Teaching platform lecturer working system

Abstract

The invention relates to the technical field of education live broadcast management, in particular to a teaching platform lecturer working system, which comprises a time resource distribution modeling module for collecting a working calendar of a lecturer and a curriculum schedule of a student, evaluating time use conditions of the lecturer and the student in each time period and generating resource occupation information of the current time period. According to the method, optimization of time resource allocation is realized from use statistics of time periods to load evaluation of resource occupation, meanwhile, course conflict probability is dynamically analyzed, conflict points are accurately positioned, course timetables are dynamically adjusted and optimized in combination with course importance weights and available time of trainees, the conflict probability is effectively reduced, and the course resource allocation efficiency is improved. And the coordination and efficiency of teaching activities are improved. By re-planning the course sequence and optimizing the time distribution, the teaching plan is more scientific and reasonable, so that the flexibility and effectiveness of the overall course arrangement are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of educational live broadcast management, and particularly to a lecturer work system for a teaching platform. Background Art

[0002] In the technical field of educational live broadcast management, digitalization of educational resources, online dissemination of course content, and intelligent management of the teaching process are achieved through technical means. Typical applications include the development of live course platforms, user permission and data security management, real-time monitoring of teaching interactions, collection and analysis of learning process data, etc., to improve the efficiency and effectiveness of online education.

[0003] Among them, the lecturer work system for the teaching platform is used to support the work process and teaching activities of lecturers on the teaching platform. Through this system, lecturers can conveniently manage course resources, arrange live broadcast time, interact with students, track teaching progress, and improve teaching strategies through the analysis function. This system aims to provide comprehensive technical support for lecturers and optimize the teaching process.

[0004] In the prior art, when supporting the teaching process of lecturers, only basic course resource management and teaching interaction support are provided, making it difficult to effectively coordinate the time arrangements of lecturers and students, and easily leading to conflicts in teaching activities. In terms of course time arrangement, existing systems usually cannot dynamically evaluate the probability and importance of course conflicts, and it is difficult to discover and adjust course conflicts in a timely manner, which may lead to a decline in the efficiency of teaching activities. In the monitoring of teaching progress, only the surface deviation between the plan and the actual situation is concerned, and the reasons and trends of the deviation are not deeply analyzed, resulting in inaccurate adjustment measures. The analysis of students' behaviors is relatively rough, and it is impossible to construct behavior patterns and abnormal analysis, so it is difficult to achieve dynamic adjustment of targeted permissions, which may have an adverse impact on teaching safety and efficiency. These deficiencies limit the adaptability of existing systems in complex teaching scenarios, easily lead to uneven distribution of teaching resources, frequent course conflicts, and the inability to continuously optimize teaching effects, affecting the overall teaching quality and user experience. Summary of the Invention

[0005] To solve the technical problems existing in the prior art, an embodiment of the present invention provides a lecturer work system for a teaching platform. The technical solution is as follows: A lecturer work system for a teaching platform, the system includes: The time resource distribution modeling module collects the work calendars of lecturers and the course schedules of students, evaluates the time usage of lecturers and students in each time period, and generates resource occupancy information for the current time period; The conflict probability analysis module analyzes the time overlap situation between courses according to the resource occupancy information of the current time period, identifies time conflict points, dynamically updates conflict data according to the importance of the courses and the availability of students, and generates a conflict possibility analysis result; The course time optimization module identifies the course arrangements with conflict risks in the future in the instructor's work calendar and the students' course schedules according to the conflict possibility analysis result, adjusts the time allocation of the corresponding conflicting courses, and generates an optimized course schedule; The teaching progress monitoring module compares the optimized course schedule with the instructor's current teaching progress, monitors the start and end times of each class, analyzes the progress or lag of the teaching progress, and generates a teaching progress monitoring result; The student behavior insight module analyzes the student participation in the teaching progress monitoring result, analyzes the behavior patterns of students, marks the normality and abnormality of the behavior patterns, and generates a student behavior analysis result; The dynamic permission adjustment module uses the student participation data and real-time monitoring data in the student behavior analysis result to adjust the access permissions according to the role of each user and the current activity scenario, and generates a dynamic configuration result of the instructor's permissions.

[0006] The improvement of the present invention is that the resource occupancy information of the current period includes the instructor's time availability, the student time overlap ratio, and the course load degree of the current period, the conflict possibility analysis result includes the course information of the conflict time period, the course time overlap ratio, and the course priority adjustment order, the optimized course schedule includes the adjusted course start and end times, the rearrangement order of the conflicting courses, and the number of courses that students can participate in, the teaching progress monitoring result includes the deviation between the planned time and the current time of each course, the completion of teaching tasks, and the distribution status of teaching time, the student behavior analysis result includes the student groups with multiple interactions, the behavior characteristics of participating students, and the description of abnormal behaviors, and the dynamic configuration result of the instructor's permissions includes the access permission groups adjusted in real time, the permission usage records, and the current permission scope.

[0007] The improvement of the present invention is that the time resource distribution modeling module includes: The calendar processing and integration sub-module collects the instructor's work calendar and the students' course schedules, analyzes the time arrangements of each instructor and student, extracts the start time and duration information of the daily courses, divides the time data of the instructor and students according to a unified time period, and generates course distribution data; The time period usage analysis sub-module, based on the course distribution data, counts the number of course arrangements in each time period, analyzes the time distribution of the instructor and students in each time period and marks the usage frequency, and generates course statistics data; The resource occupancy information generation sub-module, based on the course statistics data, analyzes the distribution of resources in each time period, evaluates the usage load of resources in each time period, and generates the resource occupancy information of the current period.

[0008] The improvement of the present invention is that the conflict probability analysis module includes: The conflict probability analysis sub-module compares the courses in each time period based on the resource occupancy information in the current period, evaluates the degree of time overlap between courses, calculates the course conflict probability that occurs in each time period, and generates a course conflict analysis result; The course conflict location sub-module locates the key points of time overlap in the course arrangement based on the course conflict analysis result, records the conflicting course topics, lecturers, and students' schedules, and generates course conflict point information; The conflict dynamic update sub-module dynamically adjusts the conflict data and updates the conflict sorting based on the course conflict point information, combined with the importance of the course content and the available time of the students, and generates a conflict possibility analysis result.

[0009] The improvement of the present invention is that for calculating the course conflict probability that occurs in each time period, the formula is adopted: ; Obtain the course conflict probability ; Wherein, represents the course conflict probability, represents the number of overlapping courses in the same time period, represents the total number of courses, represents the importance weight of the conflicting courses, represents the available time of the participating students, is a tuning parameter.

[0010] The improvement of the present invention is that the course time optimization module includes: The conflicting course identification sub-module screens the course arrangements with conflict risks in the lecturer's work calendar and the students' course schedules based on the conflict possibility analysis result, combines the current time distribution of the current course and its conflict points, and generates conflicting course arrangement information; The course sorting adjustment sub-module analyzes the dependency relationship and time constraints between courses based on the conflicting course arrangement information, adjusts the priority order of the courses according to the conflict situation, and generates a course sorting adjustment plan; The schedule optimization generation sub-module rearranges the courses involved in the conflict based on the course sorting adjustment plan, adjusts the distribution of the courses in the time period, and generates an optimized course schedule.

[0011] The improvement of the present invention is that the teaching progress monitoring module includes: The teaching time comparison sub-module compares the current teaching progress of the lecturer based on the optimized course schedule, monitors the start and end times of each course, records any behavior that deviates from the planned time, and generates teaching time deviation information; Based on the teaching time deviation information, the teaching deviation analysis sub-module analyzes the situation of the deviation time, including the reasons, frequencies, and influence scopes of course delays or advances, marks the change trend of the teaching progress, and generates the teaching deviation analysis result; Based on the teaching deviation analysis result, the teaching progress evaluation sub-module evaluates the overall teaching progress, records the advancement or lag of teaching activities, and conducts quantitative processing and grading statistics on the deviation, generating the teaching progress monitoring result.

[0012] The improvement of the present invention is that the student behavior insight module includes: Based on the teaching progress monitoring result, the interaction data collection sub-module collects the interaction data of students, including the number of logins, course viewing time, and discussion participation, sorts and converts it into a multi-dimensional behavior feature vector, and generates the student behavior feature vector; Based on the student behavior feature vector, the behavior pattern analysis sub-module conducts cluster analysis on the student behavior, identifies the behavior feature patterns of students, extracts the distribution of common behavior patterns and other behavior patterns, and generates the student behavior pattern analysis result; Based on the student behavior pattern analysis result, the behavior pattern marking sub-module classifies and marks normal behaviors and abnormal behaviors, determines the behavior characteristics of students, and generates the student behavior analysis result.

[0013] The improvement of the present invention is that the dynamic permission adjustment module includes: Based on the student behavior analysis result, the operation requirement analysis sub-module combines the real-time participation of students and the activity scenarios in the instructor's live broadcast room, analyzes the changes in the operation requirements of each user, identifies the user's permission requirements, and generates the user operation requirement analysis result; Based on the user operation requirement analysis result, the permission adjustment decision sub-module combines the current activity status and permission scope of each user to dynamically adjust the access permission and generates the user permission adjustment plan; Based on the user permission adjustment plan, the permission allocation verification sub-module conducts real-time allocation and verification of the dynamically adjusted permissions, monitors the usage of permissions, and generates the instructor permission dynamic configuration result.

[0014] The improvement of the present invention is that for dynamically adjusting the access permission by combining the current activity status and permission scope of each user, the formula is used: ; Calculate the permission adjustment priority score ; Among them, represents the requirement intensity of the th operation, represents the activity weight of the th operation, Represents the total number of operation requirements.

[0015] The beneficial effects brought by the technical solutions provided by the embodiments of the present invention at least include: Through the use statistics of time periods to the load assessment of resource occupancy, the optimization of time resource allocation is realized. At the same time, the probability of course conflicts is dynamically analyzed and the conflict points are accurately located. Combining the importance weights of courses and the available time of students, the course schedule is dynamically adjusted and optimized, effectively reducing the probability of conflicts and improving the coordination and efficiency of teaching activities. By re-planning the course order and optimizing the time allocation, the teaching plan becomes more reasonable, thereby enhancing the flexibility and effectiveness of the overall course arrangement. In the teaching progress monitoring, through deviation quantification analysis and hierarchical statistics, behaviors deviating from the plan can be identified and adjusted in real time, strengthening the controllability of the teaching process. The student behavior insight function, through the construction of behavior feature vectors and pattern analysis, identifies abnormal behaviors and dynamically optimizes the permission allocation, improving the efficiency and security of teacher-student interaction. Based on the real-time activity status and operation requirements of students, the permissions are dynamically adjusted to further achieve personalized support and ensure the efficient operation of the teaching platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is the system module diagram of the present invention; Figure 2 It is the system framework diagram of the present invention; Figure 3 It is the schematic diagram of the time resource distribution modeling module of the present invention; Figure 4 It is the schematic diagram of the conflict probability analysis module of the present invention; Figure 5 It is the schematic diagram of the course time optimization module of the present invention; Figure 6 It is the schematic diagram of the teaching progress monitoring module of the present invention; Figure 7 It is the schematic diagram of the student behavior insight module of the present invention; Figure 8 It is the schematic diagram of the dynamic permission adjustment module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] The following describes the technical solutions in the present invention with reference to the drawings.

[0019] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to give examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or more advantageous than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0020] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0021] In the embodiments of the present invention, sometimes subscripts such as W 1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0022] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0023] Please refer to Figure 1 , the embodiments of the present invention provide a teaching platform lecturer work system, the system includes: The time resource distribution modeling module collects the work calendars of lecturers and the course schedules of students, evaluates the time usage of lecturers and students in each time period, and generates resource occupancy information for the current time period; The conflict probability analysis module analyzes the time overlap situation between courses according to the resource occupancy information of the current time period, identifies time conflict points, dynamically updates the conflict data according to the importance of the courses and the availability of the students, and generates a conflict probability analysis result; The course time optimization module identifies the course arrangements in the work calendars of lecturers and the course schedules of students that have conflict risks in the future according to the conflict probability analysis result, adjusts the time allocation of the corresponding conflict courses, and generates an optimized course schedule; The teaching progress monitoring module compares the optimized course schedule with the current teaching progress of the lecturer, monitors the start and end times of each class, analyzes the progress or lag of the teaching progress, and generates a teaching progress monitoring result; The student behavior insight module analyzes the student participation in the teaching progress monitoring result, analyzes the behavior patterns of the students, marks the normality and abnormality of the behavior patterns, and generates a student behavior analysis result; The dynamic permission adjustment module utilizes the trainee participation data and real-time monitoring data in the trainee behavior analysis results, adjusts the access permissions according to the role of each user and the current activity scenario, and generates the dynamic configuration result of the instructor permissions.

[0024] The resource occupancy information for the current period includes the instructor's time availability, the trainee time overlap ratio, and the course load level for the current period. The conflict possibility analysis results include the course information for the conflict time period, the course time overlap ratio, and the course priority adjustment order. The optimized course schedule includes the adjusted course start and end times, the rearrangement order of the conflict courses, and the number of courses that trainees can participate in. The teaching progress monitoring results include the deviation between the planned time and the current time for each course, the completion status of teaching tasks, and the allocation status of teaching time. The trainee behavior analysis results include the groups of trainees with multiple interactions, the behavioral characteristics of the participating trainees, and the description of abnormal behaviors. The dynamic configuration result of the instructor permissions includes the access permission groups adjusted in real time, the permission usage records, and the current permission scope.

[0025] Please refer to Figure 2 and Figure 3 , the time resource distribution modeling module includes: The calendar processing and integration sub-module collects the work calendars of instructors and the course schedules of trainees, analyzes the time arrangements of each instructor and trainee, extracts the start time and duration information of daily courses, divides the time data of instructors and trainees according to a unified time period, and generates course distribution data; Collect the work calendars of instructors and the course schedules of trainees, extract the start time, end time, and course arrangements for each day, divide the whole day into 48 30-minute time periods through the time parsing method, match the time arrangements of each course to the corresponding time periods, identify the overlapping time and independent time through the time comparison method, and record the course duration at the same time. If the number of courses in a single time period exceeds 5, it is marked as a high-density time period. If it is less than 2, it is marked as a low-density time period. Record the course distribution of the time period in the time period mapping table to generate course distribution data.

[0026] The time period usage analysis sub-module, based on the course distribution data, counts the number of course arrangements in each time period, analyzes the time distribution of instructors and trainees in each time period and marks the usage frequency, and generates course statistics data; The frequency distribution analysis method is used to evaluate the time utilization rate of lecturers and trainees. The time periods with the course arrangement quantity greater than the average number of courses in the whole-day time period are marked as high-frequency time periods (for example, the course arrangements from 08:00 to 10:00 usually reach 6 to 8 courses), and the time periods with the course arrangement quantity less than the average number of courses in the whole-day time period are marked as low-frequency time periods (for example, the course arrangements from 12:00 to 14:00 are generally 1 to 2 courses). A frequency distribution graph is generated according to the course quantity distribution of time periods, and the activities of lecturers and trainees in different time periods are recorded to generate course statistical data.

[0027] Based on the course statistical data, the resource occupancy information generation sub-module analyzes the distribution of resources in each time period, evaluates the usage load of resources in each time period, and generates the resource occupancy information of the current time period; The clustering analysis algorithm (such as the K-means clustering algorithm) is used to perform clustering calculations on the number of participants of lecturers and trainees in a time period. The number of participants data in the time period is used as the clustering eigenvalue and is divided into three levels: high, medium, and low. The high level means that the number of participants accounts for more than 75% of the total number of people in the whole day (for example, in the time period from 08:00 to 10:00, usually due to the concentration of courses, the number of participants is more than 80% of the total number of people), the medium level is that the number of participants accounts for 30% to 75% of the total number of people in the whole day (for example, in the time period from 16:00 to 18:00, the course arrangements are relatively uniform, and the number of people is about 40% of the total number of people in the whole day), and the low level is that the number of participants accounts for less than 30% of the total number of people in the whole day (for example, in the time period from 22:00 to 24:00, there are very few courses, and the number of people is only less than 20% of the total number of people), and the resource occupancy information of the current time period is generated.

[0028] Please refer to Figure 2 and Figure 4 , the conflict probability analysis module includes: Based on the resource occupancy information of the current time period, the conflict probability analysis sub-module compares the courses in each time period, evaluates the time overlap degree between courses, calculates the course conflict probability that appears in each time period, and generates the course conflict analysis result; By analyzing the course arrangement and the number of participants data in each time period, the situation where resources are jointly occupied by multiple courses is identified. Next, the courses in each time period are compared in detail. In this process, the system will check the specific time arrangements of each course, identify the overlaps in specific times, that is, the same time period is occupied by two or more courses, and then evaluate the intersection degree between these time-overlapping courses, which includes the similarity of course content, the overlap of the participating lecturer and trainee groups, so as to evaluate the possibility and influence of conflicts. For calculating the course conflict probability that appears in each time period, the formula is used: ; Obtain the course conflict probability ; Among them, represents the course conflict probability, represents the number of overlapping courses within the same time period, obtained by checking the time in the course schedule, represents the total number of courses, represents the importance weight of the conflict courses, set according to the course content and students' needs. The higher the course importance, the greater the weight. For example, if a course is prepared for students who are about to participate in an international competition, its importance may be set to 0.9; while a regular course may be set to 0.3. represents the available time of the participating students, is a tuning parameter used to adjust the influence of importance and availability on the conflict probability, set according to the results of previous conflict resolution efficiency and teaching satisfaction surveys. For example, if the data shows that increasing the weights of importance and availability on the conflict probability can significantly improve the post-resolution satisfaction, then increase the value.

[0029] For example, in the time period from 08:00 to 09:00, there are 3 courses arranged simultaneously, the total number of courses is 5, and two of the courses are marked as high importance ( ), all students can participate in the courses during this time period ( ), and the tuning parameter is set. According to the formula calculation: is or 79%.

[0030] The course conflict location sub-module, based on the course conflict analysis results, locates the key points of time overlap in the course arrangement, records the conflict course topics, instructors, and students' schedules, and generates course conflict point information; The previous calculation result shows that the course conflict probability in some time periods is as high as 79%. Therefore, further locate these time periods with high conflict probability and analyze the arrangements of each course in these time periods in detail, especially paying attention to those courses that involve multiple instructors and multiple student groups at the same time. By automatically tracking the specific time points of these courses by the system, identify the key points of time overlap. For example, if the same instructor is arranged for two different courses in the same time period, or the same student group needs to participate in two different courses at the same time, at this time, the system will record the details of the conflict course topics, relevant instructors, and students' schedules, so as to generate course conflict point information, including the names of the courses, the participating instructors and students, and the specific time conflict points, and generate course conflict point information.

[0031] The conflict dynamic update sub-module, based on the course conflict point information, combines the importance of the course content and the available time of the students, dynamically adjusts the conflict data and updates the conflict ranking, and generates the conflict possibility analysis result; Considering the overall requirements of the teaching plan and the individual learning needs of the trainees, analyze the importance of the course content involved in each conflict point and the time availability of the participating trainees. The system utilizes these analysis results to determine the priority of each conflicting course. By rescheduling the course time, minimize time conflicts as much as possible. Or, in the case of inevitable conflicts, prioritize the courses with higher importance or those with more limited trainee time. During this process, the system continuously updates the conflict data to ensure the real-time and accuracy of all data. After dynamic adjustment, the system generates the latest conflict probability analysis result. This result shows that compared with the original conflict situation, the conflict probability of the adjusted class schedule is significantly reduced, improving the utilization efficiency of teaching resources.

[0032] Please refer to Figure 2 and Figure 5 , the course time optimization module includes: The conflicting course identification sub-module, based on the conflict probability analysis result, screens the course arrangements with conflict risks in the instructor's work calendar and the trainee's class schedule, and combines the current time distribution of the courses and their conflict points to generate conflicting course arrangement information; Using database cross-query technology, screen out the course arrangements during these time periods, carefully review the instructor's and trainee's class schedules, and identify direct time overlaps, such as the same instructor being scheduled for two overlapping courses, or the same group of students being required to attend two concurrent courses. This analysis process involves comparing the time data in the class schedule and using SQL query statements to extract relevant course information from the education platform, such as course names, participating instructors and trainees, and specific course times, to generate conflicting course arrangement information.

[0033] The course sorting and adjustment sub-module, based on the conflicting course arrangement information, analyzes the dependency relationships and time constraints between courses, adjusts the priority order of the courses according to the conflict situation, and generates a course sorting and adjustment plan; Using database cross-query technology, screen out the course arrangements during these time periods, carefully review the instructor's and trainee's class schedules, and identify direct time overlaps, such as the same instructor being scheduled for two overlapping courses, or the same group of students being required to attend two concurrent courses. This analysis process involves comparing the time data in the class schedule and using SQL query statements to extract relevant course information from the education management system, such as course names, participating instructors and trainees, and specific course times, and generates a course sorting and adjustment plan based on this information.

[0034] The class schedule optimization and generation sub-module, based on the course sorting and adjustment plan, rearranges the courses involved in the conflict, adjusts the distribution of the courses in the time period, and generates an optimized class schedule; Optimize the course time allocation using the linear programming algorithm. Linear programming is a mathematical method for optimizing resource allocation, which can find the optimal resource allocation plan under given constraints. The module dynamically adjusts the position of courses in the schedule according to the course priority and relevant time constraints to ensure that each adjustment can reduce conflicts and improve teaching efficiency. The result of each adjustment is evaluated to ensure that the optimized course schedule can significantly reduce time conflicts and improve the utilization efficiency of teaching resources.

[0035] Please refer to Figure 2 and Figure 6 , the teaching progress monitoring module includes: The teaching time comparison sub-module, based on the optimized course schedule, compares the current teaching progress of the lecturer, monitors the start and end times of each course, records any behavior that deviates from the planned time, and generates teaching time deviation information. First, receive the optimized course schedule, which specifies the planned start and end times of each class. The module monitors the actual start and end times of each class precisely by comparing with the times recorded in actual teaching activities, using time comparison analysis techniques. Any behavior that deviates from the plan, such as a course starting early or ending late, will be recorded by the system. These data are processed through time series analysis and finally generate detailed teaching time deviation information, which includes the name of the specific course, the type of deviation (early or late), the length of the deviation time, and its frequency.

[0036] The teaching deviation analysis sub-module, based on the teaching time deviation information, analyzes the deviation time situation, including the reasons, frequencies, and influence ranges of course delays or advances, marks the change trend of the teaching progress, and generates the teaching deviation analysis result. Deeply analyze the specific situation of the deviation time through statistical analysis methods, including the specific reasons for course delays or advances, such as time changes caused by teachers adjusting teaching content or delays caused by increased student interactions. The module evaluates the frequencies of these time deviations and their influence ranges on the teaching progress, uses trend analysis techniques, marks the change trend of the teaching progress, identifies the courses or time periods that may need to be adjusted, and generates the teaching deviation analysis result, which details the types and influences of various deviations.

[0037] The teaching progress evaluation sub-module, based on the teaching deviation analysis result, evaluates the overall teaching progress, records the progress or lag of teaching activities, and conducts quantitative processing and hierarchical statistics on the deviations to generate the teaching progress monitoring result. By recording the progress or lag of teaching activities, the actual progress of each teaching activity is compared with the planned schedule to calculate the deviation value. These deviation values are based on pre-set criteria. For example, a course being advanced or delayed by more than 10 minutes is considered a minor deviation, and more than 30 minutes is a major deviation. Then, the deviations of all courses are classified and statistically analyzed. For example, the deviations are stratified and analyzed according to course type, instructor, student group, etc. to identify the patterns and frequencies of deviation occurrences, and the teaching progress monitoring results are generated.

[0038] Please refer to Figure 2 and Figure 7 , the student behavior insight module includes: The interactive data collection sub-module collects the interactive data of students based on the teaching progress monitoring results, including the number of logins, course viewing time, and discussion participation, organizes and transforms them into multi-dimensional behavior feature vectors, and generates student behavior feature vectors. First, it receives the data from the teaching progress monitoring results, which include the behavior records of students on the teaching platform, such as the number of logins, course viewing time, and discussion participation degree. Through data preprocessing operations, including data cleaning and formatting, the accuracy and consistency of the data are ensured. Next, this sub-module uses the principal component analysis (PCA) technique to extract key features from the original data and transform them into multi-dimensional behavior feature vectors. These feature vectors include but are not limited to students' activity levels, participation degrees, viewing depths, and interaction frequencies. Each dimension is quantified from specific interactive behaviors, generating student behavior feature vectors, which provide the basic data for further behavior pattern analysis.

[0039] The behavior pattern analysis sub-module conducts cluster analysis on students' behaviors based on the student behavior feature vectors, identifies the behavior feature patterns of students, extracts the distribution of common behavior patterns and other behavior patterns, and generates the student behavior pattern analysis results. Through the K-means clustering algorithm, the module groups students according to the similarity of their behavior characteristics and identifies common behavior patterns and variant behavior patterns. Common behavior patterns include high participation patterns (such as logging in more than 3 times a day, course viewing rate exceeding 90%, and frequent participation in discussions), medium participation patterns (such as logging in 3 to 5 times a week, course viewing rate between 50% and 80%, and occasional participation in discussions), and low participation patterns (such as logging in less than 3 times a week, course viewing rate below 30%, and hardly participating in discussions). Variant behavior patterns refer to behaviors that are significantly different from the common patterns, such as extremely high participation patterns (logging in more than 10 times a day, course viewing rate and discussion participation rate both approaching 100%) or intermittent participation patterns (extremely high participation in certain time periods but completely absent in other time periods). The module statistically analyzes the distribution of each pattern and generates the student behavior pattern analysis results.

[0040] Based on the analysis results of the trainee behavior patterns, the behavior pattern marking sub-module classifies and marks normal behaviors and abnormal behaviors, determines the behavior characteristics of the trainees, and generates the trainee behavior analysis results; The decision tree algorithm is adopted to classify and mark normal behavior patterns and abnormal behavior patterns. Normal behavior patterns include the aforementioned high participation, medium participation, and low participation patterns, which account for the main proportion in the trainee group and are regular. Abnormal behavior patterns include the extremely high participation pattern (for example, showing an overlearning tendency, which may require teacher guidance to adjust the learning rhythm) and the intermittent participation pattern (for example, due to work or personal reasons, the learning discontinuity is obvious, and additional course flexibility arrangements are needed). The module assigns clear labels to each behavior pattern and further marks the influence scope of abnormal behaviors. For example, low participation may have a negative impact on the passing rate of exams, while intermittent participation may pose a risk to the course completion rate, generating the trainee behavior analysis results.

[0041] Please refer to Figure 2 and Figure 8 , the dynamic permission adjustment module includes: Based on the trainee behavior analysis results, the operation requirement analysis sub-module analyzes the changes in the operation requirements of each user by combining the real-time participation of the trainees and the activity scenarios in the instructor's live broadcast room, identifies the user's requirements for permissions, and generates the user operation requirement analysis results; Receiving the real-time participation data of the trainees, including the course viewing time, interaction frequency, and permission request situation, the module uses data mining techniques to analyze the trainees' permission requirements. By dynamically comparing the real-time data, it matches the behavior characteristics of the trainees with the activity scenarios in the live broadcast room. For example, in the screen sharing or discussion session, it identifies the trainees' requirements for additional permissions, such as file download permissions or permission upgrade requirements. The analysis process extracts key requirements through association rule mining, combining the behavior characteristic frequency, scenario type, and trainee operation history records, and finally generates the user operation requirement analysis results, which include the priority requirements and classification of requirement types for each user.

[0042] Based on the user operation requirement analysis results, the permission adjustment decision sub-module dynamically adjusts the access permissions by combining the current activity status and permission scope of each user, and generates the user permission adjustment plan; For dynamically adjusting the access permissions by combining the current activity status and permission scope of each user, the formula is adopted: ; Calculate the permission adjustment priority score ; Among them, represents the The demand intensity of an operation reflects the intensity of the user's current operation permission requirements. This value is obtained by counting the frequency and type of the user's specific operations in the current scenario. For example, it is obtained by recording behavioral data such as the number of user question submissions and file requests. Indicates the activity weight of the operation, which reflects the relative importance of the operation to the current scenario or task. It is obtained by analyzing the specific background of the operation and the course priorities of the trainees. For example, the course priority level can be set by the teaching plan (such as courses related to exams having a higher weight), and the participation frequency is extracted from real-time participation data. Indicates the total number of operation requirements, representing all the permission requests made by the user in the current scenario.

[0043] For example, in a live broadcast scenario, the user's permission requirements include asking questions, requesting file sharing, and participating in discussions. If the user submits 5 questions, with a demand intensity of 1 for each question, the total demand intensity , the user requests file sharing 2 times, with a demand intensity of 2 each time, the total demand intensity , the user participates in the discussion 1 time, with a demand intensity of 3, the total demand intensity , and the activity weights are respectively: , reflecting the importance of the question, , reflecting the importance of file sharing, , reflecting the importance of participating in the discussion, and the total demand number .

[0044] Calculate the priority score: ; Assume that the general priority is 2.5. Comparing with the general priority of 2.5, the result shows that this priority score indicates that the user's permission requirements have a relatively high level of urgency in the current scenario.

[0045] The permission allocation verification sub-module, based on the user permission adjustment plan, performs real-time allocation and verification of the dynamically adjusted permissions, monitors the usage of permissions, and generates the dynamic configuration result of the instructor permissions.

[0046] Apply the dynamically generated permission plan to user accounts in real time and perform specific permission allocation operations, such as allocating discussion permissions or questionnaire permissions within a specific time period. The module also monitors the permission usage situation through event logs, including recording the time, frequency, and validity of user permission calls, verifying whether the actual usage of permissions is consistent with the allocation plan. In addition, the module performs integrity verification on the operation behaviors of user permissions to ensure that the operations within the permission scope do not exceed the specified range, and generates the dynamic configuration result of instructor permissions through the analysis of permission call efficiency. The result includes permission allocation efficiency, abnormal permission call records, and verification status, providing detailed feedback data for optimizing permission policies.

[0047] It should be understood that the term "and / or" in this article is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0048] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (s) or plural item (s). For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0049] It should be understood that in various embodiments of the present invention, the magnitudes of the serial numbers of the above - mentioned processes do not mean the sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0050] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0051] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above - described devices, apparatuses, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0052] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0053] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0054] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0055] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0056] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A teaching platform lecturer work system, characterized by: The system comprises: The time resource distribution modeling module collects the lecturer's work calendar and the student's course schedule, evaluates the time usage of the lecturer and the student in each time period, and generates resource occupancy information for the current period; The conflict probability analysis module analyzes the time overlap between courses based on the resource occupancy information of the current period, identifies time conflict points, dynamically updates conflict data based on the importance of the courses and the availability of the students, and generates conflict possibility analysis results; The course time optimization module identifies the course schedules with future conflict risks in the lecturer's work calendar and the student's course schedule according to the conflict possibility analysis results, adjusts the time allocation of the corresponding conflicting courses, and generates an optimized course schedule; The teaching progress monitoring module compares the optimized course schedule with the current teaching progress of the lecturer, monitors the start and end time of each class, analyzes the progress or lag of the teaching progress, and generates teaching progress monitoring results; The student behavior insight module analyzes the student participation in the teaching progress monitoring results, analyzes the student behavior patterns, marks the normality and abnormality of the behavior patterns, and generates student behavior analysis results; The dynamic permission adjustment module uses the student participation data and real-time monitoring data in the student behavior analysis results to adjust the access rights according to the role of each user and the current activity scenario, and generates a dynamic configuration result of the instructor's permissions.

2. The teaching platform lecturer work system according to claim 1 is characterized by: The resource occupancy information of the current time period includes the instructor's time availability, the student time overlap ratio and the course load level of the current time period; the conflict possibility analysis result includes the course information of the conflicting time period, the course time overlap ratio and the course priority adjustment order; the optimized course schedule includes the adjusted course start and end times, the re-arranged order of conflicting courses and the number of courses that students can participate in; the teaching progress monitoring result includes the deviation between the planned time and the current time of each course, the completion status of the teaching tasks and the allocation status of the teaching time; the student behavior analysis result includes the student groups with multiple interactions, the behavioral characteristics of the participating students and the description of abnormal behavior; the instructor authority dynamic configuration result includes the real-time adjusted access permission grouping, permission usage records and the current permission scope.

3. The teaching platform lecturer work system according to claim 1 is characterized by: The time resource distribution modeling module includes: The calendar processing and integration submodule collects lecturers’ work calendars and students’ course schedules, analyzes the schedules of each lecturer and student, extracts the start time and duration information of daily courses, divides lecturers’ and students’ time data into unified time periods, and generates course distribution data; The time period usage analysis submodule counts the number of courses arranged in each time period based on the course distribution data, analyzes the time distribution of lecturers and students in each time period, marks the usage frequency, and generates course statistics; The resource occupancy information generating submodule analyzes the distribution of resources in each time period based on the course statistical data, evaluates the usage load of resources in each time period, and generates resource occupancy information for the current time period.

4. The teaching platform lecturer work system according to claim 1 is characterized in that: The conflict probability analysis module includes: The conflict probability analysis submodule compares the courses in each time period based on the resource occupancy information of the current time period, evaluates the time overlap between courses, calculates the probability of course conflict in each time period, and generates course conflict analysis results; The course conflict location submodule locates the key points of time overlap in the course schedule based on the course conflict analysis results, records the conflicting course topics, lecturers and student schedules, and generates course conflict point information; The conflict dynamic update submodule dynamically adjusts the conflict data and updates the conflict ranking based on the course conflict point information, combined with the importance of the course content and the available time of the students, to generate a conflict possibility analysis result.

5. The teaching platform lecturer work system according to claim 4 is characterized in that: To calculate the probability of course conflict in each time period, the formula is used: ； Get the probability of course conflict ; in, represents the probability of course conflict, represents the number of overlapping courses in the same time period, Represents the total number of courses, represents the importance weight of the conflicting courses, Represents the available time of the participating students, is a tuning parameter.

6. The teaching platform lecturer work system according to claim 1 is characterized by: The course time optimization module includes: The conflict course identification submodule screens the course schedules with conflict risks between the lecturer's work calendar and the student's course schedule based on the conflict possibility analysis results, and generates conflict course schedule information based on the time distribution of the current course and its conflict points; The course sequence adjustment submodule analyzes the dependencies and time constraints between courses based on the conflicting course schedule information, adjusts the priority of courses according to the conflicting situations, and generates a course sequence adjustment plan; The timetable optimization generation submodule rearranges the conflicting courses based on the course ranking adjustment plan, adjusts the allocation of courses in time periods, and generates an optimized course timetable.

7. The teaching platform lecturer work system according to claim 1 is characterized by: The teaching progress monitoring module comprises: The teaching time comparison submodule compares the current teaching progress of the lecturer based on the optimized course schedule, monitors the start and end time of each course, records any deviation from the planned time, and generates teaching time deviation information; The teaching deviation analysis submodule analyzes the deviation time based on the teaching time deviation information, including the reasons, frequency and impact range of course delay or advance, marks the change trend of teaching progress, and generates teaching deviation analysis results; The teaching progress evaluation submodule evaluates the overall teaching progress based on the teaching deviation analysis results, records the progress or lag of teaching activities, quantifies and classifies the deviations, and generates teaching progress monitoring results.

8. The teaching platform lecturer work system according to claim 1 is characterized by: The student behavior insight module includes: The interactive data collection submodule collects the interactive data of the students based on the teaching progress monitoring results, including the number of logins, course viewing time and discussion participation, and organizes and converts them into multi-dimensional behavioral feature vectors to generate student behavioral feature vectors; The behavior pattern analysis submodule performs cluster analysis on the student behavior based on the student behavior feature vector, identifies the student's behavior feature pattern, extracts the distribution of common behavior patterns and other behavior patterns, and generates student behavior pattern analysis results; The behavior pattern marking submodule classifies and marks normal behaviors and abnormal behaviors based on the student behavior pattern analysis results, determines the student's behavior characteristics, and generates student behavior analysis results.

9. The teaching platform lecturer work system according to claim 1 is characterized by: The dynamic permission adjustment module includes: The operation demand analysis submodule analyzes the changes in the operation demand of each user based on the student behavior analysis results, combined with the real-time participation of the students and the activity scenes in the lecturer's live broadcast room, identifies the user's demand for permissions, and generates the user operation demand analysis results; The permission adjustment decision submodule dynamically adjusts the access rights based on the user operation demand analysis results and combines the current activity status and permission scope of each user to generate a user permission adjustment plan; The authority allocation and verification submodule allocates and verifies the dynamically adjusted authority in real time based on the user authority adjustment plan, monitors the usage of the authority, and generates a dynamic configuration result of the instructor authority.

10. The teaching platform lecturer work system according to claim 9 is characterized in that: To dynamically adjust access rights based on each user's current activity status and permission scope, use the following formula: ； Calculate the priority score of permission adjustment ; in, Indicates The intensity of the demand for the operation, Indicates The activity weight of the operation, Indicates the total number of operation requests.

Images