Student cognitive path tracking and teaching recommendation methods, equipment, media and products

Abstract

This application relates to the field of smart teaching technology, and in particular to a method, device, medium, and product for tracking student cognitive paths and recommending teaching. The method includes: acquiring the answer data of a target student in a target assessment stage, where the target student is any student in the target class; accessing the teaching knowledge graph of the target assessment stage, where nodes represent knowledge points and edges represent dependencies between knowledge points; mapping the answer data to the teaching knowledge graph, identifying implicit pre-breakpoints, and constructing a dynamic knowledge graph of the target student based on these implicit pre-breakpoints; aggregating the dynamic knowledge graphs of all students in the target class to generate a list of common weak knowledge points; and pushing the list of common weak knowledge points to the teacher's end to guide the teacher in conducting focused teaching. This application can achieve accurate tracking of the cognitive path of an individual student and can also extract common learning problems at the group level, improving the relevance of teaching.

Description

Technical Field

[0001] This application relates to the field of smart teaching technology, and in particular to a method, device, medium and product for tracking student cognitive paths and recommending teaching methods. Background Technology

[0002] With the widespread application of smart education and knowledge graph technology in teaching evaluation and learning recommendation, current teaching scenarios urgently need technical solutions that can accurately pinpoint learning gaps based on student answer data and guide intensive classroom teaching. Most related smart teaching systems determine knowledge mastery and push learning content by collecting student assessment answer data and matching it with static teaching knowledge graphs. However, these systems generally struggle to accurately trace the root causes of students' unmastered knowledge points and cannot aggregate the weaknesses of the entire class to provide teachers with a basis for intensive teaching. Consequently, teaching recommendations and classroom instruction lack relevance and effectiveness. Summary of the Invention

[0003] To address the problem that existing technologies struggle to accurately trace fundamental knowledge gaps in students' cognitive chains, this application provides a method, device, medium, and product for tracking student cognitive paths and recommending instruction.

[0004] Firstly, this application provides a method for tracking student cognitive paths and recommending instruction, employing the following technical solution: A method for tracking student cognitive paths and recommending instruction includes: Obtain the answer data of the target student in the target assessment stage, wherein the target student is any student in the target class; The teaching knowledge graph of the target assessment stage is invoked, where nodes represent knowledge points and edges represent dependencies between knowledge points; The answer data is mapped to the teaching knowledge graph, implicit pre-breakpoints are identified, and a dynamic knowledge graph of the target student is constructed based on the implicit pre-breakpoints. Aggregate the dynamic knowledge graphs of all students in the target class to generate a list of common weak knowledge points; The list of common weak knowledge points will be pushed to the teacher's end to guide teachers in carrying out intensive teaching.

[0005] By adopting the above technical solution, the assessment answer data of individual students in the target class is collected, matched with the knowledge point-dependent teaching knowledge graph of the corresponding assessment link, and the mapping between the answer data and the knowledge system is completed. Implicit cognitive breakpoints are accurately located and an individual dynamic knowledge graph is built. Then, the learning situation of all students in the class is aggregated to generate a list of common weak knowledge points and pushed to the teacher. This not only realizes the accurate tracking of the cognitive path of individual students, but also extracts common learning problems from the group level, breaks down the barrier between individual learning situation and class teaching, provides teachers with targeted and centralized teaching basis, and greatly improves the pertinence of teaching.

[0006] In a preferred embodiment, this application can be further configured as follows: mapping the answer data to the teaching knowledge graph and identifying implicit pre-breakpoints includes: Extract the knowledge points to be assessed for each question from the answer data, and calculate the degree of mastery of each knowledge point by the target student based on the correctness of the target student's answers to each question. From the knowledge points involved in the answer data, select the knowledge points that have no prerequisite knowledge points in the teaching knowledge graph or whose prerequisite knowledge points do not appear in the answer data, and use them as starting knowledge points; Starting from each initial knowledge point, the teaching knowledge graph is traversed along its out-degree direction, and the knowledge points being assessed are linked together to form several knowledge point cognitive chains. For each knowledge point in the cognitive chain, the mastery level of each assessment knowledge point is checked sequentially from the preceding knowledge point to the following knowledge point, and the first assessment knowledge point whose mastery level is lower than the preset mastery level threshold is marked as an implicit preceding breakpoint.

[0007] By adopting the above technical solution, the system extracts assessment knowledge points based on answer data, calculates the individual's mastery of knowledge points, selects starting knowledge points without prior dependencies to construct a cognitive chain, and then checks the first unqualified knowledge point along the knowledge dependency sequence and marks it as an implicit prior breakpoint. This abandons the traditional judgment method of only looking at the surface of wrong questions, traces the root weakness along the knowledge logic, avoids misjudging subsequent knowledge point errors as weak cores, accurately locates students' cognitive gaps, and improves the accuracy and depth of learning diagnosis.

[0008] In a preferred embodiment, this application can be further configured as follows: the calculation of the target student's mastery of each assessment knowledge point based on the target student's correct and incorrect answers to each question includes: Obtain the timestamp of each question's answer, and divide the answer data into several stages according to a preset time window; For each stage, the frequency of each assessment knowledge point appearing in the stage assessment is counted, and based on the correctness of the answers to the questions in the stage and the frequency of the stage assessment, the stage mastery of each assessment knowledge point by the target student is calculated. Calculate the time interval between the intermediate timestamp of each stage and the current time, and assign stage weights to each stage according to the time decay rule. Based on the stage weights, the mastery level of each assessment knowledge point at each stage is weighted and summed to obtain the target student's mastery level of each assessment knowledge point.

[0009] By adopting the above technical solution, the answering stages are divided based on the answer timestamp. The mastery level of each stage is calculated by combining the frequency of stage assessments and the correctness of answers. Then, the stage weights are allocated based on the time decay rule and the weighted sum is obtained to obtain the final mastery level. This approach takes into account the correctness of answers, the frequency of assessments, and the time decay factor, weakens the influence of long-term answering performance, strengthens the weight of recent answering status, and is more in line with students' real-time cognitive level. It avoids the one-sidedness of judging a single wrong answer and makes the mastery assessment more in line with the actual learning situation.

[0010] In a preferred embodiment, this application can be further configured as follows: the construction of the dynamic knowledge graph of the target student based on the implicit pre-breakpoint includes: Copy all nodes and edge structures of the teaching knowledge graph as the basic framework of the dynamic knowledge graph; Mark the target student's mastery of each assessment knowledge point on the corresponding node; The identified implicit pre-breakpoints are marked as weak knowledge points; Along the out-degree direction of the dynamic knowledge graph, assess the risk coefficient of the subsequent knowledge points of each weak knowledge point, and mark the risk coefficient on the corresponding node; The output is a dynamic knowledge graph that includes the level of mastery, the weak knowledge points, and the risk coefficient.

[0011] By adopting the above technical solutions, a personalized dynamic graph is built by replicating the standard teaching knowledge graph framework. This graph marks the individual's mastery level, weak points, and risk coefficients of subsequent knowledge points. While fully preserving the knowledge dependencies, it also embeds personalized learning data, enabling a visual presentation of students' cognitive status. This not only clarifies the current root causes of weaknesses but also predicts subsequent learning risks, providing a complete data carrier for subsequent class learning aggregation and personalized tutoring.

[0012] In a preferred example, this application can be further configured as follows: the aggregation of the dynamic knowledge graph of all students in the target class to generate a list of common weak knowledge points includes: Traverse the dynamic knowledge graph of all students in the target class and extract each student's weak knowledge points and risk coefficient; For each knowledge point, the total frequency of the knowledge point being marked as a weak knowledge point in the target class is counted, and the average risk coefficient of the knowledge point as a subsequent knowledge point is calculated. Knowledge points whose total frequency exceeds a preset total frequency threshold or whose average risk coefficient exceeds a preset average risk coefficient threshold are identified as common weak knowledge points. All common weak knowledge points are compiled into a list of common weak knowledge points.

[0013] By adopting the above technical solution, the dynamic graph of all students in the class is traversed, the frequency of knowledge point weaknesses and average risk coefficients are statistically analyzed, common weaknesses are screened through dual thresholds and integrated into a list, and common problems of the class group are extracted from individual scattered learning situations. This takes into account both the breadth of weakness coverage and the height of potential learning risks, both locking in the high-frequency weaknesses of most students and not letting go of high-risk niche weaknesses, ensuring that the selected knowledge points have concentrated teaching value and simplifying the teacher's learning situation analysis process.

[0014] In a preferred embodiment, this application can be further configured such that the method also includes: Obtain the class answer data of the target class, and calculate the average mastery level and standard deviation of each knowledge point in the class; Based on the class average mastery level and the standard deviation, the mastery level threshold for each knowledge point is dynamically calculated and used as the preset mastery level threshold.

[0015] By adopting the above technical solution, based on the overall answer data of the class, the average mastery level and standard deviation of knowledge points are statistically analyzed, and a personalized mastery level threshold is dynamically generated. This avoids the drawbacks of a one-size-fits-all approach with a fixed threshold and adapts to the differences in learning situation and difficulty of different classes and different knowledge points.

[0016] In a preferred embodiment, this application can be further configured such that the method also includes: After the teachers complete the intensive teaching based on the list of common weak knowledge points, the post-test answer data of the students in the target class is obtained; Based on the post-test answer data, update the dynamic knowledge graph of each student; By comparing the average improvement in the mastery of common weak knowledge points in each class before and after intensive teaching and the average decrease in the risk coefficient, a teaching effectiveness evaluation report is generated. The teaching effectiveness evaluation report will be sent to the teacher's end.

[0017] By adopting the above technical solutions, post-test data is collected after centralized teaching, students' dynamic knowledge graphs are updated, and evaluation reports are generated by comparing the changes in core indicators before and after teaching and pushing them to teachers. This forms a complete teaching loop of "diagnosis-teaching-retesting-evaluation", which quantitatively verifies the effectiveness of centralized teaching, intuitively presents the improvement of weak points and the effect of risk mitigation, and provides data support for subsequent teaching optimization and remedial teaching.

[0018] Secondly, this application provides an electronic device that adopts the following technical solution: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform the student cognitive path tracking and instruction recommendation method as described in any of the first aspects.

[0019] Thirdly, this application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the student cognitive path tracking and instruction recommendation method as described in any of the first aspects.

[0020] Fourthly, this application provides a computer program product, which adopts the following technical solution: A computer program product includes a computer program that, when executed by a processor, implements the student cognitive path tracking and instruction recommendation method as described in any of the first aspects.

[0021] In summary, this application includes the following beneficial technical effects: This application collects assessment answer data from individual students in a target class, matches it with knowledge-dependent teaching knowledge graphs for the corresponding assessment stages, maps the answer data to the knowledge system, accurately locates implicit cognitive breakpoints and builds individual dynamic knowledge graphs, and then aggregates the learning situation of all students in the class to generate a list of common weak knowledge points and pushes it to the teacher's end. This not only achieves accurate tracking of the cognitive path of individual students, but also extracts common learning problems at the group level, breaks down the barrier between individual learning situation and class teaching, provides teachers with targeted and concentrated teaching basis, and greatly improves the pertinence of teaching. Attached Figure Description

[0022] Figure 1 This is a flowchart illustrating a student cognitive path tracking and teaching recommendation method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0023] The following is in conjunction with the appendix Figure 1 To be continued Figure 2 This application will be described in further detail.

[0024] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0025] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0027] It should be noted that all data interaction processes involved in this application have corresponding transmission protocols, including authorized data collection and use, and both parties involved in the data interaction have completed data authorization through the execution of the protocol.

[0028] This application provides a method for tracking student cognitive paths and recommending teaching methods, such as... Figure 1 As shown, the method provided in this application embodiment is executed by an electronic device, which can be a server or a terminal device. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these. The terminal device and the server can be directly or indirectly connected via wired or wireless communication. This application embodiment does not impose any limitations on this connection. The method includes steps S101-S105, wherein: S101. Obtain the answer data of the target student in the target assessment stage. The target student is any student in the target class.

[0029] The target assessment stage can be any phase of the teaching process, such as a chapter or a month; this embodiment does not impose any limitations. Complete answer data for each student in the target class during the target assessment stage is collected, including but not limited to exams and quizzes. Answer data includes information such as the correctness of answers, the timestamp of the answer, and the related knowledge points.

[0030] S102. Call the teaching knowledge graph of the target assessment link. The nodes of the teaching knowledge graph represent knowledge points, and the edges represent the dependencies between knowledge points.

[0031] Specifically, the construction process of the teaching knowledge graph includes: based on the curriculum standards, textbook chapters, and assessment syllabus of the target subject, the teaching content is hierarchically broken down into independent and indivisible minimum knowledge units, i.e., knowledge point nodes. Each knowledge point is assigned a unique identifier, name, chapter affiliation, and assessment requirement attributes, thus standardizing the definition of graph nodes. Based on the logic of subject knowledge and students' cognitive patterns, the pre- and post-knowledge relationships between each knowledge point are identified, i.e., the edges of the graph. The prerequisite knowledge points that must be mastered before learning a particular knowledge point, as well as the corresponding post-knowledge extension points, are clearly defined, completing the qualitative labeling of knowledge point dependencies. For example, learning quadratic equations requires mastering linear equations; these are dependency edges, with the node corresponding to the linear equation pointing to the node corresponding to the quadratic equation. A graph database is used to structurally store the standardized knowledge point nodes and dependency edges, constructing a directed graph structure where edges point from prerequisite knowledge points to post-knowledge points. Simultaneously, a graph access interface is built to enable rapid retrieval of the teaching knowledge graph in subsequent assessment stages.

[0032] S103. Map the answer data to the teaching knowledge graph, identify implicit pre-breakpoints, and construct a dynamic knowledge graph of the target students based on the implicit pre-breakpoints.

[0033] Specifically, each question in the answer data is pre-marked with the knowledge points being tested. These knowledge points can be manually marked by teachers or automatically marked by AI tools. The knowledge points being tested for each question are extracted from the target students' answer data, and the target students' mastery level of each knowledge point is calculated based on their correctness of answers. Mastery level is a numerical measure of the student's learning effectiveness for each knowledge point; a higher value indicates a higher level of mastery. Based on a pre-set mastery level threshold, knowledge points with low mastery levels are selected as implicit pre-breakpoints. These implicit pre-breakpoints represent fundamentally unmastered knowledge points in the cognitive chain and are the core reason for errors in subsequent knowledge points.

[0034] The nodes and edges of the copied teaching knowledge graph serve as the basic framework for a dynamic knowledge graph. The target student's mastery level of each knowledge point and identified implicit pre-existing weaknesses are marked as weak points on the corresponding nodes. A risk coefficient is calculated for each weak knowledge point's subsequent knowledge points; this risk coefficient represents the probability that the weak pre-existing knowledge points will lead to the student's inability to master the subsequent knowledge points. The final result is a dynamic knowledge graph containing mastery levels, weak knowledge points, and risk coefficients.

[0035] S104. Aggregate the dynamic knowledge graphs of all students in the target class to generate a list of common weak knowledge points.

[0036] The dynamic knowledge graph of all students in the class is traversed to extract each student's weak knowledge points and corresponding risk coefficients. Based on these weak knowledge points and risk coefficients, common weak knowledge points are identified. These common weak knowledge points are the root causes of weaknesses present in most students and represent the core objective of intensive teaching. All these common weak knowledge points are then integrated into a list.

[0037] S105. Push the list of common weak knowledge points to the teacher's end to guide teachers in carrying out intensive teaching.

[0038] This embodiment collects assessment answer data from individual students in the target class, matches it with knowledge-dependent teaching knowledge graphs for the corresponding assessment stages, completes the mapping between answer data and knowledge system, accurately locates implicit cognitive breakpoints and builds individual dynamic knowledge graphs, and then aggregates the learning situation of all students in the class to generate a list of common weak knowledge points and pushes it to the teacher's end. This not only achieves accurate tracking of the cognitive path of individual students, but also extracts common learning problems from the group level, breaks down the barrier between individual learning situation and class teaching, provides teachers with targeted and centralized teaching basis, and greatly improves the pertinence of teaching.

[0039] One possible implementation of this application embodiment maps answer data to a teaching knowledge graph and identifies implicit pre-breakpoints, including: Extract the knowledge points tested for each question from the answer data, and calculate the target student's mastery of each knowledge point based on the correctness of the target student's answers to each question. From the knowledge points involved in the answer data, select the knowledge points that have no prerequisite knowledge points in the teaching knowledge graph or whose prerequisite knowledge points do not appear in the answer data, and use them as the starting knowledge points. Starting from each initial knowledge point, the knowledge points are traversed along the out-degree direction of the teaching knowledge graph, and the knowledge points that are assessed are linked together to form a cognitive chain of several knowledge points. For each knowledge point in the cognitive chain, the mastery level of each assessment knowledge point is checked sequentially from the preceding knowledge point to the following knowledge point, and the first assessment knowledge point whose mastery level is lower than the preset mastery level threshold is marked as an implicit preceding breakpoint.

[0040] In this embodiment, among all the assessment knowledge points covered by the answer data, assessment knowledge points that do not have prerequisite knowledge points in the teaching knowledge graph, or whose corresponding prerequisite knowledge points are not included in the current answer data, are selected and designated as starting knowledge points. Prerequisite knowledge points are knowledge points in the teaching knowledge graph that have dependencies and need to be learned first; that is, they are the next-level nodes in the teaching knowledge graph. For example, if node A in the teaching knowledge graph points to node B, it indicates that learning node B depends on node A being learned first. Therefore, node A is the predecessor node (prerequisite knowledge point) of node B, and node B is the successor node (successor knowledge point) of node A.

[0041] Starting with each selected initial knowledge point, the traversal proceeds according to the out-degree direction of the teaching knowledge graph, i.e., from the preceding knowledge point to the subsequent knowledge point. The assessment knowledge points (knowledge points involved in the answer data) encountered during the traversal are sequentially linked together in the traversal order to form multiple independent knowledge point cognitive chains. The knowledge point cognitive chain is a student cognitive learning sequence formed by linking knowledge dependencies.

[0042] For each completed knowledge point cognitive chain, the mastery of each assessment knowledge point is checked sequentially from the preceding knowledge point to the following knowledge point. The first assessment knowledge point in each cognitive chain whose mastery level is lower than the preset mastery level threshold is marked as an implicit preceding breakpoint. The implicit preceding breakpoint is the root cause of the weak knowledge point that leads to the target student's subsequent learning and answering of questions.

[0043] This embodiment extracts assessment knowledge points from answer data, calculates individual knowledge point mastery, selects initial knowledge points without prior dependencies to construct a cognitive chain, and then checks the first unmet knowledge point along the knowledge dependency sequence and marks it as an implicit prior breakpoint. It abandons the traditional judgment method of only looking at the surface of wrong questions, traces the root weakness along the knowledge logic, avoids misjudging subsequent knowledge point errors as weak cores, accurately locates students' cognitive gaps, and improves the accuracy and depth of learning diagnosis.

[0044] One possible implementation of this application's embodiments involves calculating the target student's mastery of each assessed knowledge point based on the correctness of their answers to each question, including: Obtain the timestamp of each question's answer and divide the answer data into several stages according to a preset time window; For each stage, the frequency of each assessment knowledge point appearing in the stage assessment is counted, and based on the correctness of the answers to the questions within the stage and the frequency of stage assessment, the stage mastery of each assessment knowledge point by the target student is calculated. Calculate the time interval between the intermediate timestamp of each stage and the current time, and assign stage weights to each stage according to the time decay rule. Based on the stage weights, the mastery level of each assessment knowledge point at each stage is weighted and summed to obtain the target student's mastery level of each assessment knowledge point.

[0045] In this embodiment, the timestamps of each student's answers to each question in the target assessment process are collected. These timestamps record the precise time point at which the student submitted their answer to the corresponding question. Based on a pre-set time window, the complete answer data is divided into several independent answer stages according to chronological order, achieving staged breakdown of the answer data. The pre-set time window is a fixed time span for dividing the answer data stages, which can be flexibly determined by the teacher based on actual teaching experience; optionally, the pre-set time window is one week.

[0046] For each question-answering stage after division, the number of times each individual knowledge point is tested within that stage is counted; this is the stage assessment frequency. Each time an individual knowledge point appears in a question, the frequency is incremented by one. Combining the students' correct and incorrect answers to the corresponding questions within that stage with the stage assessment frequency, the target student's stage mastery level of that knowledge point in that stage is calculated. Stage mastery level is a quantitative value representing the student's mastery of the knowledge point within a single stage.

[0047] The time interval between the intermediate timestamp of each stage and the current assessment time is calculated, and stage weights are assigned to each stage according to the time decay rule. The time decay rule assigns a lower stage weight for larger time intervals and a higher weight for smaller time intervals. Stage weights characterize the influence of different answering stages on the final mastery level. Specifically, the reciprocal of the time interval for each stage is calculated (i.e., the ratio of 1 to the time interval); the sum of the reciprocals of the time intervals for each stage is calculated; and for each stage, the ratio of its reciprocal to the sum of its reciprocals is calculated to obtain the stage weight. By assigning higher weight to recent answering performance through time decay, the system aligns with the changing patterns of students' cognitive levels over time, making the mastery assessment more relevant to real-time learning.

[0048] This embodiment divides the answering stages based on the timestamp of the answer, calculates the mastery level of the stage by combining the frequency of stage assessments and the correctness of the answers, and then assigns stage weights based on the time decay rule and sums them up to obtain the final mastery level. It takes into account the correctness of the answers, the frequency of assessments, and the time decay factor, weakens the influence of long-term answering performance, strengthens the weight of recent answering status, and is more in line with the student's real-time cognitive level. It avoids the one-sidedness of judging a single wrong question and makes the mastery assessment more in line with the actual learning situation.

[0049] One possible implementation of this application embodiment involves constructing a dynamic knowledge graph of the target student based on implicit pre-breakpoints, including: Copy all nodes and edge structures of the teaching knowledge graph as the basic framework of the dynamic knowledge graph; Mark the target student's mastery of each assessment knowledge point on the corresponding node; The identified implicit pre-breakpoints are marked as weak knowledge points; Along the out-degree direction of the dynamic knowledge graph, assess the risk coefficient of the subsequent knowledge points of each weak knowledge point, and mark the risk coefficient on the corresponding node; The output is a dynamic knowledge graph that includes the level of mastery, weak knowledge points, and risk coefficient.

[0050] In this embodiment, the pre-calculated mastery level of each assessment knowledge point by the target student is marked on the corresponding knowledge point node in the dynamic knowledge graph framework. The mastery level is a quantitative value of knowledge point mastery obtained by comprehensively considering the correctness of answers, the frequency of stage assessments, and the time decay rule, which is used to intuitively represent the student's learning effect on the corresponding knowledge point. In the knowledge point nodes of the dynamic knowledge graph, the implicit pre-existing breakpoints identified in the previous stage are specifically marked and defined as weak knowledge points.

[0051] Using the marked weak knowledge points as baseline nodes, the subsequent knowledge points are determined along the out-degree direction of the dynamic knowledge graph, i.e., the traversal direction from the preceding knowledge point to the subsequent knowledge point. Then, the risk coefficient is calculated. The risk coefficient is used to quantitatively represent the possibility that the lack of mastery of the preceding weak knowledge points will lead to obstacles in learning and answering questions about the subsequent knowledge points. The specific calculation process is as follows: for any subsequent knowledge point of any weak knowledge point, the first frequency of the occurrence of the subsequent knowledge point in the answer data and the second frequency of the occurrence of the subsequent knowledge point and the weak knowledge point in the same question are counted. The ratio of the second frequency to the first frequency is calculated as the risk coefficient of the subsequent knowledge point.

[0052] This embodiment replicates the standard teaching knowledge graph framework to build a personalized dynamic graph, marking individual mastery levels, weak points, and risk coefficients for subsequent knowledge points. While fully preserving knowledge dependencies, it incorporates personalized learning data to achieve a visual presentation of students' cognitive status. This not only identifies current root causes of weaknesses but also predicts subsequent learning risks, providing a complete data carrier for subsequent class learning aggregation and personalized tutoring.

[0053] One possible implementation of this application embodiment involves aggregating the dynamic knowledge graphs of all students in the target class to generate a list of common weak knowledge points, including: Traverse the dynamic knowledge graph of all students in the target class and extract each student's weak knowledge points and risk coefficient; For each knowledge point, the total frequency of the knowledge point being marked as a weak knowledge point in the target class is counted, and the average risk coefficient of the knowledge point as a subsequent knowledge point is calculated. Knowledge points whose total frequency exceeds a preset total frequency threshold or whose average risk coefficient exceeds a preset average risk coefficient threshold are identified as common weak knowledge points. All common weak knowledge points are compiled into a list of common weak knowledge points.

[0054] In this embodiment, the total number of times the current knowledge point is marked as a weak knowledge point by students is counted. This total frequency represents the number of students in the target class who have a weak point in this knowledge point, directly reflecting the coverage of the group with weak knowledge points. All student data that marked the current knowledge point as a subsequent knowledge point with a risk coefficient are selected, and the corresponding risk coefficient values ​​are extracted. The sum of all valid risk coefficients is then divided by the number of students participating in the statistics to obtain the average risk coefficient for that knowledge point. The average risk coefficient represents the potential risk level of this knowledge point being affected by preceding weak knowledge points at the class-wide level.

[0055] Two standardized judgment thresholds are preset: a preset total frequency threshold and a preset average risk coefficient threshold. The preset total frequency threshold is a critical value for determining whether a knowledge point has a common group characteristic, and the preset average risk coefficient threshold is a numerical critical value for determining whether the risk of a knowledge point reaches the level of centralized teaching.

[0056] All common weak knowledge points identified through threshold testing are compiled and organized, and duplicate entries are removed. These common weak knowledge points are then extracted from the complete teaching knowledge graph and used to construct a small, independent sub-knowledge graph, retaining only the dependency edges between these weak knowledge points.

[0057] A topological sorting rule is used to sort knowledge points according to their prerequisite and successor dependencies in the teaching knowledge graph, placing weak foundational knowledge points first and advanced knowledge points last. The process involves: identifying weak foundational knowledge points in sub-graphs without prerequisites and placing them at the top of the sorting queue; removing already sorted knowledge points from the graph; continuing to find the next batch of weak knowledge points without prerequisite dependencies and adding them to the queue; repeating this process until all common weak knowledge points are sorted. If multiple knowledge points belong to the same level and have no dependencies, a secondary sort is performed based on the following priority: first, sorting by total frequency of weakness from high to low; if frequencies are the same, sorting by average risk coefficient from high to low. This ultimately forms an ordered list of common weak knowledge points that aligns with the logic of knowledge learning and the priority of class learning.

[0058] This embodiment traverses the dynamic graph of all students in the class, counts the frequency of knowledge point weaknesses and the average risk coefficient, and uses dual thresholds to screen common weaknesses and integrate them into a list. It extracts common problems of the class group from individual scattered learning situations, taking into account both the breadth of weakness coverage and the height of potential learning risks. It not only identifies high-frequency weaknesses that exist in most students, but also does not overlook high-risk niche weaknesses, ensuring that the selected knowledge points have concentrated teaching value and simplifying the teacher's learning situation analysis process.

[0059] One possible implementation of this application embodiment includes: Obtain the class answer data of the target class, and calculate the average mastery level and standard deviation of each knowledge point in the class; Based on the class average mastery level and standard deviation, the mastery level threshold for each knowledge point is dynamically calculated and used as the preset mastery level threshold.

[0060] In this embodiment, based on class answer data, the mastery level of each student for each knowledge point is calculated. For any given knowledge point, the average mastery level of all students is calculated. Standard deviation is a statistical indicator used to measure the dispersion of students' mastery level of the same knowledge point within a class, that is, the magnitude of individual differences. The larger the value, the more significant the gap in mastery level among students in the class; the smaller the value, the more consistent the mastery level among students in the class. In specific calculation, firstly, for each student in the class, the difference between their individual mastery level and the class average mastery level is calculated. Then, this difference is squared. The sum of the squared results of all students is then divided by the total number of valid answerers in the class. Finally, the result is standardized to obtain the class standard deviation for that knowledge point.

[0061] Furthermore, the difference between the class average mastery level and the standard deviation (or a fixed proportion of the standard deviation) is calculated to obtain the mastery level threshold.

[0062] This embodiment is based on the overall answer data of the class, statistically analyzes the average mastery level and standard deviation of knowledge points, and dynamically generates a personalized mastery level threshold. It avoids the drawbacks of a one-size-fits-all approach with a fixed threshold and adapts to the differences in learning situation and difficulty of different classes and different knowledge points.

[0063] One possible implementation of this application embodiment includes: After teachers complete intensive teaching based on a list of common weak knowledge points, post-test answer data of students in the target class is obtained; Update the dynamic knowledge graph of each student based on post-test answer data; By comparing the average improvement in the mastery of common weak knowledge points in each class before and after intensive teaching and the average decrease in the risk coefficient, a teaching effectiveness evaluation report is generated. The teaching effectiveness evaluation report will be sent to the teacher's end.

[0064] For specific common weak knowledge points, the average mastery level of the whole class after intensive teaching is subtracted from the average mastery level of the whole class before teaching. This reflects the learning effect of the knowledge point. For the subsequent nodes of specific common weak knowledge points, the average risk coefficient of the class after teaching is subtracted from the value before teaching. This reflects the degree to which the teaching intervention alleviates future learning obstacles.

[0065] This embodiment collects post-test data after intensive teaching, updates students' dynamic knowledge graphs, compares the changes in core indicators before and after teaching to generate an evaluation report and pushes it to the teacher's end, forming a complete teaching loop of "diagnosis-teaching-retesting-evaluation", quantitatively verifying the effectiveness of intensive teaching, intuitively presenting the improvement of weak points and the effect of risk mitigation, and providing data support for subsequent teaching optimization and remedial teaching.

[0066] This application provides an electronic device, such as... Figure 2 As shown, Figure 2 The illustrated electronic device 200 includes a processor 201 and a memory 203. The processor 201 and the memory 203 are connected, for example, via a bus 202. Optionally, the electronic device 200 may also include a transceiver 204. It should be noted that in practical applications, the transceiver 204 is not limited to one type, and the structure of this electronic device 200 does not constitute a limitation on the embodiments of this application.

[0067] Processor 201 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 201 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0068] Bus 202 may include a pathway for transmitting information between the aforementioned components. Bus 202 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 202 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 2 The symbol is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0069] The memory 203 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0070] The memory 203 stores the application code that executes the scheme of this application, and its execution is controlled by the processor 201. The processor 201 executes the application code stored in the memory 203 to implement the content shown in the aforementioned embodiment of the student cognitive path tracking and teaching recommendation method.

[0071] Figure 2 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0072] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the content shown in the aforementioned student cognitive path tracking and teaching recommendation method embodiments.

[0073] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0074] This application provides a computer program product, including a computer program that, when executed by a processor, implements the content shown in the aforementioned student cognitive path tracking and teaching recommendation method embodiments.

[0075] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A student cognitive path tracking and teaching recommendation method, characterized by, include: Obtain the answer data of the target student in the target assessment stage, wherein the target student is any student in the target class; The teaching knowledge graph of the target assessment stage is invoked, where nodes represent knowledge points and edges represent dependencies between knowledge points; The answer data is mapped to the teaching knowledge graph, implicit pre-breakpoints are identified, and a dynamic knowledge graph of the target student is constructed based on the implicit pre-breakpoints. Aggregate the dynamic knowledge graphs of all students in the target class to generate a list of common weak knowledge points; The list of common weak knowledge points will be pushed to the teacher's end to guide teachers in carrying out intensive teaching.

2. The student cognitive path tracking and teaching recommendation method according to claim 1, characterized in that, The step of mapping the answer data to the teaching knowledge graph and identifying implicit pre-breakpoints includes: Extract the knowledge points to be assessed for each question from the answer data, and calculate the degree of mastery of each knowledge point by the target student based on the correctness of the target student's answers to each question. From the knowledge points involved in the answer data, select the knowledge points that have no prerequisite knowledge points in the teaching knowledge graph or whose prerequisite knowledge points do not appear in the answer data, and use them as starting knowledge points; Starting from each initial knowledge point, the teaching knowledge graph is traversed along its out-degree direction, and the knowledge points being assessed are linked together to form several knowledge point cognitive chains. For each knowledge point in the cognitive chain, the mastery level of each assessment knowledge point is checked sequentially from the preceding knowledge point to the following knowledge point, and the first assessment knowledge point whose mastery level is lower than the preset mastery level threshold is marked as an implicit preceding breakpoint.

3. The student cognitive path tracking and teaching recommendation method according to claim 2, characterized in that, The calculation of the target student's mastery of each assessment knowledge point based on the correctness of their answers to each question includes: Obtain the timestamp of each question's answer, and divide the answer data into several stages according to a preset time window; For each stage, the frequency of each assessment knowledge point appearing in the stage assessment is counted, and based on the correctness of the answers to the questions in the stage and the frequency of the stage assessment, the stage mastery of each assessment knowledge point by the target student is calculated. Calculate the time interval between the intermediate timestamp of each stage and the current time, and assign stage weights to each stage according to the time decay rule. Based on the stage weights, the mastery level of each assessment knowledge point at each stage is weighted and summed to obtain the target student's mastery level of each assessment knowledge point.

4. The student cognitive path tracking and teaching recommendation method according to claim 1, characterized in that, The construction of the dynamic knowledge graph of the target student based on the implicit pre-breakpoints includes: Copy all nodes and edge structures of the teaching knowledge graph as the basic framework of the dynamic knowledge graph; Mark the target student's mastery of each assessment knowledge point on the corresponding node; The identified implicit pre-breakpoints are marked as weak knowledge points; Along the out-degree direction of the dynamic knowledge graph, assess the risk coefficient of the subsequent knowledge points of each weak knowledge point, and mark the risk coefficient on the corresponding node; The output is a dynamic knowledge graph that includes the level of mastery, the weak knowledge points, and the risk coefficient.

5. The student cognitive path tracking and teaching recommendation method according to claim 1, characterized in that, The dynamic knowledge graph of all students in the target class is aggregated to generate a list of common weak knowledge points, including: Traverse the dynamic knowledge graph of all students in the target class and extract each student's weak knowledge points and risk coefficient; For each knowledge point, the total frequency of the knowledge point being marked as a weak knowledge point in the target class is counted, and the average risk coefficient of the knowledge point as a subsequent knowledge point is calculated. Knowledge points whose total frequency exceeds a preset total frequency threshold or whose average risk coefficient exceeds a preset average risk coefficient threshold are identified as common weak knowledge points. All common weak knowledge points are compiled into a list of common weak knowledge points.

6. The student cognitive path tracking and teaching recommendation method according to claim 1, characterized in that, The method further includes: Obtain the class answer data of the target class, and calculate the average mastery level and standard deviation of each knowledge point in the class; Based on the class average mastery level and the standard deviation, the mastery level threshold for each knowledge point is dynamically calculated and used as the preset mastery level threshold.

7. The student cognitive path tracking and teaching recommendation method according to claim 1, characterized in that, The method further includes: After the teachers complete the intensive teaching based on the list of common weak knowledge points, the post-test answer data of the students in the target class is obtained; Based on the post-test answer data, update the dynamic knowledge graph of each student; By comparing the average improvement in the mastery of common weak knowledge points in each class before and after intensive teaching and the average decrease in the risk coefficient, a teaching effectiveness evaluation report is generated. The teaching effectiveness evaluation report will be sent to the teacher's end.

8. An electronic device, characterized in that, include: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, said at least one application being configured to: perform the student cognitive path tracking and instruction recommendation method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed in a computer, the computer is instructed to perform the student cognitive path tracking and teaching recommendation method according to any one of claims 1-7.

10. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the steps of the student cognitive path tracking and instruction recommendation method as described in any one of claims 1-7.

Images