Knowledge tracking method applying learning migration

Abstract

The invention discloses a knowledge tracking method applying learning migration, and relates to the related field of knowledge tracking processing, and the method comprises the steps: building a historical mathematical knowledge point set according to a historical learning log, and carrying out the analysis to obtain an initial mathematical knowledge point graph; updating the real-time mathematical knowledge point set to the initial mathematical knowledge point graph; obtaining a first mathematical knowledge point in the real-time mathematical knowledge point graph, and obtaining a target knowledge tracking record; reading a predetermined tracking feature, and performing feature matching on the first tracking record; and by taking the first predetermined coefficient as a weight, carrying out adjustment calculation on the first mastery obtained by carrying out variation weighting processing on the first tracking feature parameter to obtain a target mastery. The technical problem of low tracking and evaluation accuracy caused by difficulty in realizing effective migration and sharing among different courses or knowledge points in the existing knowledge tracking method is solved, and the technical effect of improving the knowledge tracking and evaluation accuracy by realizing effective migration and sharing among different courses or knowledge points is achieved.

Description

Technical Field

[0001] The present application relates to the field of knowledge tracking processing, and in particular to a knowledge tracking method using learning transfer. Background Art

[0002] With the rapid development of online education and intelligent learning systems, how to effectively track and evaluate students' learning progress and knowledge mastery has become a key issue. Knowledge tracking technology predicts and evaluates students' mastery of specific knowledge points by analyzing students' learning behaviors and historical data. However, traditional knowledge tracking methods mainly focus on tracking knowledge points within a single course, and evaluate students' mastery of knowledge points by analyzing students' learning behaviors within the course (such as answering questions, learning time, etc.). However, this method cannot achieve the transfer and sharing of knowledge points between different courses.

[0003] Among the current related technologies, knowledge tracking methods have the technical problem of being difficult to achieve effective migration and sharing between different courses or knowledge points, resulting in low accuracy in tracking and evaluation. Summary of the invention

[0004] The present application provides a knowledge tracking method for applied learning transfer, which adopts the method of forming a historical mathematics knowledge point set according to the historical learning log of the target user, and analyzing to obtain an initial mathematics knowledge point map, updating the real-time mathematics knowledge point set obtained by decomposing the target course to the initial mathematics knowledge point map to obtain the real-time mathematics knowledge point map, obtaining the first mathematics knowledge point in the real-time mathematics knowledge point map with the real-time mathematics knowledge point set as a constraint, and obtaining the target knowledge tracking record of the target user for the first mathematics knowledge point, reading a predetermined tracking feature, and performing feature matching on the first tracking record based on the predetermined tracking feature to obtain a first tracking feature parameter, obtaining a first predetermined coefficient, and using the first predetermined coefficient as a weight to adjust and calculate the first mastery degree obtained by weighting the variation of the first tracking feature parameter to obtain the target mastery degree and other technical means, thereby achieving the technical effect of improving the accuracy of knowledge tracking and evaluation by realizing effective migration and sharing between different courses or knowledge points.

[0005] This application provides a knowledge tracking method for application learning transfer, including: A historical mathematics knowledge point set is formed according to the historical learning log of the target user, and the historical mathematics knowledge point set is analyzed to obtain an initial mathematics knowledge point map; the real-time mathematics knowledge point set obtained by decomposing the target course is updated to the initial mathematics knowledge point map to obtain a real-time mathematics knowledge point map; the first mathematics knowledge point in the real-time mathematics knowledge point map is obtained with the real-time mathematics knowledge point set as a constraint, and the target knowledge tracking record of the target user for the first mathematics knowledge point is obtained, and the target knowledge tracking record includes a first tracking record; a predetermined tracking feature is read, and a feature matching is performed on the first tracking record based on the predetermined tracking feature to obtain a first tracking feature parameter; a first predetermined coefficient is obtained, and the first predetermined coefficient is used as a weight to adjust and calculate the first mastery degree obtained by weighting the variation of the first tracking feature parameter to obtain a target mastery degree, wherein the target mastery degree is used to characterize the mastery degree of the target user on the first mathematics knowledge point.

[0006] In a possible implementation, a historical mathematics knowledge point set is formed according to the historical learning log of the target user, and the historical mathematics knowledge point set is analyzed to obtain an initial mathematics knowledge point map, and the following processing is performed: A task database is established, wherein the task database includes a plurality of tasks with tags involving mathematical knowledge points; a first historical mathematical knowledge point and a second historical mathematical knowledge point in the historical mathematical knowledge point set are randomly obtained; it is determined whether the first historical mathematical knowledge point and the second historical mathematical knowledge point co-occur in the first tag involving mathematical knowledge points; if they co-occur, a first task corresponding to the first tag involving mathematical knowledge points is reversely matched, and the first task is added to a co-occurring task list; a ratio of the number of tasks in the co-occurring task list to the number of tasks in the task database is used as a correlation between the first historical mathematical knowledge point and the second historical mathematical knowledge point; and the initial mathematical knowledge point map is constructed by combining the first historical mathematical knowledge point and the second historical mathematical knowledge point with the correlation as a constraint.

[0007] In a possible implementation, the following processing is performed using the ratio of the number of tasks in the co-occurring task list to the number of tasks in the task database as the correlation between the first historical mathematics knowledge point and the second historical mathematics knowledge point: Obtain a first historical vector of the first historical mathematical knowledge point; obtain a second historical vector of the second historical mathematical knowledge point; obtain the similarity between the first historical vector and the second historical vector using the cosine similarity principle; and adjust the correlation using the similarity as a weight.

[0008] In a possible implementation, the first mathematical knowledge point in the real-time mathematical knowledge point graph is obtained with the real-time mathematical knowledge point set as a constraint, and the target knowledge tracking record of the target user for the first mathematical knowledge point is obtained, and the following processing is performed: Extract a second task from the multiple tasks with mathematical knowledge point labels, the second task corresponding to a second mathematical knowledge point label; determine whether the first mathematical knowledge point belongs to the second mathematical knowledge point label; if so, add the second task to a candidate task list; monitor the process of the target user processing each task in the candidate task list to obtain the target knowledge tracking record.

[0009] In a possible implementation, the process of the target user processing each task in the candidate task list is monitored to obtain the target knowledge tracking record, and the following processing is performed: Taking the first mathematical knowledge point as the center and a predetermined distance as the radius, the real-time mathematical knowledge point map is analyzed to determine the first associated mathematical knowledge point range of the first mathematical knowledge point; extract any associated mathematical knowledge point in the first associated mathematical knowledge point range; determine whether the any associated mathematical knowledge point belongs to a third-related mathematical knowledge point label; if so, add a third task corresponding to the third-related mathematical knowledge point label to the candidate task list.

[0010] In a possible implementation, the following processing is performed: The predetermined tracking features include task accuracy and unit task time.

[0011] In a possible implementation, a first predetermined coefficient is obtained, and the first predetermined coefficient is used as a weight to adjust and calculate the first mastery degree obtained by weighting the variation of the first tracking feature parameter to obtain a target mastery degree, and the following processing is performed: Reverse matching the first candidate task corresponding to the first tracking record, wherein the first candidate task corresponds to a first candidate mathematical knowledge point label; randomly extracting any candidate mathematical knowledge point in the first candidate mathematical knowledge point label; combining the real-time mathematical knowledge point map to obtain any correlation between the any candidate mathematical knowledge point and the first mathematical knowledge point; taking the mean of the any correlation as the first task migration index of the first candidate task, and recording the first task migration index as the first predetermined coefficient.

[0012] In a possible implementation, after obtaining any correlation between any candidate mathematical knowledge point and the first mathematical knowledge point in combination with the real-time mathematical knowledge point graph, the following processing is performed: The learning time of any candidate mathematical knowledge point is obtained; the learning time is analyzed in combination with a predetermined learning memory curve to obtain a memory coefficient of the target user for the any candidate mathematical knowledge point; and the arbitrary relevance is adjusted using the memory coefficient as a weight.

[0013] The knowledge tracking method for applied learning transfer proposed in this application first forms a historical mathematics knowledge point set according to the historical learning log of the target user, and analyzes the historical mathematics knowledge point set to obtain an initial mathematics knowledge point map, then updates the real-time mathematics knowledge point set obtained by decomposing the target course to the initial mathematics knowledge point map, and obtains the real-time mathematics knowledge point map, and then obtains the first mathematics knowledge point in the real-time mathematics knowledge point map with the real-time mathematics knowledge point set as a constraint, and obtains the target knowledge tracking record of the target user for the first mathematics knowledge point, the target knowledge tracking record includes a first tracking record, and then reads a predetermined tracking feature, and performs feature matching on the first tracking record based on the predetermined tracking feature to obtain a first tracking feature parameter, and finally obtains a first predetermined coefficient, and uses the first predetermined coefficient as a weight to adjust and calculate the first mastery degree obtained by weighting the variation of the first tracking feature parameter to obtain a target mastery degree, wherein the target mastery degree is used to characterize the mastery degree of the target user of the first mathematics knowledge point, thereby achieving a technical effect of improving the accuracy of knowledge tracking and evaluation by realizing effective migration and sharing between different courses or knowledge points. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A flowchart of a knowledge tracking method for application learning transfer provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of the process of obtaining an initial mathematical knowledge point map in the knowledge tracking method for applied learning transfer provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a knowledge tracking method for applying learning transfer, such as Figure 1 As shown, the method includes: Step S100, a historical mathematical knowledge point set is formed according to the historical learning log of the target user, and the historical mathematical knowledge point set is analyzed to obtain an initial mathematical knowledge point map. Specifically, a data crawler technology or an API interface is used to extract the historical learning log of the target user (such as a student) from the learning platform or system (such as an online education system, a learning management system, etc.). These logs record the mathematical knowledge points, exercise completion status, learning time and other information that the target user has learned in the past, including but not limited to: the user's login time and learning time; the user's learning progress in different mathematics courses; the exercises and test questions completed by the user and their answer status (such as correct rate, answer time, error type, etc.); the content of the discussion area in which the user participates (such as asking questions, answering questions, etc.). The extracted data is preprocessed, including data cleaning (removing invalid or duplicate data) and data formatting (converting data into a unified structured format). According to the historical learning log of the target user, the text content in the learning log (such as course name, exercise description, user questions, etc.) is analyzed using natural language processing (NLP) technology to extract all the mathematical knowledge points that the user has learned. Build a predefined mathematical knowledge point vocabulary and extract knowledge points from the log by keyword matching. For example, match keywords such as "linear equation" and "sum of interior angles of a triangle" with the text in the log. De-duplicate the extracted knowledge points and classify them according to the classification system of mathematical subjects (such as algebra, geometry, probability, etc.). According to the logical relationship between knowledge points (such as "linear equation" is a knowledge point under the "algebra" branch), build a hierarchical structure of knowledge points to form a historical mathematical knowledge point set, which includes various mathematical concepts, formulas, theorems, etc. that the target user has been exposed to in the past. Conduct an in-depth analysis of this historical mathematical knowledge point set to build an initial mathematical knowledge point map, define each mathematical knowledge point as a node in the map, and the attributes of the node include the name of the knowledge point, the subject classification to which it belongs, and the learning frequency. Define the edges between nodes according to the association between knowledge points (such as co-occurrence frequency, logical dependency, etc.). The weight of the edge is calculated by the co-occurrence frequency or cosine similarity of the knowledge point in the exercise. Use a graph database (such as Neo4j) or a graph visualization tool (such as Gephi) to store and display the initial mathematical knowledge point map. A graph is a graphical representation that can intuitively show the connections and relationships between various knowledge points. In this graph, each knowledge point is regarded as a node, and the lines between the nodes represent the degree of association or dependency between the knowledge points. For example, if two knowledge points often appear in the same question or the same course at the same time, then their distance in the graph will be relatively close, indicating that they are highly associated.

[0021] Take user A as an example. The knowledge points involved in his historical learning log include "linear equation" and "sum of interior angles of a triangle". Through co-occurrence frequency calculation, it is found that the correlation between "linear equation" and "quadratic equation" is high (weight is 0.8), while the correlation between "linear equation" and "sum of interior angles of a triangle" is low (weight is 0.2). The Gephi tool is used to visualize the mathematical knowledge map of user A. The line between the "linear equation" and "quadratic equation" nodes in the map is thicker, indicating that the correlation between them is strong.

[0022] like Figure 2As shown, in a possible implementation, a historical mathematical knowledge point set is formed according to the historical learning log of the target user, and the historical mathematical knowledge point set is analyzed to obtain an initial mathematical knowledge point map, and step S100 further includes step S110, forming a task database, and the task database includes multiple tasks with mathematical knowledge point labels. Specifically, a large number of mathematical exercises are collected from the learning platform (through API calls), the educational resource library (using Python and other programming languages ​​to write crawler programs to crawl exercise data) or the user's learning history (extracted from the user's learning behavior log), and each exercise is annotated with knowledge points, that is, the main mathematical knowledge points involved in each question are determined. The method of knowledge point annotation is: construct a predefined library containing all possible mathematical knowledge points. Use natural language processing (NLP) technology to analyze the text content of the exercises and automatically match the knowledge points in the predefined knowledge point library. The results of the automatic annotation are manually reviewed to ensure the accuracy of the annotation. For exercises that cannot be automatically annotated, they are manually annotated by professional teachers. The annotated exercises and their corresponding knowledge point labels are stored in the task database to form a set of tasks containing multiple mathematical knowledge point labels. Step S120, randomly obtain the first historical mathematics knowledge point and the second historical mathematics knowledge point in the set of historical mathematics knowledge points. Specifically, two mathematics knowledge points are randomly selected from the set of historical mathematics knowledge points as the first historical mathematics knowledge point and the second historical mathematics knowledge point for subsequent analysis. Step S130, determine whether the first historical mathematics knowledge point and the second historical mathematics knowledge point co-occur in the first involved mathematics knowledge point label. Specifically, check whether the two historical mathematics knowledge points appear at the same time in the involved mathematics knowledge point label of the same task (i.e., exercises). If so, it means that the two knowledge points are related to some extent. Step S140, if it is co-occurrence, reverse match the first task corresponding to the first involved mathematics knowledge point label, and add the first task to the co-occurrence task list. Specifically, if the two historical mathematics knowledge points co-occur, reversely find the exercises containing the two knowledge points, and use them as co-occurrence tasks, and add the found co-occurrence tasks to the co-occurrence task list, which is used to record which tasks involve the two knowledge points at the same time. Step S150, taking the ratio of the number of tasks in the co-occurring task list to the number of tasks in the task database as the correlation between the first historical mathematics knowledge point and the second historical mathematics knowledge point. Specifically, the correlation between the two historical mathematics knowledge points is evaluated by calculating the ratio of the number of tasks in the co-occurring task list to the total number of tasks in the task database. The higher the ratio, the higher the frequency of the two knowledge points appearing in the task, and therefore the higher the correlation between them. Step S160, taking the correlation as a constraint, combining the first historical mathematics knowledge point and the second historical mathematics knowledge point to construct the initial mathematics knowledge point map.Specifically, with the calculated relevance as a constraint, an initial mathematical knowledge point map is constructed by combining various historical mathematical knowledge points. In this map, the distance between knowledge points reflects the relevance between them. The knowledge points with higher co-occurrence frequency (i.e., greater relevance) are closer in the map. This implementation method infers the degree of association between knowledge points by analyzing the co-occurrence of knowledge points in tasks, thereby constructing a map that can reflect the internal connection between knowledge points, providing a basis for subsequent learning transfer and knowledge tracking.

[0023] In a possible implementation, the ratio of the number of tasks in the co-occurring task list to the number of tasks in the task database is used as the correlation between the first historical mathematics knowledge point and the second historical mathematics knowledge point. Step S150 further includes step S151, obtaining the first historical vector of the first historical mathematics knowledge point. Specifically, all learning tasks (i.e., exercises) related to the first historical mathematics knowledge point and their completion status (such as accuracy, time consumption, etc.) are extracted from the historical learning log. Based on these learning tasks and their completion status, features related to the first historical mathematics knowledge point, such as accuracy, error type, learning time, etc., are extracted. The extracted features are quantified and combined into a multidimensional vector as the historical vector of the first historical mathematics knowledge point. Step S152, obtaining the second historical vector of the second historical mathematics knowledge point. Similarly, all learning tasks related to the second historical mathematics knowledge point and their completion status are extracted from the historical learning log. Based on these learning tasks and their completion status, features related to the second historical mathematics knowledge point are extracted. The extracted features are quantified and combined into a multidimensional vector as the historical vector of the second historical mathematics knowledge point. Step S153, using the cosine similarity principle to obtain the similarity between the first historical vector and the second historical vector. Specifically, the two historical vectors are standardized so that their lengths (i.e., the modulus of the vectors) are 1. Then, the dot product of the two standardized historical vectors is calculated and divided by the product of their moduli to obtain the cosine similarity. The cosine similarity is an indicator to measure the degree of similarity between the directions of two vectors, and the value range is [-1, 1]. When the directions of the two vectors are exactly the same, the cosine similarity is 1; when the directions of the two vectors are completely opposite, the cosine similarity is -1; when the two vectors are perpendicular, the cosine similarity is 0. Step S154, adjusting the correlation using the similarity as a weight. Specifically, according to the cosine similarity obtained in step S153, a weight value is determined, and this weight value can be obtained by linear or nonlinear transformation according to the specific value of the cosine similarity. The correlation based on the co-occurrence frequency calculated in step S150 is multiplied by the weight value obtained in step S153 to obtain the adjusted correlation. The adjusted correlation not only considers the co-occurrence frequency between knowledge points, but also the similarity of their historical performance during the learning process. This implementation captures the similarity of the historical performance of knowledge points during the learning process by constructing historical vectors and calculating the cosine similarity between them, and comprehensively evaluates the degree of correlation between historical mathematical knowledge points. When the co-occurrence frequency of two historical mathematical knowledge points is high and their historical performance during the learning process is similar, it is considered that the correlation between the two knowledge points is strong. At the same time, by introducing cosine similarity as a weight to adjust the correlation, the deviation of the co-occurrence frequency calculation caused by factors such as data sparsity and noise is reduced to a certain extent, and the accuracy and robustness of the correlation evaluation are improved.

[0024] Step S200, the real-time mathematical knowledge point set obtained by decomposing the target course is updated to the initial mathematical knowledge point map to obtain a real-time mathematical knowledge point map. Specifically, when the target user starts to learn a new course or knowledge point, the target course (such as the currently studied mathematics course) is decomposed into multiple mathematical knowledge points to form a real-time mathematical knowledge point set, and the knowledge points in the real-time mathematical knowledge point set are added to the initial mathematical knowledge point map, and the relevance information (such as the association between the newly added knowledge points and other knowledge points) is updated to obtain a real-time mathematical knowledge point map. This map will be continuously updated and expanded with the learning progress of the target user to reflect the current knowledge mastery of the target user in real time. For example, after a student has learned "linear equations" and "quadratic equations", he begins to learn "inequalities". Then, in the updated real-time mathematical knowledge point map, a node representing "inequality" will be added, and according to the degree of association between "inequality" and other knowledge points (such as "linear equations"), corresponding lines will be added to the map.

[0025] Step S300, using the real-time mathematical knowledge point set as a constraint to obtain the first mathematical knowledge point in the real-time mathematical knowledge point map, and obtain the target knowledge tracking record of the target user for the first mathematical knowledge point, wherein the target knowledge tracking record includes the first tracking record. Specifically, in the real-time mathematical knowledge point map, one is selected as the first mathematical knowledge point (i.e., a new knowledge point or a knowledge point currently being learned) according to the current real-time mathematical knowledge point set (i.e., the knowledge point that the user is learning). Find exercises (tasks) related to the first mathematical knowledge point, monitor the process of the target user completing these exercises, record the completion status (such as accuracy, time consumption, etc.), and form a target knowledge tracking record. That is, the target knowledge tracking record reflects the completion of related exercises by the target user when learning the first mathematical knowledge point.

[0026] In a possible implementation, the first mathematical knowledge point in the real-time mathematical knowledge point map is obtained with the real-time mathematical knowledge point set as a constraint, and the target knowledge tracking record of the target user for the first mathematical knowledge point is obtained. Step S300 further includes step S310, extracting the second task from the multiple tasks with mathematical knowledge point tags, and the second task corresponds to the second mathematical knowledge point tag. Specifically, access the task database storing the mathematical knowledge point tags, and filter out all tasks containing mathematical knowledge point tags from the task database. According to a certain strategy (such as random selection, etc.), one of these tasks is selected as the second task, and the second task is associated with one or more mathematical knowledge point tags. Step S320, determine whether the first mathematical knowledge point belongs to the second mathematical knowledge point tag. Specifically, extract the mathematical knowledge point tag involved in the second task (i.e., the second mathematical knowledge point tag), match the first mathematical knowledge point with the second mathematical knowledge point tag, and determine whether the first mathematical knowledge point is included in these tags. Step S330, if it does, add the second task to the candidate task list. Specifically, if the first mathematical knowledge point belongs to the second mathematical knowledge point label, that is, the first mathematical knowledge point is related to the second task, the second task is added to the candidate task list, which is used to store tasks related to the first mathematical knowledge point. Step S340, monitor the process of the target user processing each task in the candidate task list to obtain the target knowledge tracking record. Specifically, the tasks in the candidate task list are assigned to the target user for practice or answering. Using technical means such as a learning management system or an intelligent teaching system, the process of the target user processing these tasks is monitored in real time, and various data of the target user in the process of processing the tasks are recorded, such as accuracy, answering time, error type, etc., which constitute the target knowledge tracking record. This implementation method accurately obtains the target user's learning and mastery of the knowledge point by monitoring the target user's process of processing tasks related to the current learning knowledge point.

[0027] In a possible implementation, the process of the target user processing each task in the candidate task list is monitored to obtain the target knowledge tracking record, and step S340 further includes step S341, taking the first mathematical knowledge point as the center and the predetermined distance as the radius, analyzing the real-time mathematical knowledge point map to determine the first associated mathematical knowledge point range of the first mathematical knowledge point. Specifically, the first mathematical knowledge point currently being learned is taken as the center point of the analysis, and a radius is set according to a predetermined distance (this distance can be a fixed value, or it can be dynamically adjusted according to the complexity of learning transfer and the relevance of the knowledge point). In the real-time mathematical knowledge point map, with the center point and the radius as constraints, search for other mathematical knowledge points associated with the first mathematical knowledge point in the map. All the searched associated mathematical knowledge points constitute a range, that is, the first associated mathematical knowledge point range of the first mathematical knowledge point. Step S342, extract any associated mathematical knowledge point in the first associated mathematical knowledge point range. Specifically, traverse all associated mathematical knowledge points in the first associated mathematical knowledge point range. Extract an associated mathematical knowledge point from the range randomly or according to a certain strategy (such as according to the strength of association, etc.) as the object currently being processed. Step S343, determine whether the arbitrary associated mathematical knowledge point belongs to the third mathematical knowledge point tag. Specifically, obtain the mathematical knowledge point tag of the currently processed associated mathematical knowledge point, and determine whether the tag matches a predetermined third mathematical knowledge point tag. Step S344, if it does, add the third task corresponding to the third mathematical knowledge point tag to the candidate task list. Specifically, if the tag of the currently processed associated mathematical knowledge point matches the third mathematical knowledge point tag, find the task associated with the tag, and add the found task to the candidate task list so that the target user can be monitored and evaluated later. This implementation method increases the relevance of learning transfer by searching for other mathematical knowledge points associated with the first mathematical knowledge point and adding the tasks corresponding to these knowledge points to the candidate task list, so that the learning materials are closer to the current learning needs of the target user. By monitoring the process of the target user processing these associated tasks, more data about the target user's mastery of the first mathematical knowledge point and its associated knowledge points can be collected, thereby improving the accuracy of the evaluation of the learning transfer effect.

[0028] Step S400, read the predetermined tracking features, and perform feature matching on the first tracking record based on the predetermined tracking features to obtain first tracking feature parameters. Specifically, some tracking features are predefined, including the accuracy of questions, etc. These features reflect the user's mastery of knowledge points. Read these predetermined tracking features, and perform feature matching with the first tracking record in the target knowledge tracking record to obtain first tracking feature parameters, such as accuracy parameters and time-consuming parameters.

[0029] In a possible implementation, step S400 further includes step S410, and the predetermined tracking features include task accuracy and unit task time. Specifically, the task accuracy is calculated by counting the target user's answers to the first mathematical knowledge point in exercises, tests or homework. For example, if the user correctly answers 8 times in 10 exercises, the task accuracy is 80%. Unit task time refers to the average time, that is, the sum of all related task times divided by the number of tasks. For example, if the user spends a total of 100 minutes in 10 exercises, the average time per exercise is 10 minutes. This implementation method comprehensively evaluates the target user's mastery of the first mathematical knowledge point by combining the task accuracy and unit task time. Relying solely on the accuracy will ignore the differences in time management or learning efficiency among users. Adding unit task time can more carefully reflect the user's learning status.

[0030] Step S500, obtain a first predetermined coefficient, and use the first predetermined coefficient as a weight to adjust and calculate the first mastery obtained by the variation weighted processing of the first tracking feature parameter to obtain a target mastery, wherein the target mastery is used to characterize the mastery of the first mathematical knowledge point by the target user. Specifically, obtain a first predetermined coefficient, which is a weight coefficient obtained based on the task migration index and is used to adjust the calculation of the target mastery. Since the target knowledge tracking record includes more than one tracking record, all first tracking feature parameters are subjected to variation weighted processing, including standardization of each feature parameter, weighted summation, etc., to obtain a comprehensive indicator reflecting the overall performance, that is, the initial mastery of the first mathematical knowledge point by the target user, that is, the first mastery, which is a quantitative value that reflects the overall performance of the target user when learning the first mathematical knowledge point. The following is an example of the calculation of the first mastery: each first tracking feature parameter is standardized so that its value range is unified within the range of [0,1]. The first tracking feature parameters include accuracy, completion time, and number of attempts, with weights of 0.5, 0.3, and 0.2, respectively. Correct rate = 0.8, completion time = 120 seconds, number of attempts = 3 times. The standardized values ​​are: Correct rate = 0.8, completion time = 0.6 (maximum time is 200 seconds), number of attempts = 0.5 (maximum number of attempts is 6 times). First mastery = 0.5*0.8+0.3*0.6+0.2*0.5=0.4+0.18+0.1=0.68. After obtaining the first mastery, adjust and calculate it according to the first predetermined coefficient, multiply the first mastery by the first predetermined coefficient to obtain the final target mastery. This indicator is used to characterize the target user's mastery of the first mathematical knowledge point, and can be used as a basis for subsequent learning recommendations, evaluation or feedback. The embodiment of the present application adopts the following technical means: assembling a historical mathematics knowledge point set according to the historical learning log of the target user, and analyzing to obtain an initial mathematics knowledge point map, updating the real-time mathematics knowledge point set obtained by decomposing the target course to the initial mathematics knowledge point map, obtaining the real-time mathematics knowledge point map, obtaining the first mathematics knowledge point in the real-time mathematics knowledge point map with the real-time mathematics knowledge point set as a constraint, obtaining the target knowledge tracking record of the target user for the first mathematics knowledge point, reading a predetermined tracking feature, and performing feature matching on the first tracking record based on the predetermined tracking feature to obtain a first tracking feature parameter, obtaining a first predetermined coefficient, and using the first predetermined coefficient as a weight to adjust and calculate the first mastery degree obtained by weighting the variation of the first tracking feature parameter to obtain the target mastery degree, etc., so as to achieve the technical effect of improving the accuracy of knowledge tracking and evaluation by realizing effective migration and sharing between different courses or knowledge points.

[0031] In a possible implementation, a first predetermined coefficient is obtained, and the first predetermined coefficient is used as a weight to adjust and calculate the first mastery degree obtained by weighting the variation of the first tracking feature parameter to obtain a target mastery degree. Step S500 further includes step S510, reverse matching the first candidate task corresponding to the first tracking record, wherein the first candidate task corresponds to the first candidate involved mathematical knowledge point label. Specifically, the learning log, task record or user-system interaction history is checked, and the learning task directly related to the first tracking record is identified by reverse matching using the task identifier or knowledge point label, i.e., the first candidate task. Step S520, randomly extract any candidate mathematical knowledge point in the first candidate involved mathematical knowledge point label. Specifically, after the first candidate task is determined, all mathematical knowledge point labels involved are extracted from the first candidate task. One of these knowledge point labels is randomly selected using a random selection algorithm as any candidate mathematical knowledge point. Any candidate mathematical knowledge point is used to evaluate the relevance and migration potential of the first mathematical knowledge point and other knowledge points. Step S530, combining the real-time mathematical knowledge point map to obtain any correlation between the any candidate mathematical knowledge point and the first mathematical knowledge point. Specifically, the real-time mathematical knowledge point graph is used to calculate the correlation between any candidate mathematical knowledge point and the first mathematical knowledge point. The correlation is calculated based on the distance between the knowledge points in the graph. Knowledge points with closer distances have higher correlation. The correlation can be calculated by the following formula: Correlation = ; Wherein, the distance refers to the shortest path length between two knowledge points in the mathematical knowledge point map. Step S540, take the mean of the arbitrary correlation as the first task migration index of the first candidate task, and record the first task migration index as the first predetermined coefficient. Specifically, calculate the mean of the correlation between all randomly extracted arbitrary candidate mathematical knowledge points and the first mathematical knowledge point. This mean is used as the first task migration index of the first candidate task, which reflects the difficulty of migrating from other related knowledge points to the first mathematical knowledge point. The first task migration index is recorded as the first predetermined coefficient for the adjustment calculation of the first mastery. This implementation method accurately evaluates the difficulty that the user may encounter when learning new knowledge points by calculating the task migration index (i.e., the first predetermined coefficient), improves the accuracy of the adjustment of the first mastery, and thus improves the accuracy of the target mastery.

[0032] The following is a specific example of obtaining the first predetermined coefficient: The learning record of a target user on "linear equation of one variable" is shown in Table 1: Table 1 Learning records Task ID Knowledge points involved Completion time T001 Linear equation 2024-01-01 T002 Quadratic equation 2024-01-05 T003 First degree equation of one variable, sum of interior angles of triangle 2024-01-10 The target knowledge point that needs to be evaluated currently is the first mathematical knowledge point, which is "linear equations with one variable". Traverse Table 1 to find tasks containing "linear equations with one variable". The tasks matched are T001 and T003. For task T001, the randomly selected knowledge point is "linear equations with one variable". For task T003, the randomly selected knowledge point is "sum of the interior angles of a triangle". As shown in Table 2, the real-time mathematical knowledge point map: Table 2 Real-time mathematics knowledge point map Knowledge Point A Knowledge Point B Shortest path length Linear equation Linear equation 0 Linear equation sum of interior angles of triangle 3 For Task T001: Knowledge point A = linear equation, Knowledge point B = linear equation, Shortest path length = 0, Relevance = =1.0. For Task T003: Knowledge point A = linear equation, Knowledge point B = sum of interior angles of a triangle, Shortest path length = 3, Relevance = =0.25. Calculate the mean of all correlations: First predetermined coefficient = First task transfer index = =0.625.

[0033] In a possible implementation, after obtaining any correlation between the arbitrary candidate mathematical knowledge point and the first mathematical knowledge point in combination with the real-time mathematical knowledge point map, step S530 further includes step S531, obtaining the learning time of the arbitrary candidate mathematical knowledge point. Specifically, access the learning history record of the target user or the relevant data in the learning management system (LMS) to obtain the learning time of the target user for each arbitrary candidate mathematical knowledge point. Specifically, extract the completion time of each arbitrary candidate mathematical knowledge point from the learning history record of the target user, use the system time or server time to record the current time point, subtract the current time point from the completion time of each arbitrary candidate mathematical knowledge point, and obtain the learning time. The learning time refers to the length of time from the target user completing the learning of a certain mathematical knowledge point to the current time point. Traverse all randomly extracted arbitrary candidate mathematical knowledge points, and collect corresponding learning time data for each knowledge point. Step S532, analyze the learning time in combination with a predetermined learning memory curve to obtain the memory coefficient of the target user for the arbitrary candidate mathematical knowledge point. Specifically, a predetermined learning memory curve (such as the Ebbinghaus forgetting curve) is used to analyze the learning time of each arbitrary candidate mathematical knowledge point, and a memory coefficient is calculated accordingly. Among them, the learning memory curve describes the law of human memory decay over time. Through this curve, the user's memory retention of the knowledge point after a period of time can be estimated. The memory coefficient is a value between 0 and 1, which represents the user's memory retention ratio of the knowledge point. For example, the Ebbinghaus forgetting curve is used as the mathematical model of the learning memory curve. The curve can be expressed by the following formula: ;in, It represents the memory retention ratio at time t, and τ is a constant representing the time constant of memory decay. According to the correspondence between the learning time and the learning memory curve, a memory coefficient is calculated for each arbitrary candidate mathematical knowledge point. That is, the learning time is substituted into the formula of the learning memory curve to calculate the memory retention ratio, which is the memory coefficient, indicating the target user's memory retention degree of any candidate mathematical knowledge point. The longer the learning time, the lower the memory coefficient, indicating that the user's memory retention degree of the knowledge point is lower.

[0034] Step S533, adjusting the arbitrary relevance using the memory coefficient as a weight. Specifically, after obtaining the memory coefficient of each arbitrary candidate mathematical knowledge point, these coefficients are used as weights to adjust the arbitrary relevance calculated previously. The adjusted relevance better reflects the actual difficulty of the target user migrating from any candidate mathematical knowledge point to the first mathematical knowledge point at the current time point. Knowledge points with higher memory coefficients (i.e., knowledge points that are better retained by users) are easier to migrate, so their relevance will be improved accordingly; conversely, knowledge points with lower memory coefficients are more difficult to migrate, so their relevance will be reduced accordingly. Finally, the first task migration index of the first candidate task is calculated using the adjusted relevance. This implementation method accurately evaluates the actual difficulty of migrating from these knowledge points to the first mathematical knowledge point through the learning time and memory coefficient of any candidate mathematical knowledge point, and improves the accuracy of obtaining the mastery of the first mathematical knowledge point.

[0035] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. The knowledge tracking method of applied learning transfer is characterized by: include: A historical mathematics knowledge point set is formed according to the historical learning log of the target user, and the historical mathematics knowledge point set is analyzed to obtain an initial mathematics knowledge point map; The real-time mathematics knowledge point set obtained by decomposing the target course is updated to the initial mathematics knowledge point map to obtain a real-time mathematics knowledge point map; Acquire a first mathematical knowledge point in the real-time mathematical knowledge point graph with the real-time mathematical knowledge point set as a constraint, and acquire a target knowledge tracking record of the target user for the first mathematical knowledge point, wherein the target knowledge tracking record includes a first tracking record; Reading a predetermined tracking feature, and performing feature matching on the first tracking record based on the predetermined tracking feature to obtain a first tracking feature parameter; A first predetermined coefficient is obtained, and the first predetermined coefficient is used as a weight to adjust and calculate the first mastery degree obtained by weighted variation processing of the first tracking feature parameter to obtain a target mastery degree, wherein the target mastery degree is used to characterize the mastery degree of the target user on the first mathematical knowledge point.

2. The knowledge tracking method for application learning transfer according to claim 1 is characterized in that: A historical mathematics knowledge point set is formed according to the historical learning log of the target user, and the historical mathematics knowledge point set is analyzed to obtain an initial mathematics knowledge point map, including: Establishing a task database, wherein the task database includes a plurality of tasks having labels related to mathematical knowledge points; Randomly acquiring a first historical mathematics knowledge point and a second historical mathematics knowledge point from the historical mathematics knowledge point set; Determine whether the first historical mathematics knowledge point and the second historical mathematics knowledge point co-appear in a first related mathematics knowledge point label; If it is co-occurrence, reversely match the first task corresponding to the first mathematical knowledge point label, and add the first task to the co-occurrence task list; Using the ratio of the number of tasks in the co-occurring task list to the number of tasks in the task database as the relevance between the first historical mathematics knowledge point and the second historical mathematics knowledge point; Taking the relevance as a constraint, the initial mathematics knowledge point map is constructed by combining the first historical mathematics knowledge point and the second historical mathematics knowledge point.

3. The knowledge tracking method for application learning transfer according to claim 2 is characterized in that: The method further comprises: using the ratio of the number of tasks in the co-occurring task list to the number of tasks in the task database as the correlation between the first historical mathematics knowledge point and the second historical mathematics knowledge point; Obtaining a first history vector of the first history mathematics knowledge point; Obtaining a second history vector of the second history mathematics knowledge point; Using the cosine similarity principle, the similarity between the first history vector and the second history vector is obtained; The relevance is adjusted using the similarity as a weight.

4. The knowledge tracking method for application learning transfer according to claim 2 is characterized in that: Acquiring a first mathematical knowledge point in the real-time mathematical knowledge point graph with the real-time mathematical knowledge point set as a constraint, and acquiring a target knowledge tracking record of the target user for the first mathematical knowledge point, including: Extracting a second task from the plurality of tasks having labels related to mathematical knowledge points, wherein the second task corresponds to a second label related to mathematical knowledge points; Determine whether the first mathematical knowledge point belongs to the second mathematical knowledge point label; If yes, add the second task to the candidate task list; The process of the target user processing each task in the candidate task list is monitored to obtain the target knowledge tracking record.

5. The knowledge tracking method for application learning transfer according to claim 4 is characterized in that: Monitoring the process of the target user processing each task in the candidate task list to obtain the target knowledge tracking record also includes: Taking the first mathematical knowledge point as the center and a predetermined distance as the radius, analyzing the real-time mathematical knowledge point map to determine a range of first associated mathematical knowledge points of the first mathematical knowledge point; Extracting any associated mathematical knowledge point in the first associated mathematical knowledge point range; Determine whether the any related mathematical knowledge point belongs to a third related mathematical knowledge point label; If yes, add the third task corresponding to the third mathematical knowledge point label to the candidate task list.

6. The knowledge tracking method for application learning transfer according to claim 1, characterized in that: The predetermined tracking features include task accuracy and unit task time.

7. The knowledge tracking method for application learning transfer according to claim 1 is characterized in that: Obtaining a first predetermined coefficient, and using the first predetermined coefficient as a weight, adjusting and calculating a first mastery degree obtained by weighting the variation of the first tracking feature parameter to obtain a target mastery degree, including: Reverse matching a first candidate task corresponding to the first tracking record, wherein the first candidate task corresponds to a first candidate mathematical knowledge point label; Randomly extract any candidate mathematical knowledge point from the first candidate mathematical knowledge point label; Combining the real-time mathematical knowledge point graph, obtaining any correlation between the any candidate mathematical knowledge point and the first mathematical knowledge point; An average value of the arbitrary correlations is taken as a first task migration index of the first candidate task, and the first task migration index is recorded as the first predetermined coefficient.

8. The knowledge tracking method for application learning transfer according to claim 7 is characterized in that: Combining the real-time mathematical knowledge point map to obtain any correlation between the any candidate mathematical knowledge point and the first mathematical knowledge point, and then further comprising: Obtain the learning time of any candidate mathematics knowledge point; Analyzing the learning time in combination with a predetermined learning memory curve to obtain a memory coefficient of the target user for the arbitrary candidate mathematical knowledge point; The arbitrary correlation is adjusted using the memory coefficient as a weight.

Images