Task scheduling and monitoring method for teacher console based on data analysis

Abstract

The invention relates to the technical field of intelligent teaching, in particular to a teacher console task scheduling and monitoring method based on data analysis, and the method comprises the steps: collecting task execution data, including participation degree, task completion progress and response time, of students, and combining machine learning models such as an adaptive enhancement algorithm, a long-short-term memory network and a random forest; according to the method and the system, personalized task scheduling of students is realized, a real-time data monitoring and dynamic adjustment strategy is adopted, optimal configuration of task difficulty and time length is generated according to student performance data, task risks are identified through a support vector machine model, and multi-level early warning and intervention suggestions are provided. Performing long-term trend analysis and grouping on historical data by using a K-Means clustering algorithm, and supporting a personalized optimization scheme of task allocation; according to the invention, the problem that the task allocation is not matched with the actual learning state of the student in the prior art is effectively solved, the flexibility of task scheduling and the learning effect of the student are improved, and a more accurate and efficient teaching management tool is provided for a teacher.

Description

Technical Field

[0001] The present invention relates to the field of intelligent teaching technology, and in particular to a teacher console task scheduling and monitoring method based on data analysis. Background Art

[0002] In modern education, digital learning platforms and intelligent teacher consoles are gradually becoming core tools for classroom management and teaching support. Through integrated data analysis and automated management functions, these systems can help teachers more efficiently assign tasks, monitor students' learning performance, and provide personalized teaching support in large-scale online and hybrid teaching environments. With the increasing demand for personalized teaching in the education field, the importance of intelligent task scheduling and real-time monitoring is becoming increasingly prominent. By timely collecting and analyzing data such as student participation, task completion, and response time, the intelligent teacher console is expected to achieve a comprehensive understanding of students' learning status, thereby providing dynamic task allocation and real-time feedback that adapts to individual student performance, improving teaching efficiency and learning outcomes.

[0003] However, the existing intelligent teacher console still has significant problems in technical implementation. Current technologies are mostly limited to simple automated task allocation and static data monitoring, lacking the ability to dynamically adapt to students' learning status, and often failing to make personalized adjustments to task parameters based on students' real-time feedback data, resulting in a mismatch between task difficulty and duration and students' actual learning status. Existing technologies also have deficiencies in forward-looking task planning and personalized intervention, lacking effective prediction and early warning mechanisms for learning bottlenecks that students may face. In addition, the lack of in-depth analysis capabilities for long-term data makes it difficult to provide targeted task scheduling optimization for students with different learning progress. Summary of the invention

[0004] The invention provides a teacher console task scheduling and monitoring method based on data analysis.

[0005] The task scheduling and monitoring method of the instructor console based on data analysis includes the following steps:

[0006] S1, Data Collection: Collect real-time and historical data related to tasks and student participation, including task assignment information and student participation indicators. Student participation indicators include attention span, participation rate and task completion speed. The data is transmitted to the central data warehouse in real time through the integrated sensor network and feedback system for subsequent data analysis;

[0007] S2, dynamic task scheduling: Based on the real-time and historical data collected by S1, tasks are dynamically assigned using an adaptive enhancement algorithm. The adaptive enhancement algorithm analyzes students’ participation and completion speed characteristics, determines the difficulty and duration of tasks, and ensures that tasks match students’ current performance status. Adjustments are made based on real-time data during the assignment process.

[0008] S3, real-time monitoring: real-time monitoring of students' task execution, including task completion progress, participation and response time. The monitoring threshold is set through the mean-variance model. When the real-time data deviates from the set threshold range, an abnormal warning is triggered and a prompt is sent to the instructor so that the instructor can adjust the task or intervene in time.

[0009] S4, Predictive Analysis: Use the long short-term memory network model to perform deep learning analysis on the historical data and real-time data in S1 to predict future task scheduling needs. The long short-term memory network model generates prediction results about task completion trends and participation changes by extracting long-term and short-term features from the data, providing suggestions for future task allocation and supporting instructors to adjust tasks in advance.

[0010] S5, feedback-based adjustment: Based on the students’ current task execution status data from S3 real-time monitoring feedback, the random forest model is used to dynamically adjust the task parameters;

[0011] S6, Historical Data Storage and Analysis: Store students’ task execution status data and participation records, support long-term trend analysis and task scheduling strategy optimization, use K-Means clustering algorithm to classify students’ historical task execution status data, group and analyze students’ task execution status data by participation and task completion, and develop personalized task allocation plans for students at different progress levels;

[0012] S7, Early Warning and Intervention: Based on the support vector machine classification model, multi-level early warnings are issued to instructors when low participation and task delays are detected. The support vector machine classification model identifies task risks and generates intervention suggestions for instructors.

[0013] Optionally, the S1 includes:

[0014] S11, collection of task assignment information: through the integrated sensor network and the teacher console, the task information assigned to students in the current system is collected in real time. The task information includes the type of task, task requirements, assignment time and task deadline. The collected task information is marked in the form of timestamp to ensure the real-time and traceability of the data, and is automatically updated to the central data warehouse;

[0015] S12, collection of student engagement indicators: real-time monitoring of student engagement and collection of student engagement indicators through integrated sensors, including attention span, engagement rate, and task completion speed;

[0016] S13, data transmission and real-time update: the collected task information (including task type, task requirements, assignment and deadline) and student participation indicators (including attention span, participation rate and task completion speed) are transmitted to the central data warehouse through the integrated sensor network;

[0017] S14, historical data storage: classify and store historical data, including classification by time series, task type and student participation.

[0018] Optionally, S2 includes:

[0019] S21, task feature extraction: extract the student participation and completion speed features based on the collected real-time data and historical data;

[0020] S22, Adaptive enhancement algorithm construction: Use the adaptive enhancement algorithm as the scheduling algorithm to dynamically allocate tasks according to the features extracted in S21;

[0021] S23, determination of task difficulty and duration: dynamically set appropriate task difficulty and task duration for students based on the task allocation results calculated by the adaptive enhancement algorithm;

[0022] S24, real-time dynamic adjustment: During the task assignment process, continuously monitor students' real-time data, including attention span, participation rate, and task completion speed, and dynamically adjust task parameters according to changes in real-time data.

[0023] Optionally, the S3 includes:

[0024] S31, task execution status monitoring: real-time collection of student status data during task execution, including task completion progress, participation and response time;

[0025] Status data is collected in real time during task execution and transmitted to the central data warehouse to support subsequent anomaly detection and warning triggering;

[0026] S32, mean-variance model construction: construct a mean-variance model based on student historical data to set the monitoring threshold range. The mean-variance model is used to evaluate the normal range of students' task completion progress, participation and response time;

[0027] S33, abnormal warning triggering: During the task execution process, the student's task completion progress, participation and response time are monitored in real time. When a certain indicator deviates from the threshold range set by the indicator, an abnormal warning is automatically triggered and a prompt message is sent to the instructor;

[0028] S34, real-time feedback and task adjustment suggestions: abnormal warnings are fed back to the instructor console, and task adjustment suggestions are made based on the students' real-time data deviations. Adjustment suggestions include reducing task difficulty, increasing task completion time, or arranging one-on-one guidance.

[0029] Optionally, the S4 includes:

[0030] S41, data preprocessing: preprocess the historical data and real-time data collected in step S1 to ensure the integrity and consistency of the input data. The preprocessing includes normalization, missing value filling and time series reconstruction;

[0031] S42, Construction of long short-term memory network model: Establish a long short-term memory network model, perform deep learning analysis on preprocessed historical data and real-time data, and extract long-term and short-term features from historical data.

[0032] Optionally, S4 further includes:

[0033] S43, trend prediction output: through the constructed long short-term memory network model, the prediction results of task completion trend and student participation change in the future period are generated;

[0034] S44, Task Allocation Suggestion: Generate future task allocation suggestions based on the prediction results of task completion trends and participation changes generated by the long short-term memory network model;

[0035] S45, early implementation of task adjustment and intervention: The generated suggestions are fed back to the instructor console in real time to support instructors in making task adjustments and personalized interventions in advance.

[0036] Optionally, the S5 includes:

[0037] S51, collection and collation of students’ current task execution status data: based on the real-time monitoring feedback in S3, collect students’ current task execution status data, including participation, task completion progress and response time;

[0038] S52, Random Forest Model Construction: Use the random forest model to analyze students’ current task execution status data and dynamically adjust the difficulty and duration of the task;

[0039] S53, determination of optimal task parameters: through the output of the random forest model, determine the optimal task difficulty and task duration configuration to adapt to the student's current performance status;

[0040] S54, real-time application and feedback of task parameters: Apply the optimal task difficulty and task duration configuration determined by the random forest model to students’ task allocation, and continuously monitor the task execution effect.

[0041] Optionally, the S6 includes:

[0042] S61, storage of student task execution status data: the task execution status data collected from the student task execution is stored in time series, the data is stored in the central data warehouse, and hierarchically managed according to task type, student ID and time;

[0043] S62, long-term trend analysis: long-term analysis of students’ performance trends based on their historical task execution status data;

[0044] S63, task scheduling strategy optimization: automatically adjust the task scheduling strategy based on the results of long-term trend analysis;

[0045] S64, K-Means cluster analysis: Use the K-Means clustering algorithm to classify students' historical task execution status data, and group students according to their participation and task completion status;

[0046] S65, personalized task assignment plan generation: Based on the K-Means clustering results, personalized task assignment plans are formulated for different groups of students.

[0047] Optionally, the S7 includes:

[0048] S71, collection and arrangement of task risk data: based on the data collected in the real-time monitoring of step S3, a risk assessment is performed on the student's task execution status. The collected task risk data includes participation, task completion progress and response time;

[0049] S72, Support Vector Machine Classification Model Construction: Build and train a support vector machine classification model to identify the risks of low engagement and task delays;

[0050] S73, multi-level warning triggering: During the task execution process, the support vector machine classification model monitors the students' task risk data in real time. When the classification results show that there is a risk in the students' task execution (such as low participation or task delay), the multi-level warning mechanism is triggered;

[0051] S74, Generation of intervention suggestions: Generate targeted intervention suggestions for teachers based on the classification results of the support vector machine classification model;

[0052] S75, Instructor feedback and intervention optimization: After the instructor implements the intervention measures, the students' task execution status data is continuously monitored, and the feedback results are used to optimize the support vector machine classification model.

[0053] Beneficial effects of the present invention:

[0054] The present invention realizes dynamic task scheduling based on individual student performance by collecting students' task execution status and historical task execution status data in real time, combining advanced machine learning algorithms such as adaptive enhancement algorithm, long short-term memory network and random forest model. In a data-driven way, the difficulty and duration of tasks can be dynamically set according to students' participation, task completion speed, response time and other characteristics, and real-time adjustments can be made continuously during task execution, so that task configuration can more accurately adapt to students' actual learning status. This dynamic adaptability greatly improves students' task completion rate and participation enthusiasm, thereby optimizing learning effects and realizing personalized teaching support.

[0055] The present invention uses a long short-term memory network to perform deep learning analysis on students' historical task execution status data and real-time data, extracts long-term and short-term characteristics of students in task completion trends and changes in participation, and generates forward-looking task allocation suggestions, so that teachers can identify learning bottlenecks that students may face in advance and make task adjustments or interventions in a timely manner. In addition, the classification warning mechanism based on the support vector machine classification model sends multi-level warnings to teachers when low student participation or task delays are detected, and provides personalized intervention plans (such as supplementary exercises or one-on-one tutoring). This forward-looking planning and real-time intervention measures help to quickly correct students' learning deviations, support teachers to actively manage students' learning progress, and effectively improve teaching efficiency.

[0056] The present invention stores students' task execution status data by time series classification, combines the K-Means clustering algorithm, performs group analysis on students' learning progress, and supports long-term trend analysis and task scheduling strategy optimization. By analyzing the long-term changing trends of students' participation, task completion, etc., it is possible to identify groups of students with different progress, and tailor personalized task allocation plans for students with different learning progress. This scheduling strategy optimization based on long-term data not only improves the accuracy and adaptability of task allocation, but also improves the flexibility of the system in responding to different learning needs, effectively promoting students' overall learning progress and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A schematic diagram of a method flow chart of an embodiment of the present invention;

[0059] Figure 2 Schematic diagram of S4 process according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0061] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0062] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0063] like Figure 1-Figure 2 As shown, the teacher console task scheduling and monitoring method based on data analysis includes the following steps:

[0064] S1, Data Collection: Collect real-time and historical data related to tasks and student participation, including task assignment information and student participation indicators. Student participation indicators include attention span, participation rate and task completion speed. The data is transmitted to the central data warehouse in real time through the integrated sensor network and feedback system for subsequent data analysis;

[0065] S2, dynamic task scheduling: Based on the real-time data and historical data collected by S1, the adaptive enhancement algorithm is used to dynamically assign tasks. The adaptive enhancement algorithm analyzes the students' participation and completion speed characteristics, determines the difficulty and duration of the task, and ensures that the task matches the students' current performance status. During the assignment process, adjustments are made based on real-time data, thereby improving learning effects and task execution efficiency.

[0066] S3, real-time monitoring: real-time monitoring of students' task execution, including task completion progress, participation and response time. The monitoring threshold is set through the mean-variance model. When the real-time data deviates from the set threshold range, an abnormal warning is triggered and a prompt is sent to the instructor so that the instructor can adjust the task or intervene in time.

[0067] S4, predictive analysis: Use the long short-term memory network model to perform deep learning analysis on the historical data and real-time data in S1 to predict future task scheduling needs. The long short-term memory network model generates prediction results on task completion trends and participation changes by extracting long-term and short-term features from the data, providing forward-looking suggestions for future task allocation and supporting instructors to adjust tasks in advance;

[0068] S5, feedback-based adjustment: Based on the current task execution status data of students from S3 real-time monitoring feedback, the random forest model is used to dynamically adjust the task parameters. The random forest model combines the current participation of students and the completion of tasks, and analyzes the optimal task difficulty and duration configuration through a decision tree, so as to adapt to the personalized needs of students and maintain the real-time adaptability of tasks.

[0069] S6, Historical Data Storage and Analysis: Store students’ task execution status data and participation records, support long-term trend analysis and task scheduling strategy optimization, use K-Means clustering algorithm to classify students’ historical task execution status data, group and analyze students’ task execution status data by participation and task completion, and develop personalized task allocation plans for students at different progress levels;

[0070] S7, Early Warning and Intervention: Based on the support vector machine classification model, a multi-level early warning is issued to the instructor when low participation and task delay are detected. The support vector machine classification model identifies task risks and generates intervention suggestions for the instructor, such as supplementary exercises and one-on-one tutoring, to support the instructor in conducting timely and effective targeted intervention.

[0071] S1 includes:

[0072] S11, collection of task assignment information: through the integrated sensor network and the instructor console, the task information assigned to students in the current system is collected in real time. The task information includes the type of task, specific requirements of the task, the assignment time and the deadline of the task. The collected task information is annotated in the form of a timestamp to ensure that the data is real-time and traceable, and automatically updated to the central data warehouse to provide support for subsequent task scheduling and predictive analysis;

[0073] S12, collection of student engagement indicators: real-time monitoring of student engagement and collection of student engagement indicators through integrated sensors, including attention span, engagement rate, and task completion speed, among which;

[0074] Attention duration: reflects the duration of students' concentration during task execution, recorded in seconds. Attention duration is generated by capturing students' gaze direction, facial expressions and other characteristic information, and transmitted to the central data warehouse in real time;

[0075] Participation rate: reflects the frequency of students' task interaction per unit time, measured in seconds. This data is calculated by recording students' behavioral characteristics such as clicks, operation frequency, and response time.

[0076] Task completion speed: It refers to the ratio between the time students actually complete the task and the standard time set for the task. The task completion speed is recorded as a dimensionless value, which can effectively reflect the performance of students in the task execution process;

[0077] S13, data transmission and real-time update: The collected task information (including task type, task requirements, allocation and deadline) and student participation indicators (including attention span, participation rate and task completion speed) are transmitted to the central data warehouse through the integrated sensor network. The central data warehouse is equipped with a real-time data update function to ensure the timeliness and continuity of the data, and provide a unified basic data source for subsequent task dynamic scheduling, real-time monitoring and predictive analysis. The data is encrypted during the transmission process to ensure the security and privacy of the information;

[0078] S14, Historical data storage: Classify and store historical data, including classification by time series, task type and student participation. The historical data management strategy adopts a hierarchical storage mechanism to separate short-term historical data and long-term historical data. Short-term historical data provides real-time data analysis support, while long-term historical data is used for trend analysis and model training to improve the adaptability and prediction accuracy of the system.

[0079] Through the detailed collection, transmission and storage management of task assignment information and student engagement indicators, high-quality and timely data support is provided for dynamic task scheduling and subsequent analysis, ensuring that task assignment can adapt to students' learning status in real time and accurately reflect students' task execution.

[0080] S2 includes:

[0081] S21, task feature extraction: Based on the collected real-time data and historical data, the student participation and completion speed characteristics are extracted. The extracted task features include;

[0082] Attention span: reflects the length of time students focus on the task;

[0083] Participation rate: reflects the frequency of students’ task interaction per unit time;

[0084] Task completion speed: the ratio of the time it takes students to complete a task to the standard time it takes to complete the task;

[0085] S22, Adaptive Enhancement Algorithm Construction: Use the adaptive enhancement algorithm as the core scheduling algorithm to dynamically allocate tasks based on the features extracted in S21. The adaptive enhancement algorithm improves scheduling accuracy by combining multiple weak classifiers, which is expressed as:

[0086] ;

[0087] in, represents the number of weak classifiers, For the The weights of weak classifiers, For the The output of weak classifiers, in each iteration, the system is based on the student characteristics , ,and To update the weights ,gradually improve the accuracy of task allocation;

[0088] S23, determination of task difficulty and duration: dynamically set appropriate task difficulty and task duration for students based on the task allocation results calculated by the adaptive enhancement algorithm, where;

[0089] Task difficulty: used to indicate the complexity of the task. The task difficulty is evaluated based on the comprehensive results of the student's participation rate and task completion speed to ensure that the task difficulty matches the student's current status;

[0090] Task duration: According to students’ real-time performance data (such as attention span and task completion speed), set a reasonable task completion time to improve task execution efficiency;

[0091] S24, real-time dynamic adjustment: During the task allocation process, students’ real-time data, including attention span, participation rate, and task completion speed, are continuously monitored, and task parameters are dynamically adjusted according to changes in real-time data. When students’ performance changes significantly, task difficulty and duration are immediately re-evaluated, and the weight coefficient of the adaptive reinforcement algorithm is updated to ensure that task allocation can adapt to students’ real-time learning status;

[0092] Dynamic task scheduling is achieved through an adaptive enhancement algorithm. Based on real-time participation data and historical performance, the task difficulty and duration are dynamically set and adjusted in real time, thereby effectively improving task matching and learning effects.

[0093] S3 includes:

[0094] S31, task execution status monitoring: real-time collection of student status data during task execution, including task completion progress, participation and response time;

[0095] Task completion progress: indicates the percentage of students completing tasks, reflecting the overall progress of students in the task execution process;

[0096] Engagement: the frequency of students' task interaction per unit time, measured in seconds;

[0097] Response time: indicates the time it takes students to respond to task operations or questions, in seconds;

[0098] Status data is collected in real time during task execution and transmitted to the central data warehouse to support subsequent anomaly detection and warning triggering;

[0099] S32, mean-variance model construction: A mean-variance model is constructed based on students' historical data to set the monitoring threshold range. The mean-variance model is used to evaluate the normal range of students' task completion progress, participation, and response time. The calculation formula is as follows:

[0100] Mean :Calculate the average value of a certain indicator of students, expressed as:

[0101] ;

[0102] in, is the total number of historical data points, For the The observed value of data points;

[0103] variance :Calculate the variance of a student's indicator to measure the degree of dispersion of the data, expressed as:

[0104] ;

[0105] By the mean and variance Set the monitoring threshold range for each indicator ,in It is an adjustable threshold parameter used to control the sensitivity of the warning;

[0106] S33, abnormal warning trigger: During the task execution process, the student's task completion progress, participation and response time are monitored in real time. If any indicator deviates from the threshold range set by the indicator, When the abnormality is detected, the abnormal warning is automatically triggered and a prompt message is sent to the teacher. The abnormal warning message contains specific abnormal indicators and their numerical deviations, so that the teacher can understand the student's status in time and make corresponding adjustments or intervention measures.

[0107] S34, real-time feedback and task adjustment suggestions: abnormal warnings are fed back to the instructor console, and task adjustment suggestions are made according to the students' real-time data deviations. The adjustment suggestions include reducing the difficulty of the task, increasing the task completion time limit or arranging one-on-one guidance. This real-time feedback mechanism enables the instructor to respond quickly when abnormal situations occur, ensuring that the student's task execution process is always under effective monitoring;

[0108] By real-time monitoring of students' task completion progress, participation and response time, and combining the monitoring thresholds set by the mean-variance model, it is possible to trigger early warnings and provide feedback on adjustment suggestions when students' performance is abnormal, ensuring that teachers can intervene in students' task execution in a timely manner, thereby improving the timeliness and pertinence of teaching management.

[0109] S4 includes:

[0110] S41, data preprocessing: preprocess the historical data and real-time data collected in step S1 to ensure the integrity and consistency of the input data. The preprocessing includes normalization, missing value filling and time series reconstruction, wherein;

[0111] Normalization: Normalize attention duration, participation rate, and task completion speed, and map all data to the range of [0, 1] to improve the learning efficiency of the model;

[0112] Missing value filling: Use interpolation or mean filling methods to handle missing data and ensure the continuity of input data;

[0113] Time series reconstruction: Reconstruct the students’ participation and performance data into a time series format according to the chronological order of task completion so as to be input into the long short-term memory network model;

[0114] S42, Construction of long short-term memory network model: Establish a long short-term memory network model, perform deep learning analysis on pre-processed historical data and real-time data, and extract long-term and short-term features from historical data. The structure and calculation steps of the long short-term memory network model include:

[0115] (1) Forget Gate : Determines whether the memory unit of the previous moment is retained. The formula is expressed as:

[0116] ;

[0117] (2) Input gate : Controls the update degree of the current input information. The formula is:

[0118] ;

[0119] (3) Candidate memory units : Generate candidate memory content at the current moment, the formula is expressed as:

[0120] ;

[0121] (4) Update memory unit status :Update the memory unit state according to the output of the forget gate and the input gate. The formula is:

[0122] ;

[0123] (5) Output gate : Determine the degree of output content, the formula is expressed as:

[0124] ;

[0125] (6) Hidden state : Generate the final output at the current moment, the formula is expressed as:

[0126] ;

[0127] Through the long short-term memory network model, deep learning analysis is performed on historical and real-time data to extract long-term and short-term features in the data, providing high-quality input for subsequent task completion trend and participation change predictions, thereby improving the system's prediction accuracy and stability.

[0128] S4 also includes:

[0129] S43, trend prediction output: through the constructed long short-term memory network model, the prediction results of task completion trend and student participation change in the future period are generated, where;

[0130] Task completion trend prediction: Based on students’ task completion speed and task completion progress data, the long short-term memory network model outputs the expected progress change of task completion, reflecting the possible status of task completion in the future;

[0131] Prediction of participation changes: Combined with students’ attention span and participation rate, the long short-term memory network model outputs the future trend of student participation changes, identifies possible low participation situations, and provides data support for early intervention;

[0132] S44, Task Allocation Suggestions: Generate forward-looking suggestions for future task allocation based on the prediction results of task completion trends and participation changes generated by the long short-term memory network model. The suggestions include:

[0133] Task difficulty adjustment: When the forecast results show that the progress of future task completion may be delayed, it is recommended to reduce the task difficulty to ensure that the task is completed on time;

[0134] Task duration adjustment: Based on the participation prediction, the system can suggest extending or shortening the task assignment duration to adapt to the student's status changes and ensure the matching degree of task assignment;

[0135] Personalized intervention plans: When a student’s engagement is predicted to decline, the system can recommend additional learning tasks or one-on-one guidance to the instructor to support the student’s continued engagement;

[0136] S45, early implementation of task adjustment and intervention: The generated forward-looking suggestions are fed back to the instructor console in real time to support instructors to make task adjustments and personalized interventions in advance. This step ensures that when students' performance may decline or there is a risk of task completion, instructors can respond quickly and improve the success rate of task execution;

[0137] The prediction output of the long short-term memory network model generates prediction results of task completion trends and participation changes, and provides forward-looking task allocation suggestions, allowing instructors to make task adjustments and intervention decisions in advance, thereby improving students' task completion rate and participation.

[0138] S5 includes:

[0139] S51, collection and collation of students' current task execution status data: according to the real-time monitoring feedback in S3, collect students' current task execution status data, including participation, task completion progress and response time, among which;

[0140] Engagement: the frequency of students' task interaction per unit time, measured in seconds;

[0141] Task completion progress: indicates the percentage of students completing the task, expressed as a percentage;

[0142] Response time: the time it takes for students to respond to tasks or questions, in seconds;

[0143] The above feedback data is sorted into time series and used as the input of the random forest model to support real-time adjustment of task parameters;

[0144] S52, Random Forest Model Construction: Use the random forest model to analyze the students' current task execution status data and dynamically adjust the difficulty and duration of the task. The random forest model is composed of multiple decision trees, and its output is the average of the prediction results of each decision tree. The model establishment process is as follows:

[0145] (1) Data segmentation: Divide the student's current task execution status data set into a training set and a test set to ensure that the model can be effectively learned and verified;

[0146] (2) Decision tree construction: randomly select subsamples from the training set and construct multiple decision trees. Each tree analyzes the student’s current task execution status data.

[0147] (3) Integrated prediction: The output results of all decision trees are weighted averaged to generate prediction results for the optimal task difficulty and duration to ensure the stability and accuracy of the prediction results;

[0148] S53, determination of optimal task parameters: through the output of the random forest model, determine the optimal task difficulty and task duration configuration to adapt to the student's current performance status, including;

[0149] Task difficulty: Analyze students’ current participation and task completion progress based on feedback from students’ current task execution status data, and dynamically adjust the complexity of the task to match it with students’ actual abilities;

[0150] Task duration: dynamically adjust the task duration based on the student's response time and task completion progress to ensure that students can complete the task within a reasonable time;

[0151] S54, real-time application and feedback of task parameters: Apply the optimal task difficulty and task duration configuration determined by the random forest model to the students’ task assignment, and continuously monitor the task execution effect. If the adjusted task parameters significantly improve the students’ task completion rate and participation, update the parameter settings and store them as reference data for subsequent scheduling to ensure the personalization and adaptability of task assignment;

[0152] The random forest model is used to analyze the feedback data of students' current task execution status, and dynamically adjust the task difficulty and duration, so that the task configuration can adapt to their learning needs in real time according to their performance, improve the matching degree and completion efficiency of the task, and better support personalized learning experience.

[0153] S6 includes:

[0154] S61, storage of student task execution status data: the task execution status data collected from student task execution is stored in time series, the data is stored in the central data warehouse, and hierarchically managed according to task type, student ID and time to support efficient data call and analysis;

[0155] S62, long-term trend analysis: conduct long-term analysis of students’ performance trends based on their historical task execution status data, and conduct time series analysis on each student’s participation, task completion, and response time to identify changing trends in students’ performance during the learning process, including improvements in learning speed and changes in attention. Long-term trend analysis provides a basis for optimizing strategies for subsequent task allocation;

[0156] S63, task scheduling strategy optimization: based on the results of long-term trend analysis, automatically adjust the task scheduling strategy. If a student's participation or task completion shows a positive trend of improvement, the student's task difficulty can be gradually increased. If it is detected that the participation or completion rate is declining, the task difficulty can be appropriately reduced and the task time limit can be extended to ensure that the task matches the student's current learning status.

[0157] S64, K-Means cluster analysis: Use the K-Means clustering algorithm to classify the students' historical task execution status data, and group and analyze the students according to their different participation levels and task completion status. The process of the K-Means algorithm is as follows:

[0158] (1) Determine the initial cluster centers: randomly select K cluster centers and cluster the students’ historical task execution status data according to participation and task completion status;

[0159] (2) Assign data to cluster centers: Calculate the distance between each student and each cluster center and assign the student to the nearest cluster center;

[0160] (3) Update cluster centers: recalculate the cluster centers of each group and iterate until the cluster centers are stable or the preset number of iterations is reached;

[0161] (4) Through cluster analysis, students are grouped according to their learning progress, different learning levels are generated, and personalized task allocation plans are formulated for students with different progress;

[0162] S65, generation of personalized task assignment plan: Based on the K-Means clustering results, personalized task assignment plans are formulated for different groups of students. For students with faster learning progress, more challenging tasks are assigned; for students with slower progress, basic or consolidation tasks are assigned to meet the needs of different learning levels and improve the task completion rate and students' learning enthusiasm;

[0163] Through the storage of historical data, long-term trend analysis, task scheduling strategy optimization and K-Means cluster analysis, we can achieve in-depth analysis of student performance data and formulate personalized task allocation plans for students with different learning progress, thereby improving the accuracy and adaptability of task allocation and supporting students' personalized learning paths.

[0164] S7 includes:

[0165] S71, collection and arrangement of task risk data: based on the data collected in the real-time monitoring of step S3, a risk assessment is performed on the student's task execution status. The collected task risk data includes participation, task completion progress and response time;

[0166] The task risk data is sorted in time series as the input of the support vector machine classification model to analyze whether there is risk in the students' current task execution;

[0167] S72, Support vector machine classification model construction: Build and train a support vector machine classification model to identify the risks of low engagement and task delays. The model construction process is as follows:

[0168] (1) Feature selection: participation, task completion progress, and response time in task risk data are used as the main features of the classification model;

[0169] (2) Training process: Using historical task execution data as a training set, the support vector machine classification model is trained through supervised learning to establish the classification boundary between normal task execution and high-risk task execution status;

[0170] (3) Model expression: The support vector machine classification model realizes the classification boundary through the following optimization problem:

[0171] ;

[0172] Subject to , ;

[0173] in, is the weight vector, is the bias, is the slack variable, is the regularization parameter, represents the students’ task execution characteristics, is the label value (indicating whether there is a task risk);

[0174] S73, multi-level warning triggering: During the task execution process, the support vector machine classification model monitors the student's task risk data in real time. When the classification results show that the student's task execution is at risk (such as low participation or task delay), the multi-level warning mechanism is triggered. The multi-level warning mechanism includes:

[0175] Level 1 warning: When there is a slight deviation from the set standard, the system will send a reminder to the instructor to pay attention to the change in student performance;

[0176] Level 2 warning: If the student deviates significantly from the standard, the system will issue a strong reminder to the teacher, suggesting that the teacher pay attention to the student's learning status and prepare for intervention;

[0177] Level 3 warning: In case of serious deviation from the standard, the system automatically sends an emergency alert and recommends that the instructor take immediate action to intervene;

[0178] S74, Generation of intervention suggestions: Based on the classification results of the support vector machine classification model, generate targeted intervention suggestions for the instructor, including the following:

[0179] Supplementary practice: When students show low engagement or delayed task progress, the system recommends adding corresponding practice tasks to help students consolidate their knowledge;

[0180] One-to-one tutoring: When students have persistent low participation, the system recommends that teachers provide one-to-one tutoring to solve students’ learning difficulties in a timely manner;

[0181] Task difficulty adjustment: If the system determines that the task difficulty may be the reason for the low student engagement, it is recommended to reduce the task difficulty to improve student engagement and task completion;

[0182] S75, Teacher feedback and intervention optimization: After the teacher implements the intervention measures, the task execution status data of the students is continuously monitored, and the feedback results are used to optimize the support vector machine classification model. If some intervention measures have a positive impact on the students' learning effect, the intervention method is recorded as a successful case for reference in similar situations in the future. If some intervention effects are not obvious, the intervention suggestions are adjusted to provide feedback support for model learning;

[0183] The support vector machine classification model is used to identify the risks of students' task execution status, trigger multi-level warnings and generate intervention suggestions based on the classification results, so that teachers can take targeted measures in time when students have low participation or task delays, effectively improving the success rate of task execution and students' learning outcomes.

[0184] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0185] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for scheduling and monitoring tasks on a teacher console based on data analysis, characterized in that: The following steps are involved: S1, Data Collection: Collect real-time and historical data related to tasks and student participation, including task assignment information and student participation indicators. Student participation indicators include attention span, participation rate and task completion speed. The data is transmitted to the central data warehouse in real time through an integrated sensor network and feedback system. S2, dynamic task scheduling: Based on the real-time data and historical data collected by S1, the adaptive enhancement algorithm is used to dynamically assign tasks. The adaptive enhancement algorithm analyzes the students' participation and completion speed characteristics, determines the difficulty and duration of the task, and makes adjustments based on real-time data during the assignment process; S3, real-time monitoring: real-time monitoring of students' task execution, including task completion progress, participation and response time. The monitoring threshold is set through the mean-variance model. When the real-time data deviates from the set threshold range, an abnormal warning is triggered and a prompt is sent to the instructor so that the instructor can adjust the task or intervene in time. S4, Predictive Analysis: Use the long short-term memory network model to perform deep learning analysis on the historical data and real-time data in S1 to predict future task scheduling needs. The long short-term memory network model generates prediction results about task completion trends and participation changes by extracting long-term and short-term features from the data, providing suggestions for future task allocation and supporting instructors to adjust tasks in advance. S5, feedback-based adjustment: Based on the students’ current task execution status data from S3 real-time monitoring feedback, the random forest model is used to dynamically adjust the task parameters; S6, Historical Data Storage and Analysis: Store students’ task execution status data and participation records, support long-term trend analysis and task scheduling strategy optimization, use K-Means clustering algorithm to classify students’ historical task execution status data, group and analyze students’ task execution status data by participation and task completion, and develop personalized task allocation plans for students at different progress levels; S7, Early Warning and Intervention: Based on the support vector machine classification model, multi-level early warnings are issued to instructors when low participation and task delays are detected. The support vector machine classification model identifies task risks and generates intervention suggestions for instructors.

2. The teacher console task scheduling and monitoring method based on data analysis according to claim 1 is characterized in that: The S1 includes: S11, collection of task assignment information: through the integrated sensor network and the teacher console, the task information assigned to students in the current system is collected in real time. The task information includes the type of task, task requirements, assignment time and task deadline. The collected task information is marked in the form of a timestamp and automatically updated to the central data warehouse; S12, collection of student engagement indicators: real-time monitoring of student engagement and collection of student engagement indicators through integrated sensors, including attention span, engagement rate, and task completion speed; S13, data transmission and real-time update: the collected task information and student participation indicators are transmitted to the central data warehouse through the integrated sensor network; S14, historical data storage: classify and store historical data, including classification by time series, task type and student participation.

3. The method for task scheduling and monitoring of a teacher console based on data analysis according to claim 2 is characterized in that: The S2 includes: S21, task feature extraction: extract the student participation and completion speed features based on the collected real-time data and historical data; S22, Adaptive enhancement algorithm construction: Use the adaptive enhancement algorithm as the scheduling algorithm to dynamically allocate tasks according to the features extracted in S21; S23, determination of task difficulty and duration: dynamically setting task difficulty and task duration for students based on the task allocation results calculated by the adaptive enhancement algorithm; S24, real-time dynamic adjustment: During the task assignment process, continuously monitor students' real-time data, including attention span, participation rate and task completion speed, and dynamically adjust task parameters according to changes in real-time data.

4. The method for task scheduling and monitoring of a teacher console based on data analysis according to claim 3 is characterized in that: The S3 includes: S31, task execution status monitoring: real-time collection of student status data during task execution, including task completion progress, participation and response time; Status data is collected in real time during task execution and transmitted to the central data warehouse; S32, mean-variance model construction: construct a mean-variance model based on student historical data to set the monitoring threshold range. The mean-variance model is used to evaluate the normal range of students' task completion progress, participation and response time; S33, abnormal warning triggering: During the task execution process, the student's task completion progress, participation and response time are monitored in real time. When a certain indicator deviates from the threshold range set by the indicator, an abnormal warning is automatically triggered and a prompt message is sent to the instructor; S34, real-time feedback and task adjustment suggestions: abnormal warnings are fed back to the instructor console, and task adjustment suggestions are made based on the students' real-time data deviations. Adjustment suggestions include reducing task difficulty, increasing task completion time, or arranging one-on-one guidance.

5. The method for task scheduling and monitoring of a teacher console based on data analysis according to claim 4 is characterized in that: The S4 includes: S41, data preprocessing: preprocessing the historical data and real-time data collected in step S1, the preprocessing includes normalization, missing value filling and time series reconstruction; S42, Construction of long short-term memory network model: Establish a long short-term memory network model, perform deep learning analysis on preprocessed historical data and real-time data, and extract long-term and short-term features from historical data.

6. The method for task scheduling and monitoring of a teacher console based on data analysis according to claim 5, characterized in that: The S4 further comprises: S43, trend prediction output: through the constructed long short-term memory network model, the prediction results of task completion trend and student participation change in the future period are generated; S44, Task Allocation Suggestion: Generate future task allocation suggestions based on the prediction results of task completion trends and participation changes generated by the long short-term memory network model; S45, early implementation of task adjustment and intervention: The generated suggestions are fed back to the instructor console in real time to support instructors in making task adjustments and personalized interventions in advance.

7. The method for task scheduling and monitoring of a teacher console based on data analysis according to claim 6, characterized in that: The S5 includes: S51, collection and collation of students' current task execution status data: based on the real-time monitoring feedback in S3, collect students' current task execution status data, including participation, task completion progress and response time; S52, Random Forest Model Construction: Use the random forest model to analyze students’ current task execution status data and dynamically adjust the difficulty and duration of the task; S53, determination of optimal task parameters: through the output of the random forest model, determine the optimal task difficulty and task duration configuration to adapt to the student's current performance status; S54, real-time application and feedback of task parameters: Apply the optimal task difficulty and task duration configuration determined by the random forest model to students’ task allocation, and continuously monitor the task execution effect.

8. The method for task scheduling and monitoring of a teacher console based on data analysis according to claim 7, characterized in that: The S6 includes: S61, storage of student task execution status data: storing the task execution status data collected from student task execution in time series; S62, long-term trend analysis: long-term analysis of students’ performance trends based on their historical task execution status data; S63, task scheduling strategy optimization: automatically adjust the task scheduling strategy based on the results of long-term trend analysis; S64, K-Means cluster analysis: Use the K-Means clustering algorithm to classify students' historical task execution status data, and group students according to their participation and task completion status; S65, personalized task assignment plan generation: Based on the K-Means clustering results, personalized task assignment plans are formulated for different groups of students.

9. The method for task scheduling and monitoring of a teacher console based on data analysis according to claim 8, characterized in that: The S7 includes: S71, collection and arrangement of task risk data: based on the data collected in the real-time monitoring of step S3, a risk assessment is performed on the student's task execution status. The collected task risk data includes participation, task completion progress and response time; S72, Support vector machine classification model construction: Build and train a support vector machine classification model to identify mission risks; S73, multi-level warning triggering: During the task execution process, the support vector machine classification model monitors the student's task risk data in real time. When the classification result shows that the student's task execution is at risk, the multi-level warning mechanism is triggered; S74, Generation of intervention suggestions: Generate targeted intervention suggestions for teachers based on the classification results of the support vector machine classification model; S75, Instructor feedback and intervention optimization: After the instructor implements the intervention measures, the students' task execution status data is continuously monitored, and the feedback results are used to optimize the support vector machine classification model.

Images