tags and learning ability tags of the user through a preset user behavior analysis model; perform preprocessing such as cleaning and standardizing the collected learning data to obtain the preprocessed learning data. The preset user behavior analysis model can be a model such as a random forest model or a statistical model.

[0079] Exemplarily, the user behavior analysis model in this embodiment adopts a random forest model, and trains the user behavior analysis model through a large amount of historical learning data and the corresponding user status tags to obtain a pre-trained user behavior analysis model. The model learns the mapping relationship between the data and the tags. When new user learning data is input, the model can analyze the user's preference degree for different learning contents according to the learned rules, and extract interest tags; at the same time, the model evaluates the user's performance in learning tasks, such as test scores, learning progress, etc., judges the user's learning ability, and generates learning ability tags. By extracting interest tags and learning ability tags, the potential interests and true learning abilities of the user can be accurately mined, providing a basis for formulating corresponding learning activities.

[0080] Specifically, by combining the interest tags and learning ability tags, user status tags are generated. The interest tags and learning ability tags are permutated and combined, and combined with the user's learning preferences, concerns, as well as the user's strengths and weaknesses in learning. After fusion, a comprehensive and integrated user status description is obtained, providing more comprehensive user information, and can better meet the personalized needs of users when formulating learning activities and recommending learning resources, improving the user's learning experience.

[0081] Exemplarily, for the user's interest tag "Business English" and learning ability tag "Stronger English interpretation learning ability, weaker English listening learning ability", after format unification and fusion, the generated user status tag is {Interest: Business English; Learning Ability: Stronger English interpretation learning ability, weaker English listening learning ability}.

[0082] Further, based on the user status tag, combined with a preset course knowledge base, a corresponding activity generation path is generated, including:

[0083] S301. Extract the user's interest characteristics and ability characteristics according to the user status tag, and construct a user status vector;

[0084] S302. Based on the user status vector, perform matching in the preset course knowledge base to generate an activity generation path.

[0085] In this embodiment, according to the user status tag, the user's interest characteristics and ability characteristics are extracted, and the corresponding characteristics are mapped into the vector space to construct a user status vector; according to the interest tag in the user status tag, the keywords of the interest and the corresponding interest degree are extracted as the interest characteristics. For example, if the user has a high interest in the field corresponding to the interest keyword, a higher value is assigned, such as 10; if the interest is average, the value is 5; if there is no interest, the value is 0; according to the learning ability tag, the learning ability is quantified to obtain a quantitative index reflecting the strength of the user's learning ability; for example, when the learning ability tag is "Stronger mathematics learning ability", a value is set within the range of 0-10, and "stronger" is assigned 8; if it is "Weaker programming learning ability", "weaker" is assigned 3; the extracted interest characteristics and ability characteristics are combined to construct a user status vector. By constructing the user status vector, courses and learning resources that match the user status can be quickly found.

[0086] Specifically, based on the user status vector, it matches in the preset course knowledge base, searches for course knowledge with a relatively high matching degree with the user's interests and abilities, and arranges the matched courses in the corresponding logical order according to the logical relationships between the course knowledge, including the logical relationships and progressive relationships of knowledge points, etc., to generate an activity generation path, and plans a learning route that meets the user's needs for the user; by planning the activity generation path, it provides a direction for the formulation of learning activities, accurately finds courses that match the user's interests and abilities, avoids the user from learning content that is not interested in or beyond their own ability range, and through reasonable planning of the course order, it can ensure the coherence and systematicness of the learning process, help the user achieve learning goals more efficiently, and improve the user experience.

[0087] Further, the generating an activity generation path by matching in the preset course knowledge base based on the user status vector includes:

[0088] S401. Based on the preset course knowledge base, use knowledge activities as activity nodes, establish associations between activity nodes according to knowledge associations and activity difficulty, and construct a knowledge graph;

[0089] S402. According to the user status vector, match corresponding learning activities in the knowledge graph to obtain a set of candidate paths;

[0090] S403. By calculating the matching value between each path in the set of candidate paths and the user status vector, select the path with the highest matching value in the set of candidate paths as the activity generation path.

[0091] In this embodiment, first, according to the preset course knowledge base, use knowledge activities as activity nodes, and use the internal associations between knowledge and the progressive relationships of activity difficulty, etc. as the edges between activity nodes; by analyzing the logical relationships between the knowledge points involved in each knowledge activity in the course knowledge base, including the sequence, inclusion relationship, parallel relationship, etc.; for example, in the mathematics course, the "concept of function" is the basis of the "graph and properties of function", and there is a knowledge association of sequence between the two. According to the corresponding knowledge association, establish edges between the corresponding activity nodes, and integrate the determined activity nodes and the established associated edges to form a complete knowledge graph; by constructing the knowledge graph, the knowledge activities in the course knowledge base can be associated, and the connections between different learning activities and the direction of the learning path can be displayed, so as to quickly match the corresponding activity generation path in the knowledge graph.

[0092] Such as Figure 2, based on the user state vector, perform matching in the knowledge graph, filter out activity nodes that meet the user's interests and capabilities, and based on the association relationships between nodes in the knowledge graph, starting from these matching nodes, search for corresponding learning paths to form a candidate path set; perform feature matching according to the interest features and ability features in the user state vector respectively. When the value corresponding to an interest keyword in the user state vector is relatively high and the knowledge domain of a certain activity node contains this keyword, it is considered that this activity node matches the user's interest; according to the user's ability quantization value, filter out activity nodes whose difficulty levels match it; combining the results of interest matching and ability matching, match to obtain activity nodes that satisfy both the user's interest and ability; starting from the matching nodes, combining the association edges between activity nodes in the knowledge graph, search for corresponding learning paths to form a candidate path set; by filtering out various learning paths that meet the user's personalized needs, comprehensively considering the user's interests and capabilities, providing a reference for the learning route, avoiding the problem that a single fixed learning path cannot meet the needs of different users, and improving the flexibility and adaptability of learning path planning.

[0093] Specifically, after filtering out the candidate path set, analyze the matching degree between each path in the candidate path set and the user state vector, calculate the corresponding matching value, and select the path with the highest matching value as the activity generation path; by calculating the matching value to select the corresponding activity generation path, it is possible to filter out the learning path that best matches the user's interests and capabilities, ensure that the user can access learning content that is interesting and matches their learning ability during the learning process, improve the enthusiasm and effect of learning, and at the same time optimize the use efficiency of learning resources and provide a better learning experience for users.

[0094] Exemplarily, for interest matching calculation, set the calculation rule for the matching score between the knowledge domain keywords of each activity node and the interest keywords in the user state vector; for example, if the knowledge domain of the activity node completely contains the user's interest keyword, the score is 1; if it partially contains, assign a score between 0 and 1 according to the degree of inclusion; if it does not contain, the score is 0. Add up the interest matching scores of all activity nodes in the path to obtain the total interest matching score of this path. For ability matching calculation, set the calculation rule for the matching score between the difficulty level of the activity node and the ability quantization value in the user state vector; for example, when the difficulty level of the activity node completely matches the user's ability quantization value, the score is 1; if it is slightly higher or slightly lower in difficulty, assign a score between 0 and 1 according to the size of the gap; if the gap is too large, the score is 0. Add up the ability matching scores of all activity nodes in the path to obtain the total ability matching score of this path; combining the total interest matching score and the total ability matching score, through weighted summation, such as the total interest matching score accounting for 60% and the total ability matching score accounting for 40%, calculate the final matching value of each path and the user state vector.

[0095] Further, generating a path according to the activity and matching corresponding learning activities to obtain initial learning activities includes:

[0096] S501. According to the activity generation path, match corresponding first learning activities for each activity node in a preset activity template library;

[0097] S502. Optimize the first learning activities based on the user state vector to obtain second learning activities;

[0098] S503. Combine the second learning activities in the order of activity nodes in the activity generation path to obtain initial learning activities.

[0099] In this embodiment, according to the activity generation path, corresponding learning activities are matched for each activity node in the preset activity template library to obtain suitable first learning activities; various types of learning activity templates are stored in the preset activity template library, and each learning activity template corresponds to specific knowledge content, teaching objectives, and activity forms, including learning activities such as video courses, online tests, and group discussions. Analyze the attributes of each learning activity template in the activity template library, including information such as the knowledge field, teaching objectives, activity form, and applicable difficulty level targeted by the template. Compare the attributes of the activity node with the attributes of the activity template, giving priority to matching the knowledge field to ensure that the knowledge involved in the template is consistent with the requirements of the activity node; then match the learning objectives to analyze whether the activity template can meet the learning objectives set by the activity node; finally, consider the difficulty level to ensure that the template difficulty is suitable for the activity node difficulty. When the attributes of the activity template match the attributes of the activity node, use this template as the first learning activity corresponding to the activity node, and match corresponding first learning activities for each activity node in the activity generation path in the activity template library. By matching the first learning activities, specific learning activities can be quickly generated according to the activity generation path, improving the efficiency of learning activity generation.

[0100] Specifically, after matching the first learning activities, compare and analyze the user state vector with the relevant attributes of the first learning activities, adjust the activity content and form according to the user's interest preferences, adjust the difficulty and progress of the activity according to the user's learning ability, optimize the first learning activities to obtain second learning activities that better meet the user's needs. Optimizing the first learning activities based on the user state vector can fully consider the different needs of different users, make the learning activities better meet the interests and ability needs of each user, improve the user's participation and enthusiasm for learning activities by adjusting the activity content, form, difficulty, and progress, reduce learning barriers caused by unsuitable learning activities, and help improve the user's learning effect and learning experience.

[0101] Exemplarily, when the content of the first learning activity involves a knowledge area that the user is interested in, the depth or breadth of the relevant content can be increased, or the activity form can be adjusted to a form that the user prefers more. For example, if the user is interested in "artificial intelligence" and the first learning activity is about Python programming, programming cases related to artificial intelligence can be added to the programming exercises; for users with stronger learning abilities, the difficulty of the activity can be increased, such as providing more complex exercise questions or extended content; for users with weaker learning abilities, the difficulty can be reduced, splitting complex tasks into multiple simple subtasks, or extending the learning time.

[0102] Specifically, according to the sequence of learning activities in the activity generation path, the optimized second learning activities are arranged and combined in sequence to obtain the initial learning activity; for example, the activity generation path is "English vocabulary accumulation → English grammar learning → English short essay writing", and the corresponding second learning activities are "English high-frequency vocabulary memory video course and word spelling practice", "English grammar intensive online course and grammar filling exercise", "English short essay writing skill explanation and theme writing task"; according to the node sequence of the activity generation path, these three second learning activities are combined to obtain the initial learning activity. By combining learning activities, the user follows the logical sequence of knowledge and learning rules during the learning process, avoiding chaos and jumps in the learning process, which helps to improve the learning efficiency and effect.

[0103] Furthermore, by combining the user's real-time learning status, the activity generation path is optimized by adding path branches, pruning path branches, or path node replacement to obtain an activity optimization path, including:

[0104] S601. According to the user's real-time learning status, by analyzing the activity node density and dependency relationship in the activity generation path, identify the path optimization area;

[0105] S602. Optimize the path optimization area by adding path branches, pruning path branches, or path node replacement to obtain the first optimization path;

[0106] S603. Optimize the activity generation path according to the first optimization path to obtain the activity optimization path.

[0107] In this embodiment, according to the user's real-time learning status, the activity node density and dependency relationship in the activity generation path are analyzed. A too-high node density indicates that the learning content is too compact and difficult for the user to digest; a too-low node density indicates slow learning progress and incoherent content; the dependency relationship of activity nodes represents the sequence and logical association of knowledge learning. By analyzing the activity node density and dependency relationship, the part that does not match the user's real-time learning status in the current activity generation path is identified to obtain the path optimization area. According to the collected user real-time learning data, the user's real-time learning status is analyzed. The activity generation path is divided according to knowledge modules or learning stages, the number of activity nodes in each divided area is counted, the activity node density is calculated, and by comparing the activity node densities in different areas, the areas with abnormal density (too high or too low) are found. By analyzing the sequence and logical dependency relationship between each activity node in the activity generation path, unreasonable dependency relationships are identified. For example, when the user's test score in a certain knowledge module is poor and the node density in this activity area is too high, it means that the user has difficulty understanding the overly compact learning content, and this area is used as the path optimization area. When the user can complete subsequent activity nodes by skipping a certain precondition activity node, the relevant node area involved can also be used as the path optimization area. By identifying the path optimization area, the part that does not match the user's real-time learning status can be located, avoiding blindly modifying the entire path, and improving the pertinence and efficiency of path optimization.

[0108] Such as Figure 3 , the path optimization area is optimized by adding path branches, pruning path branches, or replacing path nodes to obtain the first optimized path. Adding path branches is to introduce new activity nodes or sub-paths in the path optimization area to supplement the knowledge or skills lacking by the user; pruning path branches is to remove unnecessary or inappropriate activity nodes or sub-paths for the user's current learning status, reducing the learning burden and preventing the user from wasting time on irrelevant content; path node replacement is to replace the original nodes with activity nodes more suitable for the user's current learning status to improve the learning effect. According to the specific situation of the path optimization area and the user's real-time learning status, a suitable optimization method is selected to adjust it to obtain the optimized first optimized path. By optimizing the path optimization area, the learning path can be flexibly adjusted according to the user's real-time learning status to meet the user's personalized learning needs, timely fill knowledge gaps, remove redundant content, and improve the pertinence and effectiveness of learning activities.

[0109] Specifically, according to the first optimized path, optimize the activity generation path, replace the original path optimization area part, obtain the activity optimized path, check the replaced activity generation path to see if the overall logic of the path is reasonable, whether the order and association relationship between each activity node are correct, optimize the path, such as adjusting the transition description between activity nodes, supplementing necessary learning tips, etc., to obtain the complete activity optimized path; integrating the first optimized path into the activity generation path to obtain the activity optimized path ensures the integrity and coherence of the learning path optimization, can better adapt to the user's real-time learning state, improve the quality and practicality of the learning path, and helps the user complete the learning task more smoothly and achieve the learning goal.

[0110] Further, optimizing the path optimization area by adding path branches, pruning path branches or replacing path nodes to obtain the first optimized path includes:

[0111] S701. Analyze the user's real-time interest and learning activity completion rate according to the user's real-time learning state;

[0112] S702. Add path branches corresponding to the activities in the path optimization area according to the real-time interest to obtain the first optimization area;

[0113] S703. When the learning activity completion rate is lower than the preset completion rate threshold, prune the path branches of the corresponding activities to obtain the second optimization area;

[0114] S704. Replace the path nodes with a matching degree less than the preset matching degree threshold by analyzing the matching degree between the real-time learning state and the knowledge graph to obtain the third optimization area;

[0115] S705. Combine the first optimization area, the second optimization area and the third optimization area to obtain the first optimized path.

[0116] In this embodiment, according to the user's real-time learning state, analyze the user's current stage of interest and the completion of learning activities. By analyzing the real-time interest, the knowledge fields that the user is currently concerned about and interested in can be obtained, so as to supplement the learning content that is more in line with the user's interest for the user; the learning activity completion rate reflects the progress and effect of the user when performing the learning task, and judges whether the learning activity is suitable for the user; by analyzing the user's real-time interest and learning activity completion rate, it provides a direction for path optimization, so as to meet the user's personalized learning needs and improve the fit between the learning activity and the user.

[0117] Exemplarily, during the process of user F learning the "Business English" course, the platform collected the following data: User F posted 3 posts about "Business English negotiation skills" in the discussion area and searched for relevant learning materials 5 times; in the learning activity of "Business English email writing", 8 email writing exercises and 3 teaching videos were required, and the user completed 3 exercises and watched 1 video; through analysis, it was determined that the real-time interest of user F was "Business English negotiation skills"; the completion rate of the learning activity of "Business English email writing" was calculated as (3 / 8×0.6 + 1 / 3×0.4)≈0.39, that is, 39%.

[0118] Specifically, according to the user's real-time interest, corresponding learning activities are matched, and activities suitable for the user's current learning stage and ability level are screened out. In the path optimization area, a learning activity path branch corresponding to the real-time interest is inserted. According to the knowledge logic relationship and learning sequence, the connection method between the new branch and the original path node is determined to ensure the coherence and logic of the path. After adding the path branch, the first optimization area including the new learning activity is obtained; by adding the path branch, the change of the user's interest can be responded to, more interesting learning content can be provided for the user, the learning enthusiasm and participation of the user can be improved, the learning path can be made more personalized and attractive, and the user's learning experience can be enhanced.

[0119] Specifically, when the completion rate of the learning activity is lower than the preset threshold, it means that the user encounters difficulties or is not interested in the activity when performing the learning activity. Continuing to retain the activity will affect the user's learning progress and enthusiasm. The corresponding path branch is trimmed to remove the learning content that is not suitable for the user, reduce the learning burden, and make the learning path more concise and efficient; by trimming the path branch, the learning burden of the user can be reduced, and the effectiveness and learning efficiency of the learning path can be improved.

[0120] Specifically, according to the matching degree between the user's real-time learning state and the knowledge graph, the path nodes with a matching degree less than the preset matching degree threshold are replaced to obtain the third optimization area. When the matching degree is less than the preset matching degree threshold, it means that the path node is not suitable for the user's current state. By replacing it with a more suitable node, the learning path is optimized to make it more suitable for the user's learning needs. By calculating the cosine similarity between the user's real-time learning state vector and each path node vector in the knowledge graph, the corresponding matching degree is obtained; for the path nodes with a matching degree less than the preset matching degree threshold, nodes with a higher matching degree and more suitable for the user's current learning stage and ability are searched in the knowledge graph for replacement, and the association relationship between the nodes is updated; by analyzing the matching degree between the real-time learning state and the knowledge graph to replace the path nodes, it can be ensured that the content learned by the user matches the actual situation of the user, and the pertinence and effectiveness of learning can be improved.

[0121] Merge the path content of the first optimization region, the second optimization region, and the third optimization region, remove the duplicate parts, retain the valid learning activity nodes and path branches, sort out the integrated path, check whether the sequence and logical relationship between the activity nodes are reasonable, and adjust the connection relationship between the nodes to obtain the final first optimized path. By optimizing the path in different ways, various factors such as the user's interests, learning effects, and knowledge system adaptability are fully considered, providing the user with a learning route that better meets their own needs, helping to improve learning efficiency, enhance learning effects, and comprehensively improve the user's learning experience and learning achievements.

[0122] Further, optimize the initial learning activity through the activity optimization path to obtain an optimized learning activity for dynamically optimizing the interactive learning activity, including:

[0123] S801. According to the activity optimization path, perform hierarchical optimization on the initial learning activity to obtain the corresponding first optimized activity;

[0124] S802. Combine the first optimized activities to obtain an optimized learning activity for dynamically optimizing the interactive learning activity.

[0125] In this embodiment, according to the activity optimization path, perform hierarchical optimization on the initial learning activity, optimize the initial learning activity according to different dimensions, and perform targeted optimization on learning activities at different levels according to the adjustment requirements for each part in the activity optimization path, so that each learning activity can better fit the user's current learning needs and status, thereby obtaining the first optimized activity; by performing hierarchical optimization on the initial learning activity, the optimization can be made more meticulous and comprehensive, meeting the user's learning needs, avoiding the problem of inaccurate optimization caused by general adjustment of learning activities, improving the effect and efficiency of optimization, and helping to improve the quality of learning activities.

[0126] Specifically, the first optimized activity is combined according to the corresponding logical order and learning rules to form a complete and coherent learning activity sequence, obtaining an optimized learning activity; the combination order of the first optimized activity is determined according to the order of activity nodes in the activity optimization path and the logical relationship between learning activities (including the sequence of knowledge, the progressive relationship of skill cultivation, etc.); for example, in programming learning, the learning activity of programming language basics should be carried out first, and then the learning activities related to data structures and algorithms; the learning content in the first optimized activity is integrated in sequence, checking whether the transition between adjacent activities is natural, whether there is duplication or omission in the content, streamlining the duplicated content, and supplementing the missing key knowledge points or skill training to ensure the coherence and integrity of the learning activity content; the connection between learning activities is optimized to obtain an optimized learning activity; by combining the optimized activities, the systematicness and coherence of the learning activities are ensured, which helps users better understand and master knowledge and skills, can better meet the user's learning needs that change in real time, improve the learning effect and the user's learning experience, and enhance the guiding and promoting effect of the learning activities on the user's learning.

[0127] Further, the initial learning activity is hierarchically optimized according to the activity optimization path to obtain the corresponding first optimized activity, including:

[0128] S901. According to the optimized activity nodes in the activity optimization path, match the corresponding learning activities in the preset activity template library to obtain optimized activities;

[0129] S902. Replace the corresponding learning activities in the initial learning activity with the optimized activities and adjust the order and duration of the learning activities to obtain the first optimized activity.

[0130] In this embodiment, according to the optimized activity nodes in the activity optimization path, activity matching is performed in the preset activity template library to match the corresponding learning activities to obtain optimized activities; analyze the attributes such as the knowledge field, learning objective, and difficulty level of each optimized activity node in the activity optimization path to obtain the attributes of the optimized activity nodes; compare the attributes of the optimized activity nodes in the activity optimization path with the attributes of the templates in the activity template library, first match the knowledge field to ensure that the knowledge involved in the template is consistent with the node requirements; then match the learning objective to analyze whether the template can meet the learning objective set by the node; then match the difficulty level to ensure that the template difficulty is suitable for the node difficulty; finally, consider factors such as activity form and learning duration to select the matching activity template; match the corresponding optimized activity for each optimized activity node in the activity optimization path; by matching the optimized activities, learning activities that meet the current learning needs changes of users can be found quickly and efficiently, ensuring a high degree of matching between the optimized activities and user needs.

[0131] Specifically, use the matched optimized activity to replace the corresponding learning activity in the initial learning activity, and adjust the order and duration of the learning activity to obtain the first optimized activity. In the initial learning activity, find the learning activity corresponding to the optimized activity node in the activity optimization path, replace the corresponding original activity in the initial learning activity with the corresponding optimized activity, and adjust the order of the replaced learning activities according to the order of each activity node in the activity optimization path to ensure that the entire learning activity sequence conforms to the new learning path logic. Combine the learning duration of the optimized activity, the overall learning plan, and the user's learning time arrangement to adjust the duration of the learning activity, and make corresponding adjustments to the start time and duration of the subsequent learning activities to ensure that the time arrangement of the entire learning activity sequence is reasonable and compact. After activity replacement, order adjustment, and duration adjustment, the complete first optimized activity is obtained. By replacing the initial learning activity with the optimized activity and adjusting the order and duration, the learning activity can quickly adapt to the changes in the user's learning state, update the learning content in a timely manner, ensure the logic and fluency of the learning process, meet the user's current learning needs, and improve the user's learning experience and learning effect.

[0132] Exemplarily, the original order of the initial learning activities is "Python Basic Syntax Learning (3 hours) → Python Web Development Basics (5 hours) → Python Data Processing (4 hours)". After replacing the "Python Web Development Basics" learning activity with the "Django Advanced Framework Application Practical Course", according to the order requirements of the activity optimization path, it is adjusted to "Python Basic Syntax Learning (3 hours) → Django Advanced Framework Application Practical Course (8 hours) → Python Data Processing (4 hours)". At the same time, considering the overall learning progress and the user's daily available learning time, the duration of "Python Basic Syntax Learning" is adjusted to 2 hours, and the duration of "Python Data Processing" is adjusted to 3 hours. Finally, the first optimized activity is obtained: "Python Basic Syntax Learning (2 hours) → Django Advanced Framework Application Practical Course (8 hours) → Python Data Processing (3 hours)".

[0133] Embodiment 2:

[0134] In this embodiment, as Figure 4 shown, an interactive learning activity dynamic optimization system is provided for implementing the described interactive learning activity dynamic optimization method, including:

[0135] A user state analysis module that obtains the user's learning data, extracts the user's interest tags and learning ability tags through a preset user behavior analysis model, and generates user state tags;

[0136] An activity generation path formulation module generates a corresponding activity generation path based on the user status tags and in combination with a preset course knowledge base;

[0137] A learning activity formulation module matches corresponding learning activities according to the activity generation path to obtain initial learning activities;

[0138] An activity generation path optimization module optimizes the activity generation path by adding path branches, pruning path branches or replacing path nodes in combination with the user's real-time learning status to obtain an activity optimization path;

[0139] A learning activity optimization module optimizes the initial learning activities through the activity optimization path to obtain optimized learning activities so as to dynamically optimize the interactive learning activities.

[0140] In this embodiment, the user status analysis module extracts the user's interest tags and learning ability tags by collecting multi-dimensional learning data such as user behavior logs, learning duration, and interaction records and using a preset user behavior analysis model, and fuses the two to generate user status tags that comprehensively reflect the user's interests and abilities, providing an accurate user status basis for formulating and optimizing learning activities; the activity generation path formulation module extracts the user's interest and ability characteristics and converts them into vectors according to the user status tags generated by the user status analysis module. In the preset course knowledge base, by constructing a knowledge graph, it analyzes the associations and difficulties between knowledge activities, calculates the similarity between the user status vector and the course vector, matches the corresponding courses and resources, and arranges them in the order of knowledge logic to generate a personalized activity generation path, providing a direction for formulating learning activities.

[0141] Specifically, the learning activity formulation module matches the first learning activities for each node in the preset activity template library according to the activity generation path, and then optimizes the activity content, form, difficulty, and progress from the perspectives of interest and ability based on the user status vector to obtain the second learning activities. Finally, it combines them in the order of path nodes to form the initial learning activities, generating specific executable learning task activities; the activity generation path optimization module monitors the user's learning process data in real time, identifies the areas to be optimized by analyzing the node density and dependency relationships of the activity generation path, and dynamically adjusts the path by adding path branches that meet the user's real-time interests, pruning inefficient branches with low completion rates, and replacing path nodes with low matching degrees to the user status, ensuring that the learning path always fits the user's actual learning situation and improving the learning pertinence and effectiveness; the learning activity optimization module performs hierarchical optimization on the initial learning activities based on the activity optimization path to obtain the first optimized activities, and then integrates the content and adjusts the connection according to the order of path nodes and the activity logic relationship to combine the first optimized activities into optimized learning activities, realizing the dynamic optimization of interactive learning activities and bringing a better learning experience to the user.

[0142] The foregoing has shown and described the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and what is described in the above embodiments and the specification is only to illustrate the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will also have various changes and improvements, and these changes and improvements fall within the scope of the present invention claimed. The scope of the present invention claimed is defined by the appended claims and their equivalents.

Claims

1. An interactive learning activity dynamic optimization method, characterized in that including: Obtain the learning data of the user, extract the interest tags and learning ability tags of the user through a preset user behavior analysis model, and generate user status tags; Based on the user status tags, combine with a preset course knowledge base to generate a corresponding activity generation path; According to the activity generation path, match corresponding learning activities to obtain initial learning activities; Combine the real-time learning status of the user, and optimize the activity generation path by adding path branches, pruning path branches or replacing path nodes to obtain an activity optimization path; Through the activity optimization path, optimize the initial learning activities to obtain optimized learning activities, so as to dynamically optimize the interactive learning activities.

2. The dynamic optimization method for an interactive learning activity according to claim 1, wherein The obtaining the learning data of the user, extracting the interest tags and learning ability tags of the user through a preset user behavior analysis model, and generating user status tags includes: Obtain the learning data of the user by collecting the user's behavior logs, learning duration and interaction records; According to the learning data, extract the interest tags and learning ability tags of the user through a preset user behavior analysis model; Fuse the interest tags and learning ability tags to generate user status tags.

3. The dynamic optimization method for an interactive learning activity according to claim 1, characterized in that, The generating a corresponding activity generation path based on the user status tags and combining with a preset course knowledge base includes: Extract the interest characteristics and ability characteristics of the user according to the user status tags, and construct a user status vector; Based on the user status vector, perform matching in a preset course knowledge base to generate an activity generation path.

4. An interactive learning activity dynamic optimization method according to claim 3, characterized in that, The performing matching in a preset course knowledge base based on the user status vector to generate an activity generation path includes: Based on a preset course knowledge base, use knowledge activities as activity nodes, establish associations between activity nodes according to knowledge associations and activity difficulties, and construct a knowledge graph; According to the user status vector, match corresponding learning activities in the knowledge graph to obtain a candidate path set; By calculating the matching value between each path in the candidate path set and the user status vector, select the path with the highest matching value in the candidate path set as the activity generation path.

5. An interactive learning activity dynamic optimization method according to claim 1, characterized in that, The matching corresponding learning activities according to the activity generation path to obtain initial learning activities includes: According to the activity generation path, match corresponding first learning activities for each activity node in a preset activity template library; Based on the user status vector, optimize the first learning activities to obtain second learning activities; According to the order of activity nodes in the activity generation path, combine the second learning activities to obtain initial learning activities.

6. An interactive learning activity dynamic optimization method according to claim 1, characterized in that, The combining the real-time learning status of the user and optimizing the activity generation path by adding path branches, pruning path branches or replacing path nodes to obtain an activity optimization path includes: According to the real-time learning status of the user, identify a path optimization region by analyzing the activity node density and dependency relationship in the activity generation path; Optimize the path optimization region by adding path branches, pruning path branches or replacing path nodes to obtain a first optimization path; Optimize the activity generation path according to the first optimization path to obtain an activity optimization path.

7. An interactive learning activity dynamic optimization method according to claim 6, characterized in that Optimizing the path optimization region by adding path branches, pruning path branches, or replacing path nodes to obtain a first optimized path includes: Analyzing the user's real-time interests and learning activity completion rate according to the user's real-time learning status; Adding path branches corresponding to activities in the path optimization region according to the real-time interests to obtain a first optimized region; When the learning activity completion rate is lower than a preset completion rate threshold, pruning the path branches of the corresponding activity to obtain a second optimized region; Replacing path nodes with a matching degree less than a preset matching degree threshold by analyzing the matching degree between the real-time learning status and the knowledge graph to obtain a third optimized region; Combining the first optimized region, the second optimized region, and the third optimized region to obtain a first optimized path.

8. An interactive learning activity dynamic optimization method according to claim 1, characterized in that, Optimizing the initial learning activity through the activity optimization path to obtain an optimized learning activity for dynamically optimizing the interactive learning activity includes: Hierarchically optimizing the initial learning activity according to the activity optimization path to obtain a corresponding first optimized activity; Combining the first optimized activities to obtain an optimized learning activity for dynamically optimizing the interactive learning activity.

9. An interactive learning activity dynamic optimization method according to claim 8, characterized in that, The hierarchically optimizing the initial learning activity according to the activity optimization path to obtain a corresponding first optimized activity includes: Matching corresponding learning activities in a preset activity template library according to the optimized activity nodes in the activity optimization path to obtain optimized activities; Replacing the corresponding learning activities in the initial learning activity with the optimized activities and adjusting the order and duration of the learning activities to obtain a first optimized activity.

10. An interactive learning activity dynamic optimization system, characterized in that, Used to implement an interactive learning activity dynamic optimization method as described in any one of claims 1 to 9, including: A user status analysis module that obtains the user's learning data, extracts the user's interest tags and learning ability tags through a preset user behavior analysis model, and generates user status tags; An activity generation path formulation module that generates a corresponding activity generation path based on the user status tags in combination with a preset course knowledge base; A learning activity formulation module that matches corresponding learning activities according to the activity generation path to obtain an initial learning activity; An activity generation path optimization module that combines the user's real-time learning status and optimizes the activity generation path by adding path branches, pruning path branches, or replacing path nodes to obtain an activity optimization path; A learning activity optimization module that optimizes the initial learning activity through the activity optimization path to obtain an optimized learning activity for dynamically optimizing the interactive learning activity.

Images