A student behavior data management system and method for the teaching process

Abstract

This invention discloses a student behavior data management system and method for the teaching process, relating to the field of student behavior data processing technology. The system and method include: S1, collecting multi-source data during the execution of teaching tasks and preprocessing it to construct a standardized student behavior dataset; S2, evaluating the stability of task switching rhythm and providing behavioral guidance accordingly; S3, analyzing the continuity of behavior during cross-task transitions and dynamically adjusting rhythm prompting strategies; S4, comprehensively evaluating rhythm fluctuations and triggering intervention linkage mechanisms; and S5, identifying rhythm anomalies and generating prompts that are pushed to teachers and students. This solves the problem in multi-station teaching where existing data management methods cannot track fluctuations in student behavior rhythm at different task stages, leading to confusion in operation methods and imbalance in behavior rhythm when students switch stations and migrate across tasks.

Description

Technical Field

[0001] This invention relates to the field of student behavior data processing technology, specifically to a student behavior data management system and method for the teaching process. Background Technology

[0002] With the continuous advancement of digitalization in teaching, students' behavioral information during the execution of teaching tasks is gradually becoming an important analytical object for measuring the learning process and task participation. Currently, in vocational education, contextualized teaching, and practical training task-driven courses, teachers and teaching platforms are increasingly using students' behavioral data to help judge their learning status and task mastery. Especially in teaching organization methods such as multi-workstation teaching, contextualized task-driven teaching, and phased assessment, students' behavioral time series, task transition trajectories, and behavioral stability characteristics are gradually becoming important reference indicators reflecting learning status and adaptability.

[0003] For example, the invention patent with announcement number CN112488236B discloses an integrated unsupervised student behavior clustering method. This invention addresses the limitations of questionnaire methods in data collection and the heavy reliance of statistical, supervised, and semi-supervised learning methods on student labels, proposing an integrated unsupervised student behavior clustering method. First, it extracts features from student behavior data, dividing them into three parts: mode, mean, and range to describe the central tendency; minimum, first quantile, median, third quantile, and maximum to express the dispersion; and Shannon entropy to measure the regularity of the time and location of behavior occurrences. Then, variance and correlation analysis are used to select the optimal behavioral features. Finally, DBSCAN is used to perform initial clustering of student behavior features, and K-means is used to further subdivide very large clusters to obtain the final clustering results. This invention does not rely on student labels, completing clustering solely through behavioral data analysis, laying the foundation for refined student services and management.

[0004] For example, the invention patent with announcement number CN109977132B discloses a method for analyzing abnormal student behavior patterns based on unsupervised clustering, including the following steps: Step 1: Extracting key features of abnormal student behavior; Step 2: Extracting abnormal student behavior classes using unsupervised clustering analysis; Step 3: Grouping and measuring the abnormal behavior individuals within each abnormal student class; Step 4: Detecting abnormal groups with similar behaviors using a student spatiotemporal correlation graph. Using the technical solution of this invention, accurate analysis of abnormal student behavior on campus can be achieved, helping campus administrators to accurately and quickly analyze student behavior.

[0005] However, existing student behavior data management methods mostly focus on task completion results and static behavior logs, lacking dynamic extraction mechanisms for rhythm switching between task stages, continuity of behavioral paths, and short-term behavioral fluctuation characteristics. This makes it impossible to accurately depict the trajectory of student behavior changes during task transitions, workstation relocations, or rhythm disturbances. Furthermore, continuous variables such as behavioral rhythm characteristic values, switching stability indicators, and rhythm fluctuation levels lack a unified organizational framework, making it difficult to support rapid identification and immediate feedback of behavioral instability, thus limiting the ability to provide refined guidance and dynamic control during the teaching process.

[0006] To address the above issues, there is an urgent need for a student behavior data management system and method for the teaching process. Summary of the Invention

[0007] Technical problems to be solved

[0008] To address the shortcomings of existing technologies, this invention provides a student behavior data management system and method for the teaching process. This solves the problem that existing data management methods in multi-station teaching cannot track the fluctuations in students' behavior rhythm at different task stages, which can lead to confusion in operation methods and imbalance in behavior rhythm when students switch stations and migrate across tasks.

[0009] Technical solution

[0010] To achieve the above objectives, the present invention provides the following technical solution: a student behavior data management system and method for the teaching process, comprising: S1, collecting behavioral operation data, task transition data, and behavioral stability data during the execution of teaching tasks, and preprocessing the collected behavioral operation data, task transition data, and behavioral stability data to construct a standardized student behavior dataset; S2, evaluating the rhythm stability state of students during task switching based on the standardized student behavior dataset, and providing behavioral guidance based on the evaluation results; S3, analyzing the continuity of students' behavior during cross-task transitions based on the standardized student behavior dataset, and dynamically adjusting rhythm prompt strategies based on the analysis results; S4, comprehensively evaluating the fluctuations in rhythm evolution during the teaching cycle using the rhythm stability state evaluation results and the behavior continuity analysis results as input, and triggering a teaching intervention linkage mechanism based on the evaluation results; S5, identifying abnormal rhythm segments based on the evolution trend of behavioral fluctuation intensity values, judging instability characteristics by combining switching stability characteristic values ​​and behavioral rhythm response values, generating structured prompt information and synchronously pushing it to teachers and students.

[0011] Furthermore, the specific steps for collecting behavioral operation data, task transition data, and behavioral stability data during the execution of teaching tasks, and preprocessing the collected behavioral operation data, task transition data, and behavioral stability data to construct a standardized student behavior dataset are as follows: Behavioral operation data during the execution of teaching tasks is collected through teaching terminal logs. This behavioral operation data includes: the number of task operations per unit time, the number of operations within a unit task, the average response time and average operation interval of students in the current task phase, and the rate of change of rhythm is calculated by determining the difference between the average operation interval of the current window and the average operation interval of the previous window; Task transition data is collected through a task flow tracking mechanism. This task transition data includes: the first response delay time after task switching, the response time of two adjacent windows, and the average response time of students in the current task phase. The data includes the average task completion time, the number of parallel subtasks during task switching phases, and the task switching frequency per unit time. Behavioral stability data is collected using a behavioral sequence analysis engine, including the operation frequency, student behavior trigger intervals, and number of times the operation sequence is disordered in each task. A path backtracking detection algorithm records the number of erroneous operations and repeated operations within task switching segments. The collected behavioral operation data, task switching data, and behavioral stability data are standardized and normalized to correct for behavioral rhythm scale deviations caused by differences in task type, operating habits, and teaching context. The standardized behavioral operation data, task switching data, and behavioral stability data are then uniformly archived and stored to construct a standardized student behavior dataset.

[0012] Furthermore, the specific steps for evaluating the rhythm stability during student task switching based on the standardized student behavior dataset are as follows: Extract the number of task operations per unit time, the number of actions within a unit task, and the average response time of students in the current task phase from the standardized student behavior dataset. Multiply the number of task operations, the number of actions, and the average response time by one to obtain the task behavior density value. Extract the number of repeated operations by students within a unit task. Take the opposite of the number of repeated operations, perform an exponential transformation, and then add one to obtain the behavior time diffusion value. Extract the mean of the operation interval and the rhythm change rate. Multiply the product of the rhythm change rate by one and the mean of the operation interval, take the reciprocal, add one, and then take the logarithm to obtain the operation response elasticity value. Use the product of the task behavior density value and the operation response elasticity value as the numerator and the behavior time diffusion value as the denominator to obtain the behavior rhythm response value.

[0013] Furthermore, the specific steps for guiding behavior based on the evaluation results are as follows: Real-time comparison of the current student's behavioral rhythm response value with the behavioral rhythm threshold: When the behavioral rhythm response value is less than or equal to the behavioral rhythm threshold, it is determined to be a stable rhythmic coordination segment. The current teaching task guidance rhythm, workstation operation guidance speech rate, and operation demonstration rhythm are continued, maintaining stable operation of the sliding window length and data extraction parameter configuration of each behavioral data collection node, without needing to adjust the synchronization logic of the operation feedback rhythm and workstation switching rhythm; When the behavioral rhythm response value is greater than the behavioral rhythm threshold, it is determined to be a rhythmic imbalance transition segment. The task operation response window length is dynamically shortened, and the current task operation frequency sampling period is shortened from 10 seconds to 5 seconds to capture student rhythm instability details at a high frequency, enhancing the temporal resolution of the behavioral rhythm curve and temporarily increasing the frequency of workstation interaction prompts.

[0014] Furthermore, the specific steps for analyzing the continuity of student behavior during cross-task transitions based on the standardized student behavior dataset are as follows: Extract the operation frequency and student behavior trigger interval from the standardized student behavior dataset for the current task; multiply the logarithm of the student behavior trigger interval (plus one) by the operation frequency to obtain the rhythm difference weighted value for the current task; extract the first response delay time after task switching; subtract the first response delay time from one and divide by the average task completion time of the two adjacent tasks plus one to obtain the behavior continuity retention rate; multiply the square root of the number of erroneous operations by the behavior continuity retention rate to obtain the continuity harmonic value; traverse all tasks included in the analysis within the current sliding window, sum the rhythm difference weighted values ​​of all tasks, and then sum them with the current continuity harmonic value to obtain the switching stability feature value.

[0015] Furthermore, the specific steps of the rhythm prompt strategy dynamically adjusted based on the analysis results are as follows: When the switching stability feature value continues to rise in three consecutive sliding windows and the increase gradually increases, the current and previous workstations are immediately recorded at the micro-cycle level. Simultaneously, the operation sequence misalignment, step jumps, and behavior sticking phenomena in the current task are captured, and operation sequence correction suggestions are automatically generated for students on the platform. When the switching stability feature value frequently alternates between high and low in consecutive windows and the fluctuation amplitude increases significantly, the behavioral path structure of adjacent task stages is retrieved in conjunction with the analysis. The rhythm discontinuity and switching blind spots of the operation logic of different workstations are identified. At the same time, it is dynamically judged whether there are problems such as overload of operation information input, excessively dense instruction rhythm, and uneven distribution of prompts in the current task node, and the frequency of auxiliary instruction push is automatically reduced. When the switching stability feature value changes slowly and the trend is stable in multiple consecutive sliding windows, the difference between the behavioral structure of the current task and the behavioral path characteristics of the previous high-fluctuation task node is compared to assess whether it belongs to a false stable state where the task rhythm is temporarily stable but cognition is not synchronized. When it is determined to be in a false stable state, the structural maladaptation area of ​​the next task stage is deduced, and an advance prompt page is pushed before entering.

[0016] Furthermore, the specific steps for comprehensively evaluating the fluctuations in rhythm evolution during the teaching cycle, using the rhythm stability assessment results and behavioral coherence analysis results as inputs, are as follows: Obtain the switching stability feature value and the behavioral rhythm response value; multiply the switching stability feature value and the behavioral rhythm response value as the numerator; add one to the number of parallel subtasks within the task switching phase, take the logarithm to the base 10, and add one more as the denominator to obtain the rhythm switching fusion value; extract the task switching frequency per unit time; multiply the task switching frequency by the number of times the operation sequence disorder was identified within the current time window, and add one more to obtain the enhancement adjustment value; multiply the rhythm switching fusion value by the enhancement adjustment value to obtain the behavioral fluctuation intensity value.

[0017] Furthermore, the specific steps of the teaching intervention linkage mechanism triggered based on the evaluation results are as follows: Real-time comparison of the current behavioral fluctuation intensity value with the behavioral stability evolution threshold, which includes a first fluctuation threshold and a second fluctuation threshold: When the behavioral fluctuation intensity value is less than or equal to the second fluctuation threshold, it is determined to be in a rhythmic stability stage. The existing behavior collection frequency and label update strategy remain unchanged, and a low-frequency rhythm change tracking mechanism is simultaneously activated to periodically detect minor changes in operation intervals and step completion times; When the behavioral fluctuation intensity value is greater than the second fluctuation threshold and less than or equal to the first fluctuation threshold, it is determined to be in a rhythmic fluctuation transition stage. Prioritize identifying high-frequency backtracking nodes and repetitive triggering operations in the behavioral sequence. Simultaneously, marked completed and incomplete task steps in the task flow with semi-transparent and highlighted color schemes. The background synchronously collects the logical jump index and repetitive path backtracking density between operation steps in this stage. When the behavioral fluctuation intensity value exceeds the first fluctuation threshold, it is determined to be a stage of severe behavioral rhythm instability. The current task stage is temporarily divided into several sub-task blocks, and the operation feedback rhythm and prompt interaction method within the stage are reset. At the same time, a rhythm intervention suggestion pop-up is pushed to the teacher's end, and the abnormal behavior path compression mode is entered simultaneously, retaining only the main logic and key feedback actions.

[0018] Furthermore, the specific steps for identifying rhythmic abnormalities based on the evolution trend of behavioral fluctuation intensity values, determining instability characteristics by combining switching stability feature values ​​and behavioral rhythm response values, and generating structured prompt information to be synchronously pushed to teachers and students are as follows: Based on the continuous evolution results of behavioral fluctuation intensity values, a sliding window in a rhythmic abnormality segment is identified, and the switching stability feature value and behavioral rhythm response value within the window are combined to determine whether rhythmic instability characteristics exist during the current task execution process; subsequently, structured prompt information is generated based on behavioral fluctuation intensity, and processed according to the prompt target: for students, the prompt information is embedded in the task execution interface for operation guidance; for teachers, the student's current behavioral state and rhythmic evolution trend are synchronously pushed, and teacher intervention suggestion cards are activated; when rhythmic instability is severe, the prompt density and interaction rhythm of the teaching terminal are automatically adjusted, the key step prompt dwell time is extended in subsequent tasks, the task switching frequency is reduced, and the recovery of behavioral rhythm is tracked in real time.

[0019] The second aspect of this invention provides a student behavior data management system for the teaching implementation process, comprising: a data acquisition and preprocessing module, used to collect behavioral operation data, task transition data, and behavioral stability data during the execution of teaching tasks, and to preprocess the collected behavioral operation data, task transition data, and behavioral stability data to construct a standardized student behavior dataset; a behavior rhythm feature extraction module, used to evaluate the rhythm stability state of students during task switching based on the standardized student behavior dataset, and to guide behavior based on the evaluation results; a switching stability index generation module, used to analyze the continuity of students' behavior during cross-task transitions based on the standardized student behavior dataset, and to dynamically adjust the rhythm prompt strategy based on the analysis results; a behavior fluctuation window monitoring module, used to comprehensively evaluate the fluctuation of rhythm evolution during the teaching cycle using the rhythm stability state evaluation results and the behavior continuity analysis results as input, and to trigger a teaching intervention linkage mechanism based on the evaluation results; and a rhythm instability prompt and feedback trigger module, used to identify abnormal rhythm segments based on the evolution trend of behavior fluctuation intensity values, and to judge instability characteristics by combining switching stability feature values ​​and behavior rhythm response values, generating structured prompt information and synchronously pushing it to teachers and students.

[0020] Beneficial effects

[0021] The present invention has the following beneficial effects:

[0022] (1) The student behavior data management system and method in the teaching process, through the joint analysis of behavior rhythm and stability characteristics in a continuous window, identifies typical rhythm abnormal patterns and triggers personalized control prompts, supports the teaching terminal to automatically adjust task rhythm parameters, and enhances the ability to respond to individual differences in student behavior.

[0023] (2) The student behavior data management system and method in the teaching implementation process, by extracting abnormal jumps, repeated backtracking and key operation breakpoints in the behavior path, identifies the cognitive bottleneck area in the task process, and provides micro-diagnostic basis for the design of teaching task process and rhythm optimization from the behavior layer.

[0024] (3) The student behavior data management system and method in the teaching implementation process improves the real-time early warning capability of rhythm imbalance state by extracting the intensity of behavior fluctuations under continuous windows, linking the abnormal rhythm section labeling and structured prompt generation logic, and effectively enhancing the perception and response efficiency of abnormal behavior on both the teacher and student ends.

[0025] (4) The student behavior data management system and method in the teaching implementation process, by constructing a feedback triggering mechanism based on the rhythm fluctuation level, pushes the rhythm instability prompts to the teacher end and the student end in sync, realizing the dynamic linkage of guidance strategies, work station switching rhythm and feedback rhythm in teaching tasks, and improving the timeliness of teaching intervention and the flexible adjustment of rhythm control.

[0026] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0027] Figure 1 This is a flowchart of a student behavior data management method during the teaching process according to the present invention;

[0028] Figure 2 This is a structural diagram of a student behavior data management system for the teaching implementation process according to the present invention;

[0029] Figure 3 This is a bar chart showing the intensity values ​​of behavioral fluctuations involved in this invention.

[0030] Figure 4 This is an example diagram of the student behavior rhythm curve involved in the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Please see Figures 1-4This invention provides a technical solution: a student behavior data management system and method for the teaching process, comprising: S1, collecting behavioral operation data, task transition data, and behavioral stability data during the execution of teaching tasks, and preprocessing the collected behavioral operation data, task transition data, and behavioral stability data to construct a standardized student behavior dataset; S2, evaluating the rhythm stability state of students during task switching based on the standardized student behavior dataset, and providing behavioral guidance based on the evaluation results; S3, analyzing the continuity of students' behavior during cross-task transitions based on the standardized student behavior dataset, and dynamically adjusting rhythm prompt strategies based on the analysis results; S4, comprehensively evaluating the fluctuation of rhythm evolution during the teaching cycle using the rhythm stability state evaluation results and the behavior continuity analysis results as input, and triggering a teaching intervention linkage mechanism based on the evaluation results; S5, identifying abnormal rhythm segments based on the evolution trend of behavioral fluctuation intensity values, and judging instability characteristics by combining switching stability characteristic values ​​and behavioral rhythm response values, generating structured prompt information and synchronously pushing it to teachers and students.

[0033] Specifically, behavioral operation data, task transition data, and behavioral stability data are collected during the execution of teaching tasks. The collected data is then preprocessed to construct a standardized student behavior dataset. The specific steps are as follows: Behavioral operation data is collected during the execution of teaching tasks through a real-time monitoring module on the teaching terminal log. This data includes the number of effective task operations per unit time, the number of specific actions within each task unit, the average response time of students in the current task phase, and the average operation interval. Simultaneously, based on a sliding time window, the difference between the average operation interval of the current window and the previous window is calculated to obtain the rhythm change rate, which characterizes the degree of fluctuation in behavioral rhythm. An operation rhythm curve fitting algorithm is introduced during the collection of behavioral operation data to filter out short-term interference and stabilize the rhythm change trend line.

[0034] Task transition data is acquired through a task flow tracking mechanism. This data includes the initial response delay after a task switch, the average task completion time between two adjacent tasks, the number of parallel subtasks within the task switch interval, and the task switch frequency per unit time. The extraction of task switch frequency is combined with the structural analysis results of the task event sequence. A density clustering algorithm is used to identify high-frequency switching segments, and task switch mapping pairs are automatically extracted based on the task number trajectory.

[0035] Behavioral stability data was collected using a behavioral sequence analysis engine. This data included the frequency of operations during task execution, the intervals between student behavior triggers at each stage, and the number of times the operation sequence was disrupted. Behavioral stability was further evaluated using a path backtracking detection algorithm. This algorithm identified the number of erroneous operations and repetitive actions within key task switching segments and constructed an operation sequence confusion graph to quantify stability shifts.

[0036] The collected behavioral operation data, task transition data, and behavioral stability data were standardized. A distributed reconstruction method was used to align different data dimensions to a uniform scale, eliminating the impact of rhythm differences caused by task type, operation style, and teaching context. Subsequently, a unified normalization process was executed to compress and map all indicator values ​​to a closed interval between 0 and 1, ensuring the uniformity of the feature space and computational stability. Finally, all standardized data were aggregated and archived to construct a standardized student behavior dataset covering the entire teaching task process, serving as the foundational data support for subsequent behavioral rhythm status assessment and path analysis.

[0037] This implementation plan establishes a unified, comparable, and stable data foundation throughout the entire teaching process, supporting dynamic evaluation of student behavioral rhythm and multidimensional analysis of task path structure. By collecting and processing behavioral operation data, task transition data, and behavioral stability data, the plan effectively captures the temporal characteristics and rhythmic change trends of student behavioral responses during teaching activities. Through standardization and normalization, it eliminates rhythm scale deviations caused by differences in task type, operational habits, and context, thereby ensuring a unified expression and horizontal comparison capability of behavioral rhythm data across different students and tasks. This provides high-quality input data support for subsequent rhythm fluctuation identification, behavioral path analysis, and the generation of control strategies.

[0038] Specifically, based on a standardized student behavior dataset, the steps for evaluating the rhythm stability during student task switching are as follows: Extract the number of task operations per unit time, the number of actions within a unit task, and the average response time of students in the current task phase from the standardized student behavior dataset. Multiply the number of task operations, the number of actions, and the average response time by one to obtain the task behavior density value. Extract the number of repeated operations by students within a unit task. Take the opposite of the number of repeated operations, perform an exponential transformation, and then add one to obtain the behavior time diffusion value. Extract the mean of the operation interval and the rhythm change rate. Multiply the product of the rhythm change rate by one and the mean of the operation interval, take the reciprocal, add one, and then take the logarithm to obtain the operation response elasticity value. Use the product of the task behavior density value and the operation response elasticity value as the numerator and the behavior time diffusion value as the denominator to obtain the behavior rhythm response value.

[0039] The formula for calculating the behavioral rhythm response value is:

[0040] ;

[0041] In the formula: It represents the number of task operations per unit of time, used to measure the student's operational activity level in the current task stage. It is a core parameter for constructing the intensity of behavioral rhythm, derived from the real-time counting record of operation actions per second in the front-end teaching interaction device, and automatically segmented in combination with the task timing module. This represents the number of operations within a unit task. It indicates the total number of effective operations performed by a student in completing a complete task and is an important basis for judging the task execution density. It is derived from the operation event count results in the task node log and counts the number of times the operation category is a valid action. This represents the average response time of students in the current task phase. It is used to reflect the average processing delay of students for task events and is an important parameter for evaluating rhythm lag. It is derived from the time difference between the task trigger point and the first operation action and is the average value of a sliding window across multiple task segments. It represents the number of times a student performs repeated operations within a unit of task, and is used to indicate the frequency of repeated behaviors during the task. It is a key indicator for identifying behavioral anomalies such as hesitation and repeated attempts, and is derived from the number of repeated records of the same operation in a short period of time in behavioral stability data. It represents the mean operation interval, which is used to measure the average time interval between two adjacent valid operations. It is a basic indicator of the smoothness of operation rhythm and is derived from the average difference of timestamp sequences in the standardized behavioral time dataset. The rate of change of rhythm is used to reflect the degree of fluctuation of the current behavior rhythm relative to the previous window. It is an important parameter for evaluating the smoothness of rhythm switching and is derived from the normalized result of the difference between the average operation time intervals in two consecutive sliding windows.

[0042] This implementation plan comprehensively evaluates students' behavioral activity, response rhythm, and operational stability during the execution of teaching tasks. By integrating multiple key characteristics such as task operation density, response delay, frequency of repetitive behaviors, and rhythm fluctuations, it quantifies the efficiency and rhythm coordination of students' operational behaviors per unit of time. The calculation results can serve as an important basis for identifying abnormal behavioral rhythm segments, judging the fluency of task execution, triggering teaching intervention mechanisms, and dynamically adjusting the task rhythm, providing structured quantitative support for subsequent rhythm adaptability analysis and teaching feedback decisions.

[0043] Specifically, the steps for guiding behavior based on the assessment results are as follows: Real-time comparison of the current student's behavioral rhythm response value with the behavioral rhythm threshold:

[0044] When the behavioral rhythm response value is less than or equal to the behavioral rhythm threshold, it is determined to be a rhythmic coordination stable segment. During this stage, the student's operational rhythm is relatively stable, and there is a clear regularity between the response time, operation interval, and task execution frequency. Therefore, the current teaching task guidance rhythm, workstation operation guidance speech speed, and operation demonstration rhythm can continue to be used. The sliding window length of various behavioral data collection nodes remains at the initial configuration of 20-second window and 2-second sliding step, without needing to modify the synchronization logic of operation feedback rhythm and workstation switching rhythm.

[0045] When the behavioral rhythm response value exceeds the behavioral rhythm threshold, it is identified as a rhythm imbalance transition zone, indicating anomalies such as a sudden increase in behavioral frequency, a contraction in response intervals, and a disordered operational sequence during the current student operation. At this point, the task operation response window length is dynamically shortened, reducing the sampling period for task operation frequency from the original 10 seconds to 5 seconds to construct a high-frequency sampling mechanism. Within the shortened window, subtle perturbations in student behavioral rhythm are captured with higher temporal resolution, accurately extracting instability features including operation beat drift, hesitation during task switching, and short-term frequency concentration, thus enhancing the temporal resolution of the behavioral rhythm curve. Simultaneously, to match the rate of change in behavioral perturbation rhythm, the frequency of workstation interaction prompts is increased, adjusting the visual prompt refresh frequency from once every 30 seconds to once every 15 seconds, enabling rapid response guidance in fast-paced situations. This effectively supports the adaptive correction of rhythm control strategies and rapid intervention in the rhythm recovery process.

[0046] like Figure 4The diagram shows an example of a student behavior rhythm curve. The curve plots task execution time on the horizontal axis and behavior rhythm response value on the vertical axis, reflecting the changing trend of student behavior rhythm during the execution of a teaching task. The curve exhibits obvious rhythm fluctuations at different stages, which can be divided into a stable rhythm segment and a rhythm imbalance segment. The red dashed line in the diagram represents the behavior rhythm threshold, the green and orange areas represent the stable rhythm segment and the rhythm imbalance segment, respectively, and the blue curve represents the student's real-time behavior rhythm response value. In the 0s to 35s interval, the curve remains at a low level of 0.3 to 0.4, indicating stable student operation intervals and a balanced rhythm, typical of a stable rhythm segment, as shown at the marked points 10s and 35s. The behavior rhythm response value remains in a low fluctuation range, reflecting smooth student operation and small rhythm fluctuations. After 35s, the curve rises rapidly, reaching its first peak at 60s, indicating a significant increase in operation density and an intensification of rhythm fluctuations. Between 60 and 90 seconds, the curve remains at a high plateau, forming a rhythmic imbalance zone. This indicates frequent student actions and intensive feedback during this phase, with the rhythmic characteristics exhibiting strong volatility, peaking at 90 seconds. From 90 seconds onwards, the curve drops sharply, reaching around 0.3 by 105 seconds, with the response value falling below the rhythmic threshold again, entering a new rhythmic stability zone. Afterwards, fluctuations subside around 115 seconds, and the rhythmic response returns to a more regular pattern. The overall curve reveals the rhythmic trajectory of students throughout the task execution process, from stability to imbalance and back to stability. Six key nodes reflect rhythmic inflection points and behavioral beat shifts, providing precise references for controlling the rhythm of teaching feedback and dynamically adjusting task prompts.

[0047] In this implementation plan, by comparing students' behavioral rhythm response values ​​with behavioral rhythm threshold values ​​in real time, the system accurately identifies whether students are currently in a stable or unbalanced rhythm state. When a stable segment is identified, the established teaching rhythm and operation prompt frequency are maintained to ensure the continuity and consistency of the teaching process. When an unbalanced segment is identified, the operation window for task response is immediately shortened, and the sampling frequency and prompt density are increased. This enhances the ability to capture abnormal states such as sudden changes in student behavior and rhythm disturbances, providing timely and accurate data support for subsequent adjustments to teaching instructions and optimization of feedback strategies, and improving the adaptability to individual behavioral fluctuations and the sensitivity of rhythm intervention.

[0048] Specifically, based on a standardized student behavior dataset, the analysis of the continuity of student behavior during cross-task transitions involves the following steps: Extracting the operation frequency and student behavior trigger interval from the standardized student behavior dataset; multiplying the logarithm of the student behavior trigger interval (plus one) by the operation frequency to obtain the rhythm difference weighted value for the current task; extracting the first response delay time after task switching; subtracting the first response delay time from one and dividing by the average task completion time of the two adjacent tasks plus one to obtain the behavior continuity retention rate; multiplying the square root of the number of erroneous operations by the behavior continuity retention rate to obtain the continuity harmonic value; traversing all tasks included in the analysis within the current sliding window, summing the rhythm difference weighted values ​​of all tasks, and then summing this sum with the current continuity harmonic value to obtain the switching stability feature value.

[0049] The formula for calculating the switching stable eigenvalue is:

[0050] ;

[0051] In the formula, n represents the total number of tasks included in the analysis in the current sliding comparison window, which is used to set the number of task samples within the analysis range. It is the basic dimension parameter for calculating the switching stable feature value, and comes from the set of task numbers in the continuous sliding window in the task execution log. The operation frequency in the i-th task is used to measure the operation trigger density per unit time during task execution, reflecting the student's operational activity level. It is derived from the operation timestamp statistics in the task behavior time data of the behavior data collection module. This represents the student behavior trigger interval in the i-th task, which is the average time interval between two adjacent operations. It reflects the continuity and rhythm of the behavior and is derived from the time series calculation results in the behavior time data. This indicates the number of erroneous operations within the task switching section, reflecting the student's stability and operational accuracy during the task switching process. It is derived from the statistics of abnormal action markers in the task switching data, including accidental clicks, repeated clicks, and operational errors. It represents the delay time for the first response after a task switch, that is, the time required for a student to successfully respond to an instruction for the first time after a task change. It measures the adaptability to task switching and is derived from the time difference between the first operation record after the switch and the switch trigger point in the task switching data. This represents the average task completion time between two adjacent tasks, used to standardize response latency and error frequency. It is derived from the moving average of the start and end time differences of each task segment in the behavior stability data.

[0052] This implementation plan comprehensively assesses students' behavioral stability and adaptability during the switching of teaching tasks. The first half quantifies the continuity and rhythm of students' operations in consecutive tasks by measuring the operation frequency and behavior trigger interval of each task within a sliding window. The second half integrates the number of misoperations, the first response delay time, and the task completion time in the task switching segment to reflect the stability and adjustment ability of students during the task transition. The final calculated switching stability characteristic value can be used to identify abnormal behavior segments with short-term high fluctuations, rhythm drift, and operational breaks, providing a quantitative basis for subsequent behavioral rhythm instability alerts, teaching guidance strategy adjustments, and dynamic intervention mechanisms.

[0053] Specifically, the steps for dynamically adjusting the rhythm prompt strategy based on the analysis results are as follows: To dynamically grasp the continuity of students' behavior and the quality of rhythm transition during task switching, a switching stability feature value is continuously calculated based on a sliding window mechanism, and differentiated response strategies are triggered in combination with different changing trends. When the switching stability feature value continues to rise in three consecutive sliding windows, and the increase gradually expands, the operation sequence of the current and previous workstations is immediately recorded at the micro-period level, marking the number of task jumps, repeated behavior segments, and workstation switching duration. At the same time, the system simultaneously captures operation sequence misalignment, step jumps, and behavior sticking phenomena in the current task, automatically generates a list of correction suggestions on the terminal, and pushes behavior path optimization prompts corresponding to the current task's structure.

[0054] When the switching stable feature value frequently alternates between high and low in a continuous window and the fluctuation amplitude continues to increase, the behavior path structure between the current task and the previous and next tasks is retrieved in real time. The behavior rhythm breakpoint and switching stagnation node are extracted. Combined with the task structure analysis, the operation prompt frequency, behavior trigger density and information instruction accumulation rate are recorded. The problems of information input overload, excessive instruction density and prompt aggregation imbalance in the task process are identified, and the push frequency of auxiliary instructions is temporarily adjusted to reduce overload interference and release the student's operation buffer.

[0055] When the switching stable feature value maintains a slow change over multiple consecutive sliding windows, and the overall trend is relatively stable, the behavior path comparison algorithm is invoked to compare the rhythm characteristics of the current task structure with those of the previous volatile task node. This analyzes the differences in task rhythm changes and the degree of cognitive rhythm delay to determine if it belongs to a false stable state where the task rhythm is temporarily stable but cognitive synchronization is lagging. If signs of false stability appear, the algorithm deduces the high-difficulty segments and behavioral rhythm transition nodes in subsequent tasks based on the evolutionary relationship of the task stage structure. Before the rhythm load is expected to exceed the threshold, an advance warning page is proactively displayed to guide students in preparing for the rhythm transition, reducing the occurrence of rhythm instability in subsequent stages.

[0056] This implementation plan dynamically identifies the trend of students' behavioral continuity changes during task switching, accurately distinguishes three typical states: rhythm enhancement, rhythm disorder, and rhythm pseudo-stable, and triggers corresponding behavior recording mechanisms, auxiliary strategy adjustments, and rhythm warning prompts accordingly. This enables real-time monitoring and intervention of operational misalignment, information overload, and cognitive lag, thereby improving the rhythm adaptability of cross-task behavioral structures and the continuity of learning.

[0057] Specifically, using the rhythm stability assessment results and behavioral coherence analysis results as inputs, the comprehensive evaluation of rhythm evolution fluctuations during the teaching cycle involves the following steps: obtaining the switching stability feature value and the behavioral rhythm response value; multiplying the switching stability feature value and the behavioral rhythm response value as the numerator; adding one to the number of parallel subtasks within the task switching phase, taking the logarithm to the base 10, and adding one again as the denominator to obtain the rhythm switching fusion value; extracting the task switching frequency per unit time; multiplying the task switching frequency by the number of times the operation sequence disorder was identified within the current time window, and adding one again to obtain the enhancement adjustment value; and multiplying the rhythm switching fusion value by the enhancement adjustment value to obtain the behavioral fluctuation intensity value.

[0058] The formula for calculating the intensity of behavioral fluctuations is:

[0059] ;

[0060] In the formula, S represents the switching stability feature value, which is used to measure the consistency of students' behavior and operational stability during task transitions. The behavioral rhythm response value reflects the student's operational activity and rhythm adaptation level in the current task; D represents the number of parallel subtasks in the task switching phase, which describes the complexity of task switching, and the data comes from the synchronous switching path identification results. This indicates the frequency of task switching per unit of time, reflecting the intensity of switching behavior during task execution. It is obtained by statistically analyzing the number of task switching events within a standard time period, and is derived from task execution logs and switching trigger timestamp data. This indicates the number of times the operation sequence disorder was identified within the current time window. It is used to measure the degree of abnormality in the operation execution logic after task switching and is derived from the comparison results between the operation behavior sequence and the standard task path.

[0061] In this implementation example, the switching stability feature value of Case 1 is set to 0.612, the behavior rhythm response value is 0.735, the number of parallel subtasks is 3, the task switching frequency is 4, and the number of times the operation order is disordered is 2.

[0062] In Case 2, the switching stability feature value was set to 0.488, the behavior rhythm response value was 0.691, the number of parallel subtasks was 2, the task switching frequency was 3, and the number of times the operation order was disordered was 1.

[0063] In Case 3, the switching stability feature value was set to 0.823, the behavior rhythm response value was 0.812, the number of parallel subtasks was 4, the task switching frequency was 5, and the number of times the operation order was disordered was 3.

[0064] In Case 4, the switching stability feature value was set to 0.379, the behavior rhythm response value was 0.552, the number of parallel subtasks was 1, the task switching frequency was 2, and the number of times the operation order was disordered was 0.

[0065] In Case 5, the switching stability feature value was set to 0.693, the behavior rhythm response value was 0.624, the number of parallel subtasks was 2, the task switching frequency was 4, and the number of times the operation order was disordered was 1.

[0066] The switching stability feature value of Case 6 is set to 0.735, the behavior rhythm response value is 0.781, the number of parallel subtasks is 3, the task switching frequency is 5, and the number of times the operation order is disordered is 2.

[0067] In Case 7, the switching stability characteristic value was set to 0.511, the behavioral rhythm response value to 0.598, the number of parallel subtasks to 2, the task switching frequency to 3, and the number of times the operation sequence was disordered to 1. The behavioral fluctuation intensity value for each case was calculated, as shown in Table 1.

[0068] Case Number Switching stable eigenvalues Behavioral rhythm response value Number of parallel subtasks Task switching frequency Number of times the operation sequence is disordered Behavioral fluctuation intensity value Case 1 0.612 0.735 3 4 2 1.347 Case 2 0.488 0.691 2 3 1 0.954 Case 3 0.823 0.812 4 5 3 1.946 Case 4 0.379 0.552 1 2 0 0.466 Case 5 0.693 0.624 2 4 1 1.218 Case 6 0.735 0.781 3 5 2 1.754 Case 7 0.511 0.598 2 3 1 0.988

[0069] like Figure 3 The table shown is a bar chart of behavioral fluctuation intensity values ​​provided in this application example. (See Table 1 and...) Figure 3It can be seen that Case 3 has the highest behavioral fluctuation intensity value, indicating that its switching stability characteristic value and behavioral rhythm response value are both at a high level. Furthermore, it has a large number of parallel subtasks, a high task switching frequency, and numerous instances of disordered operation sequences. This comprehensively reflects that this case exhibits significant behavioral rhythm fluctuations, high operational density, and significant abnormalities in the behavioral path during the task switching phase. It is crucial to identify whether its task structure design and guidance rhythm settings are compatible, and to appropriately add rhythm balancing mechanisms and task diversion strategies to reduce behavioral load and improve execution continuity and stability. Case 4 has the lowest behavioral fluctuation intensity value, with both its switching stability characteristic value and behavioral rhythm response value at a relatively low level. It also has a limited task switching frequency and a limited number of parallel tasks, with zero instances of disordered operation sequences. This indicates that the behavioral rhythm in this task phase is stable, and the switching transition is smooth, representing a typical rhythmic stability segment. It can serve as a reference sample for subsequent behavioral rhythm modeling and task structure benchmark design. The behavioral fluctuation intensity value bar chart clearly reflects the differences in the distribution of rhythm fluctuation states during task execution and switching for each case. A higher evaluation value indicates greater rhythm adaptation pressure and a higher intervention priority for this task phase, and should be prioritized in the teaching rhythm optimization strategy development process.

[0070] Specifically, the steps for triggering the teaching intervention linkage mechanism based on the assessment results are as follows: Real-time comparison of the current behavioral fluctuation intensity value with the behavioral stability evolution threshold. The behavioral stability evolution threshold is composed of a first fluctuation threshold and a second fluctuation threshold, used to characterize the evolutionary stage features of the behavioral rhythm state under different fluctuation intensities.

[0071] When the intensity of behavioral fluctuation is less than or equal to the second fluctuation threshold, it is determined to be a rhythmic stability stage. During this stage, the rhythmic consistency of students' operational behaviors and the average time of step completion fluctuate less, showing high coordination and high predictability. Therefore, the current behavior collection frequency and label update strategy are kept running stably. At the same time, a low-frequency rhythm change tracking mechanism is activated in the task trajectory record. An extended time window is set to periodically detect the slight changes in the average operation interval and task completion time to determine whether a potential rhythmic evolution critical point has been entered.

[0072] When the intensity of behavioral fluctuations exceeds the second fluctuation threshold but is less than or equal to the first fluctuation threshold, it is determined to be a rhythm fluctuation transition phase, indicating a certain degree of sequential disorder and repetitive operations in the behavioral sequence. This phase focuses on identifying high-frequency backtracking nodes and repetitive triggering actions in the behavioral path, and visually differentiating completed and incomplete steps in the task flow. Completed steps are marked semi-transparently, while incomplete steps are highlighted to help students quickly identify their current behavioral progress. Simultaneously, the background calculates the logical jump index and repetitive path backtracking density between task steps, providing a structural basis for rhythm change modeling and subsequent strategy switching.

[0073] When the intensity of behavioral fluctuations exceeds the first fluctuation threshold, it is determined to be a stage of severe behavioral rhythm instability, requiring temporary structuring processing of the current task stage. First, this stage is divided into several sub-task blocks, each with a finer-grained task feedback rhythm and prompt interaction method to improve students' focus on the current operation content. Simultaneously, a rhythm intervention suggestion pop-up is pushed to the teacher's end, reminding them to intervene in the task rhythm configuration of this node in a timely manner. On the data recording end, a behavioral abnormal path compression mode is entered, automatically removing a large number of invalid jumps and repetitive paths in the behavioral path, retaining only the main logical steps and key feedback actions to reduce computational complexity and focus intervention resource allocation.

[0074] This implementation plan identifies and classifies the evolution of behavioral rhythms in real time, dynamically adjusts teaching rhythm intervention strategies, and improves the accuracy of feedback response and the adaptability of task guidance during periods of behavioral instability. During the stable rhythm phase, by maintaining the original behavior collection and labeling strategies and initiating low-frequency rhythm change tracking, potential rhythm evolution trends can be continuously detected, providing a foundation for the early warning mechanism and avoiding excessive intervention in the teaching process under stable conditions. During the transitional phase of rhythm fluctuations, by identifying high-frequency regression nodes and repetitive operational behaviors and labeling task flow states in a differentiated manner, students' self-rhythm awareness can be improved. Simultaneously, key node data is accumulated for backend behavioral path analysis, enhancing the structural clarity of rhythm evolution modeling. During the phase of severe rhythm instability, through task sub-block reconstruction and interactive prompt strategy adjustments, combined with teacher intervention pop-ups and abnormal path compression mechanisms, refined management and rapid guidance of rhythm imbalance segments are achieved, ensuring the recovery capability and intervention efficiency of the teaching rhythm under extreme fluctuations.

[0075] Specifically, based on the evolution trend of behavioral fluctuation intensity values, abnormal rhythm segments are identified, and instability characteristics are judged by combining switching stability feature values ​​and behavioral rhythm response values. Structured prompts are then generated and synchronously pushed to teachers and students. The specific steps are as follows: Based on the continuous evolution of behavioral fluctuation intensity values, the rhythm state of each stage within the sliding time window is dynamically determined. The slope, cumulative increase, and trend direction of the behavioral fluctuation intensity value in adjacent windows are extracted. When the fluctuation amplitude increases and the direction of change is consistent across three consecutive windows, it is identified as a potential abnormal rhythm segment. Further analysis of the switching stability feature values ​​and behavioral rhythm response values ​​within this abnormal segment is conducted. If both are in a high range, it is determined that there are significant rhythm instability characteristics during the current task execution, requiring immediate intervention.

[0076] Subsequently, based on the dynamic evolution trend of behavioral fluctuation intensity values, structured prompts are generated, including: the current rhythm level, the fluctuation starting point window number, the location of typical instability nodes, and the corresponding task stage. When the prompt target is a student, the prompt is embedded as an icon in the key operation area of ​​the task execution interface, using color gradients and graphic prompts to guide the operation rhythm back; when the prompt target is a teacher, the current student's behavioral fluctuation status, task node behavioral density, and behavioral rhythm curve are simultaneously pushed to the teaching monitoring panel, automatically activating the teacher intervention suggestion card and recommending appropriate intervention strategies based on different fluctuation levels.

[0077] When the detected rhythm instability level exceeds the intervention threshold, it indicates that the behavioral rhythm has deviated drastically from the expected task rhythm. This immediately triggers a temporary reconstruction mechanism for the prompt density and interaction frequency within the teaching terminal: extending the dwell time of graphic prompts for key steps by no less than 30%, temporarily suspending the seamless switching rhythm between tasks, and adding a buffer instruction display period for each sub-task stage. At the same time, a rhythm recovery tracking mechanism is activated, refreshing the student's behavioral rhythm curve in 3-second increments, accurately recording the rhythm stabilization trajectory, and continuously evaluating the effectiveness of the adjustment strategy.

[0078] This implementation plan accurately identifies rhythmic anomalies based on the dynamic evolution of behavioral fluctuation intensity values. It then combines multiple indicators to comprehensively assess rhythmic instability during task execution, thereby generating structured prompts and triggering differentiated guidance and intervention mechanisms for both students and teachers. This ensures that the teaching task maintains stable behavioral logic and effectively repairs the learning path even when rhythm is imbalanced. This step, through four stages—rhythm identification, prompt generation, dual-end response, and strategy reconstruction—improves the real-time and precision of task control, achieving a closed-loop rhythm management logic of early behavioral anomaly identification, rapid intervention for rhythmic instability, and flexible adjustment of prompt strategies. This helps reduce the risk of cognitive shock and behavioral disorder during task execution.

[0079] The second aspect of this invention provides a student behavior data management system for the teaching implementation process, comprising: a data acquisition and preprocessing module, used to acquire behavioral operation data, task transition data, and behavioral stability data during the execution of teaching tasks; the behavioral operation data includes the operation frequency within a unit task, the task operation response time, and the change in behavioral intervals between steps; the task transition data includes the task switching start and end nodes, response delay, and subtask overlap frequency; and the behavioral stability data includes the magnitude of operation sequence disturbance and behavior repetition rate; and performs preprocessing operations such as sliding window segmentation, rhythm baseline fitting, and interference point correction on the acquired behavioral operation data, task transition data, and behavioral stability data to construct a standardized student behavior dataset, providing a highly consistent basic expression for subsequent feature extraction and behavior evaluation;

[0080] The behavioral rhythm feature extraction module is used to evaluate the rhythm stability of students during task switching based on a standardized student behavior dataset, from two dimensions: the degree of rhythm deviation of the behavioral sequence within the task and the synchronicity of the operation response. Based on the rhythm stability level, it dynamically guides the prompt speed, task instruction granularity and behavioral example beat to match the student's current cognitive rhythm state and avoid task progress blockage caused by rhythm incompatibility.

[0081] The switching stability index generation module is used to extract the continuity of behavioral paths, operation time fluctuation value and task completion rhythm difference before and after the task switching node based on the standardized student behavior dataset. It quantifies the degree of behavioral coherence of students in the process of cross-task transition, and dynamically adjusts the rhythm prompt strategy based on the behavioral break position and the rate of change of the coherence curve, including adjusting the prompt frequency, switching reminder advance amount and information arrangement density.

[0082] The behavioral fluctuation window monitoring module is used to take the rhythm stability assessment results and behavioral coherence analysis results as inputs, integrate the rhythm deviation amplitude and operational response inertia trend, comprehensively evaluate the fluctuation of rhythm evolution in the teaching cycle, and match the corresponding teaching intervention type based on the fluctuation level to trigger a teaching intervention linkage mechanism of rhythm prompt reconstruction, task beat redirection and task path reorganization.

[0083] The rhythm instability alert and feedback trigger module is used to identify abnormal rhythm segments based on the evolution trend of behavioral fluctuation intensity values, combined with the rhythm peak distribution and instability duration within a sliding window. It also combines switching stable feature values ​​and behavioral rhythm response values ​​to determine instability characteristics. Structured alert information is generated and pushed to teachers and students in stable, transitional, and unstable states, respectively. On the student's end, pop-up micro-reminders guide the correction of task rhythm, while on the teacher's end, rhythm analysis cards indicate intervention priorities and intervention suggestions.

[0084] In this implementation plan, the data acquisition and preprocessing module comprehensively acquires various types of behavioral data during the execution of teaching tasks, including operation frequency, task response time, task switching path and behavioral stability characteristics. The module completes data standardization processing through sliding window segmentation, rhythm baseline fitting and interference correction, thus establishing a unified behavioral expression basis for subsequent feature extraction and rhythm analysis.

[0085] The behavioral rhythm feature extraction module extracts key features of the degree of deviation of the operation rhythm and the synchronicity of the response from the standardized behavioral dataset, identifies the rhythm stability of students during task switching, and supports dynamic adjustment of teaching prompt speech speed, operation demonstration rhythm and feedback density to achieve adaptive rhythm guidance in the teaching process.

[0086] The switching stability index generation module identifies the continuity and rhythm breakpoints of the operation logic before and after task switching, generates switching stability indexes that reflect the continuity and consistency of students' task transitions, and dynamically adjusts teaching prompt strategies based on the trend of index changes, optimizing the task switching rhythm and information prompt configuration.

[0087] The behavior fluctuation window monitoring module continuously assesses the fluctuation trend of rhythm evolution throughout the entire teaching task, integrates the results of rhythm stability and switching continuity to determine whether the current behavior has entered an unstable stage, and triggers teaching intervention mechanisms including prompting rhythm adjustment and information granularity reconstruction to improve the timeliness of response and control accuracy to abnormal rhythm states.

[0088] The rhythm instability alert and feedback trigger module locates rhythm instability segments based on the continuous evolution of behavioral fluctuation intensity and determines the level of instability characteristics by combining key rhythm response indicators. Then, it generates customized prompt information based on role identity, embedding it into the task interface in the form of operation guidance on the student's end, and pushing rhythm trend analysis and intervention suggestions on the teacher's end, thereby improving the efficiency of teachers and students in perceiving and responding to changes in teaching rhythm.

[0089] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0090] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for managing student behavior data in a teaching implementation process, characterized by: include: S1. Collect behavioral operation data, task transition data, and behavioral stability data during the execution of teaching tasks, and preprocess the collected behavioral operation data, task transition data, and behavioral stability data to construct a standardized student behavior dataset; S2, based on a standardized student behavior dataset, assesses the rhythm stability of students during task switching and provides behavioral guidance based on the assessment results. The specific steps for evaluating the rhythm stability during student task switching based on a standardized student behavior dataset are as follows: Extract the number of task operations per unit time, the number of operations within a unit task, and the average response time of students in the current task stage from the standardized student behavior dataset. Multiply the number of task operations, the number of operations, and the average response time of students by one to obtain the task behavior density value. Extract the number of repeated operations performed by students within a unit task, take the opposite number of the number of repeated operations, perform an exponential transformation, and then add one to obtain the behavior time diffusion value. Extract the mean of the operation interval and the rate of change of rhythm. Multiply the product of the rate of change of rhythm by one and the mean of the operation interval, take the reciprocal of the product, add one, and then take the logarithm to obtain the operation response elasticity value. The product of the task behavior density value and the operation response elasticity value is used as the numerator, and the behavior time diffusion value is used as the denominator to obtain the behavior rhythm response value. S3, based on a standardized student behavior dataset, analyzes the coherence of students' behavior during cross-task transitions and dynamically adjusts the pacing prompt strategy based on the analysis results. The specific steps for analyzing the consistency of student behavior during cross-task transitions based on a standardized student behavior dataset are as follows: Extract the operation frequency and student behavior trigger interval in the current task from the standardized student behavior dataset. Multiply the logarithm of the student behavior trigger interval (plus one) with the operation frequency to obtain the rhythm difference weighted value of the current task. Extract the first response delay time after task switching, and subtract the first response delay time from one and divide it by the average task completion time of the two adjacent tasks plus one to obtain the behavior continuity retention rate. The square root of the number of erroneous operations is multiplied by the continuity retention rate to obtain the continuity harmonic value; Traverse all tasks included in the analysis in the current sliding window, sum the rhythm difference weights of all tasks, and then add them to the current continuity harmonic value to obtain the switching stability feature value; S4 uses the results of rhythm stability assessment and behavioral coherence analysis as inputs to comprehensively assess the fluctuations in rhythm evolution during the teaching cycle, and triggers a teaching intervention linkage mechanism based on the assessment results. S5 identifies rhythmic abnormalities based on the evolution trend of behavioral fluctuation intensity values ​​and combines switching stable feature values ​​with behavioral rhythm response values ​​to determine instability characteristics, generating structured prompt information that is simultaneously pushed to teachers and students.

2. The student behavior data management method in a teaching implementation process according to claim 1, characterized in that: The specific steps for collecting behavioral operation data, task transition data, and behavioral stability data during the execution of teaching tasks, and preprocessing the collected behavioral operation data, task transition data, and behavioral stability data to construct a standardized student behavior dataset are as follows: The behavioral operation data during the execution of teaching tasks is collected through the teaching terminal logs. The behavioral operation data includes: the number of task operations per unit time, the number of operation actions within a unit task, the average response time and average operation interval of students in the current task stage, and the rhythm change rate is calculated by calculating the difference between the average operation interval of the current window and the previous window. Task transition data is collected through a task flow tracking mechanism. The task transition data includes: the first response delay time after task switching, the average task completion time of two adjacent tasks, the number of parallel subtasks in the task switching phase, and the task switching frequency per unit time. Behavioral stability data is collected through a behavioral sequence parsing engine. The behavioral stability data includes: the operation frequency in each task, the student behavior trigger interval, and the number of times the operation order is disordered. At the same time, the number of erroneous operations and the number of repeated operations in the task switching segment are recorded through a path backtracking detection algorithm. The collected behavioral operation data, task transition data, and behavioral stability data are standardized and normalized to correct the deviation in behavioral rhythm scale caused by differences in task type, operation habits, and teaching context. The standardized behavioral operation data, task transition data, and behavioral stability data are then archived and stored in a unified manner to construct a standardized student behavior dataset.

3. The method for managing student behavior data during the teaching process according to claim 1, characterized in that: The specific steps for guiding behavior based on the evaluation results are as follows: Real-time comparison of the current student's behavioral rhythm response value with the behavioral rhythm threshold: When the behavior rhythm response value is less than or equal to the behavior rhythm threshold, it is determined to be a stable rhythm coordination segment. Continue to use the current teaching task guidance beat, workstation operation guidance speech speed and operation demonstration rhythm, and maintain the stable operation of the sliding window length and data extraction parameter configuration of each behavior data collection node. There is no need to adjust the synchronization logic of operation feedback rhythm and workstation switching rhythm. When the behavior rhythm response value is greater than the behavior rhythm threshold, it is determined to be a rhythm imbalance transition section. The task operation response window length is dynamically shortened, and the sampling period of the current task operation frequency is shortened from 10 seconds to 5 seconds. This allows for high-frequency capture of students' rhythm instability details, enhances the temporal resolution of the behavior rhythm curve, and temporarily increases the frequency of workstation interaction prompts.

4. The method for managing student behavior data during the teaching process according to claim 1, characterized in that: The specific steps for dynamically adjusting the rhythm prompting strategy based on the analysis results are as follows: When the switching stable characteristic value continues to rise in three consecutive sliding windows and the increase gradually increases, the current and previous workstations are immediately recorded at the micro-cycle level. Simultaneously, the operation sequence misalignment, step jump and behavior sticking phenomena in the current task are captured, and operation sequence correction suggestions are automatically generated for students on the platform. When the switching stable feature value frequently alternates between high and low in a continuous window and the fluctuation amplitude increases significantly, the behavior path structure of adjacent task stages is retrieved in conjunction with the action, the rhythm discontinuity and switching blind spot of the operation logic of different workstations are identified, and at the same time, the problem of overload of operation information input, too dense instruction rhythm and uneven distribution of prompts in the current task node is dynamically judged, and the frequency of auxiliary instruction push is automatically reduced. When the switching stable feature value changes slowly and the trend is stable in multiple consecutive sliding windows, compare the difference between the current task behavior structure and the behavior path characteristics of the previous high-fluctuation task node to assess whether it belongs to a false stable state where the task rhythm is temporarily stable but cognition is not synchronized. When it is determined to be in a false stable state, deduce the structural maladaptation zone of the next task stage and push an advance reminder page before entering.

5. The method for managing student behavior data during the teaching process according to claim 1, characterized in that: The specific steps for comprehensively evaluating the fluctuations in rhythm evolution during the teaching cycle, using the results of rhythm stability assessment and behavioral coherence analysis as inputs, are as follows: Obtain the switching stable feature value and the behavior rhythm response value. Take the product of the switching stable feature value and the behavior rhythm response value as the numerator, and take the logarithm of the number of parallel subtasks in the task switching phase plus one as the denominator to obtain the rhythm switching fusion value. Extract the task switching frequency per unit time, multiply the task switching frequency by the number of times the operation sequence disorder was identified within the current time window, and then add one to obtain the enhancement adjustment value; Multiplying the rhythm switching fusion value by the enhancement adjustment value yields the behavioral fluctuation intensity value.

6. The method for managing student behavior data during the teaching process according to claim 1, characterized in that: The specific steps for triggering the teaching intervention linkage mechanism based on the assessment results are as follows: Real-time comparison of the current behavioral fluctuation intensity value with the behavioral stability evolution threshold, which includes a first fluctuation threshold and a second fluctuation threshold: When the intensity of behavioral fluctuation is less than or equal to the second fluctuation threshold, it is determined to be a stable rhythm phase. The existing behavior collection frequency and tag update strategy are maintained unchanged, and a low-frequency rhythm change tracking mechanism is started simultaneously to periodically detect the slight changes in operation interval and step completion time. When the intensity of behavioral fluctuation is greater than the second fluctuation threshold and less than or equal to the first fluctuation threshold, it is determined to be the rhythm fluctuation transition stage. Priority is given to identifying high-frequency backtracking nodes and repeated triggering operations in the behavioral sequence. At the same time, completed and incomplete task steps are marked in the task flow with semi-transparent and highlighted color-coded. The background synchronously collects the logical jump index and repeated path backtracking density between the operation steps in this stage. When the intensity of behavioral fluctuations exceeds the first fluctuation threshold, it is determined to be a stage of severe behavioral rhythm instability. The current task stage is temporarily divided into several sub-task blocks, and the operation feedback rhythm and prompt interaction method within the stage are reset. At the same time, a rhythm intervention suggestion pop-up is pushed to the teacher's end, and the abnormal behavior path compression mode is entered simultaneously, retaining only the main logic and key feedback actions.

7. The method for managing student behavior data during the teaching process according to claim 1, characterized in that: The specific steps for identifying rhythmic abnormalities based on the evolution trend of behavioral fluctuation intensity values, determining instability characteristics by combining switching stable feature values ​​and behavioral rhythm response values, and generating structured prompt information to be synchronously pushed to teachers and students are as follows: Based on the continuous evolution of behavioral fluctuation intensity values, sliding windows in rhythm abnormality segments are identified, and the switching stability feature value and behavioral rhythm response value within the window are combined to determine whether there are rhythm instability features during the current task execution process. Subsequently, structured prompts are generated based on the intensity of behavioral fluctuations, and processed according to the prompt objectives: for students, the prompts are embedded in the task execution interface to guide their operations; for teachers, the current behavioral status and rhythm evolution trend of students are pushed synchronously, and teacher intervention suggestion cards are activated. When the rhythm becomes severely unstable, the prompt density and interaction rhythm of the teaching terminal are automatically adjusted. In subsequent tasks, the dwell time of prompts for key steps is extended, the frequency of task switching is reduced, and the recovery of the behavior rhythm is tracked in real time.

8. A student behavior data management system for the teaching implementation process as described in any one of claims 1-7, characterized in that: include: The data acquisition and preprocessing module is used to collect behavioral operation data, task transformation data, and behavioral stability data during the execution of teaching tasks, and to preprocess the collected behavioral operation data, task transformation data, and behavioral stability data to construct a standardized student behavior dataset. The behavior rhythm feature extraction module is used to evaluate the rhythm stability of students during task switching based on a standardized student behavior dataset, and to guide behavior based on the evaluation results. Switch the stability index generation module to analyze the consistency of students' behavior during cross-task transitions based on a standardized student behavior dataset, and dynamically adjust the rhythm prompt strategy based on the analysis results. The behavioral fluctuation window monitoring module is used to comprehensively evaluate the fluctuation of rhythm evolution during the teaching cycle, taking the rhythm stability assessment results and behavioral coherence analysis results as inputs, and triggering a teaching intervention linkage mechanism based on the assessment results. The rhythm instability alert and feedback trigger module is used to identify abnormal rhythm segments based on the evolution trend of behavioral fluctuation intensity values, and to judge instability characteristics by combining switching stable feature values ​​and behavioral rhythm response values, generating structured alert information and pushing it synchronously to teachers and students.

Images