College student education evaluation management method and system based on deep learning

Abstract

The invention is suitable for the technical field of education management, and provides a college student education evaluation management method and system based on deep learning, and the method comprises the steps: obtaining college student information which comprises basic information and learning behavior data, and obtaining a course arrangement of a school which comprises course content and a teaching plan; the learning progress of the college students is obtained, the learning attitudes of the students are obtained, the learning attitudes comprise emotional tendencies, and a classification model is adopted for multi-dimensional comprehensive evaluation; acquiring evaluation results, classifying the evaluation results, acquiring teaching intervention strategies corresponding to classification, and performing differentiated management according to teaching intervention; according to the method, learning progress improvement schemes under different management conditions are obtained, personalized learning resource recommendation and course rhythm adjustment are performed according to the schemes, and the problems that teaching schemes cannot be adjusted in time according to the learning progress of college students and teaching strategies cannot be changed according to local conditions according to the learning conditions of different students are solved.

Description

Technical Field

[0001] The present invention belongs to the field of educational management technology, and in particular, relates to a method and system for college student education assessment management based on deep learning. Background Art

[0002] With the popularization and development of higher education, the comprehensive quality of college students has become an important indicator of education evaluation. The comprehensive quality of college students includes not only academic performance, but also learning attitude, learning methods and teaching plans.

[0003] It is easy for students to develop a bias in their studies, be distracted in class, and have related defects in the acquisition and methods of knowledge and skills, which leads to a decline in their academic performance.

[0004] In the current assessment of college students' deep learning, there is a problem of being unable to adjust the teaching plan in a timely manner according to the learning progress of college students, and being unable to change the teaching strategy according to the learning conditions of different students. Summary of the invention

[0005] The purpose of the embodiment of the present invention is to provide a method for college student education assessment management based on deep learning, aiming to solve the problems raised in the third part of the background technology.

[0006] The embodiment of the present invention is implemented as follows: a method for managing college student education assessment based on deep learning, the method comprising: Obtaining college student information, including basic information and learning behavior data, and obtaining the school's course schedule, including course content and teaching plans; Obtain the learning progress of college students and their learning attitudes, including emotional tendencies, and use classification models to conduct multi-dimensional comprehensive evaluations; Obtain the evaluation results, classify the evaluation results, obtain the corresponding teaching intervention strategies, and perform differentiated management according to the teaching intervention; Obtain learning progress improvement plans under different management conditions, and make personalized learning resource recommendations and adjust the course rhythm based on the plans.

[0007] Preferably, the step of obtaining the learning progress of college students, obtaining the learning attitude of students, wherein the learning attitude includes emotional tendency, and using a classification model to conduct a multi-dimensional comprehensive evaluation specifically includes: Obtaining online learning platform data, wherein the online learning platform data is used to record the learning status of students, and obtaining the learning progress of college students according to the online learning platform data; Obtain student feedback data, determine student learning attitudes based on the feedback data, obtain camera data, and analyze student emotional tendencies through camera data; Comprehensive evaluation is conducted based on learning progress, learning attitude and emotional tendency, and classification model is used for multi-dimensional evaluation.

[0008] Preferably, the steps of obtaining the evaluation results, classifying the evaluation results, obtaining the teaching intervention strategies corresponding to the classifications, and performing differentiated management according to the teaching interventions specifically include: Obtain the evaluation results, obtain the interval classification of the evaluation results, and classify the evaluation results according to the interval classification; Obtaining classification results, including learning progress, emotional tendency and comprehensive performance, and obtaining teaching intervention strategies corresponding to the classification, including adjustment of teaching methods and optimization of learning resources; Differentiated management is carried out according to teaching intervention, and differentiated management is achieved through differentiated management, which includes stratified teaching.

[0009] Preferably, the steps of obtaining learning progress improvement plans under different management conditions, and recommending personalized learning resources and adjusting the course rhythm according to the plans specifically include: Obtain learning progress improvement plans under different management conditions and obtain students' learning behaviors, including video watching speed, test completion time and wrong question analysis; Recommend personalized learning resources based on the plan and adjust the course rhythm according to the plan, including accelerating the learning process, slowing down the learning process and adjusting the course tasks; The improvement effect of the reminder scheme is obtained, and the improvement effect is obtained through a questionnaire.

[0010] Preferably, the learning status includes class attendance, class tests and examination scores.

[0011] Another object of an embodiment of the present invention is to provide a college student education assessment management system based on deep learning, the system comprising: An information acquisition module is used to acquire college student information, including basic information and learning behavior data, and to acquire the school's course schedule, including course content and teaching plans; The evaluation module obtains the learning progress and learning attitude of college students, including emotional tendencies, and uses a classification model to conduct a comprehensive multi-dimensional evaluation; The partition management module obtains the evaluation results, classifies the evaluation results, obtains the corresponding teaching intervention strategies, and performs differentiated management according to the teaching intervention; The improvement plan module obtains learning progress improvement plans under different management conditions, and recommends personalized learning resources and adjusts the course rhythm based on the plans.

[0012] Preferably, the evaluation module includes: A learning progress unit, which obtains online learning platform data, wherein the online learning platform data is used to record the learning status of students, and obtains the learning progress of college students according to the online learning platform data; Learning attitude unit, obtains student feedback data, determines student learning attitude based on the feedback data, obtains camera data, and analyzes student emotional tendencies through camera data; The assessment unit conducts a comprehensive assessment based on learning progress, learning attitude and emotional tendency, and uses a classification model to conduct multi-dimensional assessment.

[0013] Preferably, the partition management module includes: A classification unit, which obtains the evaluation results, obtains the interval classification of the evaluation results, and classifies the evaluation results according to the interval classification; The teaching intervention unit obtains classification results, including learning progress, emotional tendency and comprehensive performance, and obtains teaching intervention strategies corresponding to the classification, including adjustment of teaching methods and optimization of learning resources; The zoning management unit performs differentiated management according to the teaching intervention, and realizes differentiated management through differentiated management, wherein the differentiated management includes stratified teaching.

[0014] Preferably, the improvement scheme module includes: Learning behavior unit, which obtains learning progress improvement plans under different management conditions and obtains students' learning behaviors, including video watching speed, test completion time and wrong question analysis; Improve the plan unit, recommend personalized learning resources according to the plan, and adjust the course rhythm according to the plan, including accelerating the learning process, slowing down the learning process, and adjusting the course tasks; The effect unit obtains the improvement effect of the reminder scheme, wherein the improvement effect is obtained through a questionnaire.

[0015] Preferably, the learning status includes class attendance, class tests and examination scores.

[0016] The embodiment of the present invention provides a method for managing college student education assessment based on deep learning, which obtains college student information, basic information and learning behavior data, obtains the school's course schedule, obtains course content and teaching plans, obtains online learning platform data, uses the online learning platform data to record student learning status, obtains student feedback data, determines student learning attitudes based on the feedback data, obtains camera data, analyzes student emotional tendencies through camera data, uses classification models to conduct multi-dimensional assessments based on learning progress, learning attitudes and emotional tendencies, captures student expression changes in distance learning or online classes, further analyzes their attitudes towards learning content, obtains assessment results, and classifies the assessment results based on interval classification to obtain classification results, which include learning progress, Emotional tendencies and comprehensive performance, obtain classification corresponding teaching intervention strategies, intervention strategies include adjustment of teaching methods and optimization of learning resources, differentiated management according to teaching intervention, differentiated management through differentiated management, achieve the effect of stratified teaching, obtain learning progress improvement plans under different management conditions, obtain students' learning behavior, obtain video viewing speed, test completion time and wrong question analysis, recommend personalized learning resources according to the plan, adjust the course rhythm according to the plan, including accelerating the learning process, slowing down the learning process and adjusting the course tasks, obtain the improvement effect of the reminder plan, and obtain the improvement effect through questionnaires, which solves the problem of not being able to adjust the teaching plan in time according to the learning progress of college students and not being able to change the teaching strategy according to local conditions according to the learning conditions of different students. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a method for college student education assessment management based on deep learning provided by an embodiment of the present invention; Figure 2 A flowchart of the steps of obtaining the learning progress of college students, obtaining the learning attitude of students, and using a classification model to conduct a multi-dimensional comprehensive evaluation provided by an embodiment of the present invention; Figure 3 A flowchart of the steps of classifying the evaluation results, obtaining the teaching intervention strategies corresponding to the classifications, and performing differentiated management according to the teaching interventions provided in an embodiment of the present invention; Figure 4 A flowchart of the steps of obtaining a learning progress improvement plan under different management conditions, and recommending personalized learning resources and adjusting the course rhythm according to the plan provided by an embodiment of the present invention; Figure 5 An architecture diagram of a college student education assessment management system based on deep learning provided by an embodiment of the present invention; Figure 6 An architectural diagram of an evaluation module provided in an embodiment of the present invention; Figure 7An architectural diagram of a partition management module provided in an embodiment of the present invention; Figure 8 The schematic diagram of the improvement scheme module provided in the embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0020] like Figure 1 As shown, a method for college student education assessment management based on deep learning is provided in an embodiment of the present invention, and the method includes: S100, obtaining college student information, the student information including basic information and learning behavior data, and obtaining the school's course schedule, the course schedule including course content and teaching plan.

[0021] In this step, the information of college students is obtained. Obtaining the information of college students is the basis of education management, including students' basic information, learning behavior data and psychological state, etc. The university's learning management system (LMS) and campus card system are used to automatically collect students' personal information, course selection, class assignment, library borrowing records, etc. These data can be used as basic features, such as learning interests and subject preferences; Through questionnaire surveys, sentiment analysis and connection with the psychological counseling room, we can obtain information about students' learning habits, stress conditions and emotional states. This helps us understand students' learning status from a psychological perspective; Obtaining and understanding the school's course schedule is a prerequisite for optimizing learning management. The course content is digitized, including the course outline, chapter division of knowledge points, marking of key points and difficulties, etc., to form a course knowledge map. The knowledge map can help students quickly find relevant knowledge points and improve review efficiency. By connecting with the academic affairs system, the timetable, exam schedule, homework deadline, etc. of each course can be obtained. At the same time, this information is synchronized with the online learning platform so that students' calendars and study plans can be automatically updated.

[0022] S200, obtaining the learning progress of college students and the learning attitude of students, wherein the learning attitude includes emotional tendency, and adopting a classification model to conduct a comprehensive evaluation in multiple dimensions.

[0023] In this step, the learning progress of college students is obtained. Obtaining the learning progress of college students is the core work to understand the current knowledge mastery of students. For example, through the data of online learning platforms, the behavior of students watching videos on online learning platforms is analyzed, including viewing time, playback speed, number of pauses, skipping segments, etc. The behavior of repeatedly watching a specific video may indicate that the knowledge point is difficult. The online system can be used to obtain the number of submissions, completion accuracy, and test scores of students' assignments. For example, if a student submits each assignment on time and scores high, it means that his learning progress in the course is relatively smooth. The frequency and duration of each login on the learning platform can be recorded to help understand the student's learning habits. Too little learning time may mean that the learning progress is lagging behind; In remote teaching or classroom discussions, students' emotional states can be judged by analyzing their tone, speaking speed, and pauses. For example, a flat tone and slowed speech speed may indicate that the student is confused or lacks interest, while a fast and forceful tone may indicate that the student is interested and engaged. Learning attitude reflects students' subjective feelings about the learning content and learning process, and emotional tendency is a key component of students' learning attitude. By analyzing students' emotional tendencies, we can gain a deeper understanding of their learning motivation, interest, and learning pressure.

[0024] S300, obtaining evaluation results, classifying the evaluation results, obtaining teaching intervention strategies corresponding to the classifications, and performing differentiated management according to the teaching interventions.

[0025] In this step, the assessment results are obtained. By obtaining the assessment results of the students, they are classified and corresponding teaching intervention strategies are formulated based on the classification results. Finally, differentiated management is carried out according to different intervention strategies, so that personalized educational support can be achieved. The evaluation results are based on the analysis of multi-dimensional data such as students' learning progress, learning attitudes, and emotional tendencies. These evaluation results can fully reflect students' learning performance and psychological state. According to the evaluation results of students, they can be divided into different categories. This classification can help teachers quickly understand the overall learning status of students and take corresponding measures; Differentiated management is carried out according to teaching interventions. Differentiated management is achieved through differentiated management. Differentiated management is based on the classification results of students and teaching intervention strategies to carry out personalized teaching resource allocation and learning management. Each category of students has different management needs, so it is necessary to flexibly adjust the course rhythm, learning content and tutoring support.

[0026] S400, obtains learning progress improvement plans under different management conditions, and recommends personalized learning resources and adjusts the course rhythm based on the plans.

[0027] In this step, learning progress improvement plans under different management conditions are obtained. Students' learning progress is affected by many factors. Common management conditions include the speed of learning progress, positive or negative emotional tendencies, active or passive learning attitudes, etc. Based on these conditions, the system can develop learning progress improvement plans suitable for different student groups.

[0028] Recommend the most appropriate learning resources for each student based on different learning progress improvement plans, which can help students improve their learning effectively based on their existing abilities. Personalized learning resources should be tailored to students’ learning progress, learning style, and emotional state; Adjusting the course pace in a timely manner according to students’ learning progress and emotional state is a key part of personalized teaching. Adjusting the course pace can ensure that students receive appropriate learning content at the appropriate time, avoiding learning pressure or lack of motivation caused by too fast or too slow progress.

[0029] like Figure 2 As shown, as a preferred embodiment of the present invention, the steps of obtaining the learning progress of college students, obtaining the learning attitude of students, wherein the learning attitude includes emotional tendency, and using a classification model to conduct a multi-dimensional comprehensive evaluation specifically include: S201, obtaining online learning platform data, wherein the online learning platform data is used to record the learning status of students, and the learning progress of college students is obtained according to the online learning platform data.

[0030] In this step, we obtain online learning platform data, obtain and analyze the learning status of college students from the online learning platform data to evaluate their learning progress. We can record students' learning behaviors through multiple dimensions and combine these data for detailed analysis. Record the total time each student spends watching the course video, the frequency of watching it, and the viewing time of each video. Understand whether students have watched the teaching video in its entirety or whether they frequently skip parts of the content. If a student watches the video in its entirety but frequently pauses or rewinds to watch a specific segment, it may indicate that the student has difficulty understanding a certain knowledge point; Record whether students watch videos on time and the percentage of course progress. For example, whether students have completed all the video content on time within a week, or which videos they have skipped, record the number of times students log in every day or week, and the length of time they log in to help evaluate their learning habits. A low login frequency may mean that students are not investing enough in their studies.

[0031] For example, Student A is taking a computer science course, and the online learning platform records his learning: Video Learning: Student A watched all 10 videos in the course, watching an average of 90% of the content in each video, but in a complex chapter, he paused and replayed specific parts several times.

[0032] Homework and Quizzes: Student A submitted all his homework and scored above 80. On the quizzes, he attempted some questions multiple times and finally achieved an average score of 85.

[0033] Platform usage: Student A logged into the platform 5 times a week, and each time he studied for 1-2 hours. In addition, he downloaded several supplementary learning materials, showing strong independent learning ability.

[0034] Progress Assessment: Course Completion: 100% (all videos watched).

[0035] S202, obtaining student feedback data, determining the student's learning attitude based on the feedback data, obtaining camera data, and analyzing the student's emotional tendency through the camera data.

[0036] In this step, we obtain student feedback data. By obtaining student feedback data and combining it with camera data, we can gain a deeper understanding of students’ learning attitudes and emotional tendencies. This information helps teachers and teaching systems to adjust teaching methods, content, and rhythm in a timely manner to better support students’ learning experience and results. Student feedback data includes their self-evaluation on the learning platform, feedback on the course content, interactions in class, and opinions expressed through questionnaires or discussion forums. This feedback can help us understand students' interest in the learning content, their understanding, and their initiative in learning. Students who show a positive learning attitude are usually characterized by high participation, positive course evaluations, and strong motivation to learn. For example, if a student says in feedback that the course content is "very interesting" and "I learned a lot of new knowledge," and that he or she actively participates in the discussion forum, frequently asking and answering questions, it usually indicates that the student is interested in and enthusiastic about the course content. If the student's feedback is mostly negative, such as "the course is too difficult to understand," "the progress is too fast and I can't keep up," and the student rarely participates in discussions or interactions, it may indicate that the student is not interested in the learning content or has difficulty understanding it. Camera data can capture students' facial expressions and body language. By analyzing this data, we can further understand the changes in students' emotions during the learning process. Emotional tendency (such as positive, negative or neutral) is an important dimension of learning attitude. Through emotional analysis, teachers can timely identify students' learning pressure, interest, frustration, etc., so as to intervene in teaching. If students often smile, or show concentration and relaxation on their faces when watching videos and listening to lectures, this usually reflects positive emotional tendencies. Positive emotional tendencies are usually accompanied by higher learning motivation and participation. If students show obvious negative emotions, such as frequent frowning, sighing, or often wandering eyes and distraction, it indicates that students may be in a negative mood. This may be caused by reasons such as the course content being too difficult and the learning pressure being too high.

[0037] S203, conduct a comprehensive assessment based on learning progress, learning attitude and emotional tendency, and use a classification model to conduct a multi-dimensional assessment.

[0038] In this step, a comprehensive assessment is conducted based on learning progress, learning attitude and emotional tendency, and a classification model is used for multi-dimensional analysis, which can provide a comprehensive assessment for each student, helping teachers understand the students' learning status and intervene in time. The multi-dimensional comprehensive assessment includes learning progress, learning attitude, and emotional tendency data obtained through sentiment analysis. Using the classification model, the education system can classify students in detail and formulate personalized teaching strategies based on the classification results; After obtaining the above multi-dimensional data, a classification model can be used for comprehensive evaluation. The classification model divides students into different categories by analyzing their learning progress, learning attitudes, and emotional tendencies, helping teachers identify students who need intervention or encourage students who perform well.

[0039] like Figure 3 As shown, as a preferred embodiment of the present invention, the steps of obtaining the evaluation results, classifying the evaluation results, obtaining the teaching intervention strategies corresponding to the classifications, and performing differentiated management according to the teaching interventions specifically include: S301, obtaining evaluation results, obtaining interval segment classification of the evaluation results, and classifying the evaluation results according to the interval segment classification.

[0040] In this step, the evaluation results are obtained. The evaluation results are usually generated through evaluation indicators of multiple dimensions, including students' academic performance, learning attitude, learning progress, emotional tendencies, etc. These evaluation results can be presented in the form of scores, percentages or grades, and provide a basis for subsequent classification; After obtaining the assessment results, the next step is to divide the assessment results into intervals. This step helps to group students' grades and performances according to certain standards, making it easier to identify students of different levels and formulate corresponding teaching intervention measures, and obtain the interval classification of the assessment results. The interval classification of the assessment results is to divide all students' assessment scores into different intervals according to certain rules (for example, high, medium, and low). This process helps to stratify students' overall performance and facilitates educators to classify and manage student groups; Before classifying the evaluation results into intervals, you first need to define the intervals based on the actual score distribution. This can be done using percentage methods (such as classifying the top 30% of the scores as high scores), fixed interval divisions (such as 90-100 as excellent, 70-89 as medium, and below 70 as low scores), etc.

[0041] Specific classification of students. By classifying students' test scores in different intervals, we can identify their position in the learning process. This classification is to develop personalized teaching interventions and distinguish the learning needs of different students. Students with excellent learning performance (high score segment): These students score high in the assessment, usually master the main knowledge points of the course, have a positive learning attitude and positive emotional tendencies. Such students can be motivated by accelerating their learning progress or providing more difficult tasks.

[0042] Students with average learning performance (middle score): These students are basically in line with expectations in terms of learning progress, but may have some deficiencies in certain knowledge points or emotional management. These students need to maintain their current learning pace and further consolidate their learning content through appropriate support.

[0043] Students with poor learning performance (low score): These students score low in the assessment and may have obvious difficulties in understanding the learning content, have a negative learning attitude, and have negative emotional tendencies. They need additional guidance from teachers, more learning resources, and emotional support to help them regain confidence and improve their learning progress.

[0044] S302, obtaining classification results, which include learning progress, emotional tendency and comprehensive performance, and obtaining teaching intervention strategies corresponding to the classification, which include adjustment of teaching methods and optimization of learning resources.

[0045] In this step, the classification results are obtained to obtain the classification corresponding to each college student. The learning progress reflects the students' mastery of the course content and the completion of the learning tasks. The emotional tendency captures the emotional state of the students during the learning process. The comprehensive performance is the evaluation result of the learning progress and emotional tendency, reflecting the overall learning status of the students. The comprehensive performance of students is usually divided into different levels: excellent performance: fast learning progress, positive emotions, showing high learning interest and ability; medium performance: normal learning progress, neutral or fluctuating emotional state, showing moderate learning participation; poor performance: slow learning progress, negative emotional tendency, indicating that students may encounter difficulties in learning; Based on the different classification results, teachers need to develop personalized teaching intervention strategies for each type of student's needs. These strategies are mainly divided into the adjustment of teaching methods and the optimization of learning resources. According to the performance of different types of students, the teaching methods should be flexibly adjusted to meet their specific learning needs. For example, for students with fast learning progress and positive emotions, they can be allowed to complete the course content at a faster pace, learn subsequent chapters in advance, or be given additional difficult tasks. In addition to adjusting the teaching methods, students of different categories also need to optimize the allocation of learning resources to ensure that they can obtain the most suitable learning materials. For example, high-level learning resources such as academic papers, research topics, interdisciplinary knowledge, etc. can be provided to students with outstanding performance to help them broaden their knowledge.

[0046] S303, performing differentiated management according to teaching intervention, and realizing differentiated management through differentiated management, wherein the differentiated management includes stratified teaching.

[0047] In this step, differentiated management is carried out according to teaching intervention. Differentiated management is to take targeted management measures based on the feedback results of students in the teaching intervention stage. It not only requires educators to have a deep understanding of students' learning progress, emotional state, and comprehensive performance, but also requires the design and implementation of personalized learning paths for different categories of students.

[0048] Based on the assessment results of each student, the teacher or education system designs a personalized learning path for them. This path can be adjusted dynamically based on the student's learning progress, learning style, emotional inclination, etc. Differentiated management is based on differentiated management, providing different teaching resources, tasks and support based on individual differences of students. This includes the difficulty of learning content, choice of learning methods, emotional and psychological support, etc. In differentiated management, teachers should not only design teaching plans according to the classification and level of students, but also constantly monitor students' learning progress and adjust teaching strategies through feedback. The goal of differentiated management is to help each student learn in the way that suits him best and achieve personalized education.

[0049] like Figure 4 As shown, as a preferred embodiment of the present invention, the steps of obtaining learning progress improvement plans under different management conditions, recommending personalized learning resources and adjusting the course rhythm according to the plans specifically include: S401, obtaining learning progress improvement plans under different management conditions, and obtaining students' learning behaviors, wherein the learning behaviors include video watching speed, test completion time, and wrong question analysis.

[0050] In this step, we obtain the learning progress improvement plan under different management conditions. When formulating the learning progress improvement plan under different management conditions, analyzing students' learning behavior can help us accurately understand students' learning patterns, knowledge mastery, and weak links in learning. Students' learning behavior data can come from a variety of sources, including their video viewing speed, test completion time, and wrong question analysis; After mastering the students' learning behavior data, the education system can design personalized learning progress improvement plans based on these data. These plans are adjusted according to the students' specific behaviors, aiming to improve learning efficiency, consolidate knowledge points and help them overcome difficulties in learning; Suppose a student frequently skips certain chapters while watching a video and does not replay these clips, which indicates that the student may think that he has mastered these contents. However, if he frequently pauses or replays other chapters, it may indicate that he does not understand these contents or needs more time. Simplified knowledge point review materials or tests can be provided to test whether the student has truly mastered these knowledge points. If it is found that these skipped chapters still have problems, remind the student to review them.

[0051] S402, recommend personalized learning resources according to the plan, and adjust the course rhythm according to the plan, including accelerating the learning process, slowing down the learning process, and adjusting the course tasks.

[0052] In this step, personalized learning resource recommendations are made according to the plan. Personalized learning resource recommendations are based on the analysis of each student's learning needs, progress, and learning behavior, providing the most suitable content for their learning. For students with slow learning progress or poor learning performance, basic learning resources can help them consolidate their foundation and understand core knowledge points. Simplified, step-by-step course videos and exercises specifically for basic knowledge points are used to help students consolidate their knowledge through repeated practice, and complex knowledge points are broken down into multiple small modules to guide students to complete them step by step; For students who are progressing quickly and performing well, advanced learning resources can help them broaden their knowledge and deepen their learning. These include more complex theories and concepts suitable for students who have already mastered the basics; academic papers, technical reports or interdisciplinary learning materials to help students delve deeper into a topic; and open-ended research or practical projects to encourage students to apply theory to practice. The course pace is adjusted by dynamically changing the learning speed and content difficulty based on students' learning progress and performance to ensure that every student can learn at an appropriate pace.

[0053] S403, obtaining the improvement effect of the reminder solution, wherein the improvement effect is obtained through a questionnaire.

[0054] In this step, the improvement effect of the reminder scheme is obtained. Obtaining the improvement effect of the reminder scheme through a questionnaire is a key step in measuring the effectiveness of personalized learning schemes (such as course reminders, learning task reminders, etc.). This kind of survey can help educators and system designers understand the impact of reminder strategies on students' learning progress, emotional tendencies, and learning experience, so as to optimize or adjust the scheme; These feedbacks can directly reflect whether the reminder program has a positive impact on students. If the questionnaire feedback shows that most students think the reminder frequency is appropriate, the content is helpful, and it improves learning efficiency, then the reminder program is effective. If the feedback shows that students feel more stressed or the reminder frequency is too high, then the reminder program may need to be optimized.

[0055] like Figure 5 As shown, a college student education assessment management system based on deep learning is provided in an embodiment of the present invention, and the system includes: The information acquisition module 100 is used to obtain college student information, which includes basic information and learning behavior data, and to obtain the school's course schedule, which includes course content and teaching plans.

[0056] In this system, the information acquisition module 100 acquires college student information. Acquiring college student information is the basis of education management, including students' basic information, learning behavior data and psychological state, etc. The university's learning management system (LMS) and campus card system are used to automatically collect students' personal information, course selection, class assignment, library borrowing records, etc. These data can be used as basic features, such as learning interests and subject preferences; Through questionnaire surveys, sentiment analysis and connection with the psychological counseling room, we can obtain information about students' learning habits, stress conditions and emotional states. This helps us understand students' learning status from a psychological perspective; Obtaining and understanding the school's course schedule is a prerequisite for optimizing learning management. The course content is digitized, including the course outline, chapter division of knowledge points, marking of key points and difficulties, etc., to form a course knowledge map. The knowledge map can help students quickly find relevant knowledge points and improve review efficiency. By connecting with the academic affairs system, the timetable, exam schedule, homework deadline, etc. of each course can be obtained. At the same time, this information is synchronized with the online learning platform so that students' calendars and study plans can be automatically updated.

[0057] The evaluation module 200 is used to obtain the learning progress of college students and their learning attitudes, which include emotional tendencies, and use classification models to conduct multi-dimensional comprehensive evaluations.

[0058] In this system, the evaluation module 200 obtains the learning progress of college students. Obtaining the learning progress of college students is the core work to understand the current knowledge mastery of students. For example, through the online learning platform data, the student's video viewing behavior on the online learning platform is analyzed, including viewing time, playback speed, number of pauses, skipped segments, etc. The behavior of repeatedly watching a specific video may indicate that the knowledge point is difficult. The online system can be used to obtain the number of submissions, completion accuracy, and test scores of students' assignments. For example, if a student submits each assignment on time and scores high, it means that his learning progress in the course is relatively smooth. The frequency and duration of each login on the learning platform can be recorded to help understand the student's learning habits. Too little learning time may mean that the learning progress is lagging behind; In remote teaching or classroom discussions, students' emotional states can be judged by analyzing their tone, speaking speed, and pauses. For example, a flat tone and slowed speech speed may indicate that the student is confused or lacks interest, while a fast and forceful tone may indicate that the student is interested and engaged. Learning attitude reflects students' subjective feelings about the learning content and learning process, and emotional tendency is a key component of students' learning attitude. By analyzing students' emotional tendencies, we can gain a deeper understanding of their learning motivation, interest, and learning pressure.

[0059] The partition management module 300 is used to obtain the evaluation results, classify the evaluation results, obtain the teaching intervention strategies corresponding to the classifications, and perform differentiated management according to the teaching interventions.

[0060] In this system, the partition management module 300 obtains the evaluation results, classifies the evaluation results of the students, and formulates corresponding teaching intervention strategies based on the classification results. Finally, differentiated management is performed according to different intervention strategies, so as to realize personalized education support; The evaluation results are based on the analysis of multi-dimensional data such as students' learning progress, learning attitudes, and emotional tendencies. These evaluation results can fully reflect students' learning performance and psychological state. According to the evaluation results of students, they can be divided into different categories. This classification can help teachers quickly understand the overall learning status of students and take corresponding measures; Differentiated management is carried out according to teaching interventions. Differentiated management is achieved through differentiated management. Differentiated management is based on the classification results of students and teaching intervention strategies to carry out personalized teaching resource allocation and learning management. Each category of students has different management needs, so it is necessary to flexibly adjust the course rhythm, learning content and tutoring support.

[0061] The improvement plan module 400 is used to obtain learning progress improvement plans under different management conditions, and to recommend personalized learning resources and adjust the course rhythm according to the plans.

[0062] In this system, the improvement plan module 400 obtains learning progress improvement plans under different management conditions. The learning progress of students is affected by many factors. Common management conditions include the speed of learning progress, the positive or negative emotional tendency, the initiative or negativity of learning attitude, etc. Based on these conditions, the system can formulate learning progress improvement plans suitable for different student groups.

[0063] Recommend the most appropriate learning resources for each student based on different learning progress improvement plans, which can help students improve their learning effectively based on their existing abilities. Personalized learning resources should be tailored to students’ learning progress, learning style, and emotional state; Adjusting the course pace in a timely manner according to students’ learning progress and emotional state is a key part of personalized teaching. Adjusting the course pace can ensure that students receive appropriate learning content at the appropriate time, avoiding learning pressure or lack of motivation caused by too fast or too slow progress.

[0064] like Figure 6 As shown, as a preferred embodiment of the present invention, the evaluation module 200 includes: The learning progress unit 201 is used to obtain online learning platform data, where the online learning platform data is used to record the student's learning status and obtain the college student's learning progress based on the online learning platform data.

[0065] In this module, the learning progress unit 201 obtains online learning platform data, obtains and analyzes the learning status of college students from the online learning platform data to evaluate their learning progress, and can record students' learning behaviors through multiple dimensions and conduct detailed analysis in combination with these data; Record the total time each student spends watching the course video, the frequency of watching it, and the viewing time of each video. Understand whether students have watched the teaching video in its entirety or whether they frequently skip parts of the content. If a student watches the video in its entirety but frequently pauses or rewinds to watch a specific segment, it may indicate that the student has difficulty understanding a certain knowledge point; Record whether students watch videos on time and the percentage of course progress. For example, whether students have completed all the video content on time within a week, or which videos they have skipped, record the number of times students log in every day or week, and the length of time they log in to help evaluate their learning habits. A low login frequency may mean that students are not investing enough in their studies.

[0066] For example, Student A is taking a computer science course, and the online learning platform records his learning: Video Learning: Student A watched all 10 videos in the course, watching an average of 90% of the content in each video, but in a complex chapter, he paused and replayed specific parts several times.

[0067] Homework and Quizzes: Student A submitted all his homework and scored above 80. On the quizzes, he attempted some questions multiple times and finally achieved an average score of 85.

[0068] Platform usage: Student A logged into the platform 5 times a week, and each time he studied for 1-2 hours. In addition, he downloaded several supplementary learning materials, showing strong independent learning ability.

[0069] Progress Assessment: Course Completion: 100% (all videos watched).

[0070] The learning attitude unit 202 is used to obtain student feedback data, determine the student's learning attitude based on the feedback data, obtain camera data, and analyze the student's emotional tendency through the camera data.

[0071] In this module, the learning attitude unit 202 obtains student feedback data. By obtaining student feedback data and combining it with camera data, a deeper understanding of students' learning attitudes and emotional tendencies can be obtained. This information helps teachers and teaching systems to adjust teaching methods, content, and rhythm in a timely manner to better support students' learning experience and results; Student feedback data includes their self-evaluation on the learning platform, feedback on the course content, interactions in class, and opinions expressed through questionnaires or discussion forums. This feedback can help us understand students' interest in the learning content, their understanding, and their initiative in learning. Students who show a positive learning attitude are usually characterized by high participation, positive course evaluations, and strong motivation to learn. For example, if a student says in feedback that the course content is "very interesting" and "I learned a lot of new knowledge," and that he or she actively participates in the discussion forum, frequently asking and answering questions, it usually indicates that the student is interested in and enthusiastic about the course content. If the student's feedback is mostly negative, such as "the course is too difficult to understand," "the progress is too fast and I can't keep up," and the student rarely participates in discussions or interactions, it may indicate that the student is not interested in the learning content or has difficulty understanding it. Camera data can capture students' facial expressions and body language. By analyzing this data, we can further understand the changes in students' emotions during the learning process. Emotional tendency (such as positive, negative or neutral) is an important dimension of learning attitude. Through emotional analysis, teachers can timely identify students' learning pressure, interest, frustration, etc., so as to intervene in teaching. If students often smile, or show concentration and relaxation on their faces when watching videos and listening to lectures, this usually reflects positive emotional tendencies. Positive emotional tendencies are usually accompanied by higher learning motivation and participation. If students show obvious negative emotions, such as frequent frowning, sighing, or often wandering eyes and distraction, it indicates that students may be in a negative mood. This may be caused by reasons such as the course content being too difficult and the learning pressure being too high.

[0072] The evaluation unit 203 is used to conduct a comprehensive evaluation based on learning progress, learning attitude and emotional tendency, and adopts a classification model to conduct a multi-dimensional evaluation.

[0073] In this module, the evaluation unit 203 conducts a comprehensive evaluation based on learning progress, learning attitude and emotional tendency, and adopts a classification model for multi-dimensional analysis, which can provide a comprehensive evaluation for each student, helping teachers understand the students' learning status and intervene in time. The multi-dimensional comprehensive evaluation includes learning progress, learning attitude, and emotional tendency data obtained through emotional analysis. Using the classification model, the education system can classify students in detail and formulate personalized teaching strategies based on the classification results; After obtaining the above multi-dimensional data, a classification model can be used for comprehensive evaluation. The classification model divides students into different categories by analyzing their learning progress, learning attitudes, and emotional tendencies, helping teachers identify students who need intervention or encourage students who perform well.

[0074] like Figure 7As shown, as a preferred embodiment of the present invention, the partition management module 300 includes: The classification unit 301 is used to obtain the evaluation results, obtain the interval classification of the evaluation results, and classify the evaluation results according to the interval classification.

[0075] In this module, the classification unit 301 obtains the evaluation results, which are usually generated through evaluation indicators of multiple dimensions, including students' academic performance, learning attitude, learning progress, emotional tendencies, etc. These evaluation results can be presented in the form of scores, percentages or grades, and provide a basis for subsequent classification; After obtaining the assessment results, the next step is to divide the assessment results into intervals. This step helps to group students' grades and performances according to certain standards, making it easier to identify students of different levels and formulate corresponding teaching intervention measures, and obtain the interval classification of the assessment results. The interval classification of the assessment results is to divide all students' assessment scores into different intervals according to certain rules (for example, high, medium, and low). This process helps to stratify students' overall performance and facilitates educators to classify and manage student groups; Before classifying the evaluation results into intervals, you first need to define the intervals based on the actual score distribution. This can be done using percentage methods (such as classifying the top 30% of the scores as high scores), fixed interval divisions (such as 90-100 as excellent, 70-89 as medium, and below 70 as low scores), etc.

[0076] Specific classification of students. By classifying students' test scores in different intervals, we can identify their position in the learning process. This classification is to develop personalized teaching interventions and distinguish the learning needs of different students. Students with excellent learning performance (high score segment): These students score high in the assessment, usually master the main knowledge points of the course, have a positive learning attitude and positive emotional tendencies. Such students can be motivated by accelerating their learning progress or providing more difficult tasks.

[0077] Students with average learning performance (middle score): These students are basically in line with expectations in terms of learning progress, but may have some deficiencies in certain knowledge points or emotional management. These students need to maintain their current learning pace and further consolidate their learning content through appropriate support.

[0078] Students with poor learning performance (low score): These students score low in the assessment and may have obvious difficulties in understanding the learning content, have a negative learning attitude, and have negative emotional tendencies. They need additional guidance from teachers, more learning resources, and emotional support to help them regain confidence and improve their learning progress.

[0079] The teaching intervention unit 302 is used to obtain classification results, which include learning progress, emotional tendency and comprehensive performance, and obtain teaching intervention strategies corresponding to the classification, which include adjustment of teaching methods and optimization of learning resources.

[0080] In this module, the teaching intervention unit 302 obtains the classification results and obtains the classification corresponding to each college student. The learning progress reflects the students' mastery of the course content and the completion of the learning tasks. The emotional tendency captures the emotional state of the students during the learning process. The comprehensive performance is the evaluation result of the combination of learning progress and emotional tendency, reflecting the overall learning status of the students. The comprehensive performance of students is usually divided into different levels: excellent performance: fast learning progress, positive emotions, showing high learning interest and ability; medium performance: normal learning progress, neutral or fluctuating emotional state, showing moderate learning participation; poor performance: slow learning progress, negative emotional tendency, indicating that students may encounter difficulties in learning; Based on the different classification results, teachers need to develop personalized teaching intervention strategies for each type of student's needs. These strategies are mainly divided into the adjustment of teaching methods and the optimization of learning resources. According to the performance of different types of students, the teaching methods should be flexibly adjusted to meet their specific learning needs. For example, for students with fast learning progress and positive emotions, they can be allowed to complete the course content at a faster pace, learn subsequent chapters in advance, or be given additional difficult tasks. In addition to adjusting the teaching methods, students of different categories also need to optimize the allocation of learning resources to ensure that they can obtain the most suitable learning materials. For example, high-level learning resources such as academic papers, research topics, interdisciplinary knowledge, etc. can be provided to students with outstanding performance to help them broaden their knowledge.

[0081] The partition management unit 303 is used to perform differentiated management according to the teaching intervention, and realize differentiated management through differentiated management, wherein the differentiated management includes stratified teaching.

[0082] In this module, the zone management unit 303 performs differentiated management according to the teaching intervention. Differentiated management is to take targeted management measures according to the feedback results of students in the teaching intervention stage. It not only requires educators to have an in-depth understanding of students' learning progress, emotional state, and comprehensive performance, but also requires the design and implementation of personalized learning paths for different categories of students.

[0083] Based on the assessment results of each student, the teacher or education system designs a personalized learning path for them. This path can be adjusted dynamically based on the student's learning progress, learning style, emotional inclination, etc. Differentiated management is based on differentiated management, providing different teaching resources, tasks and support based on individual differences of students. This includes the difficulty of learning content, choice of learning methods, emotional and psychological support, etc. In differentiated management, teachers should not only design teaching plans according to the classification and level of students, but also constantly monitor students' learning progress and adjust teaching strategies through feedback. The goal of differentiated management is to help each student learn in the way that suits him best and achieve personalized education.

[0084] like Figure 8 As shown, as a preferred embodiment of the present invention, the improvement scheme module 400 includes: The learning behavior unit 401 is used to obtain learning progress improvement plans under different management conditions and obtain students' learning behaviors, which include video watching speed, test completion time and wrong question analysis.

[0085] In this module, the learning behavior unit 401 obtains the learning progress improvement plan under different management conditions. When formulating the learning progress improvement plan under different management conditions, analyzing the students' learning behavior can help us accurately understand the students' learning patterns, knowledge mastery, and weak links in learning. The students' learning behavior data can come from a variety of sources, including their video viewing speed, test completion time, and wrong question analysis; After mastering the students' learning behavior data, the education system can design personalized learning progress improvement plans based on these data. These plans are adjusted according to the students' specific behaviors, aiming to improve learning efficiency, consolidate knowledge points and help them overcome difficulties in learning; Suppose a student frequently skips certain chapters while watching a video and does not replay these clips, which indicates that the student may think that he has mastered these contents. However, if he frequently pauses or replays other chapters, it may indicate that he does not understand these contents or needs more time. Simplified knowledge point review materials or tests can be provided to test whether the student has truly mastered these knowledge points. If it is found that these skipped chapters still have problems, remind the student to review them.

[0086] The improvement plan unit 402 is used to recommend personalized learning resources according to the plan and adjust the course rhythm according to the plan, including accelerating the learning process, slowing down the learning process and adjusting the course tasks.

[0087] In this module, the improvement plan unit 402 recommends personalized learning resources based on the plan. The personalized learning resource recommendation is based on the analysis of each student's learning needs, progress and learning behavior, and provides the most suitable content for their learning. For students with slow learning progress or poor learning performance, basic learning resources can help them consolidate their foundation and understand core knowledge points. Simplified, step-by-step course videos and exercises specifically for basic knowledge points are used to help students consolidate their knowledge through repeated practice, and complex knowledge points are broken down into multiple small modules to gradually guide students to complete them; For students who are progressing quickly and performing well, advanced learning resources can help them broaden their knowledge and deepen their learning. These include more complex theories and concepts suitable for students who have already mastered the basics; academic papers, technical reports or interdisciplinary learning materials to help students delve deeper into a topic; and open-ended research or practical projects to encourage students to apply theory to practice. The course pace is adjusted by dynamically changing the learning speed and content difficulty based on students' learning progress and performance to ensure that every student can learn at an appropriate pace.

[0088] The effect unit 403 is used to obtain the improvement effect of the reminder solution, and the improvement effect is obtained through a questionnaire.

[0089] In this module, the effect unit 403 obtains the improvement effect of the reminder scheme. Obtaining the improvement effect of the reminder scheme through a questionnaire is a key step in measuring the effectiveness of personalized learning schemes (such as course reminders, learning task reminders, etc.). This kind of survey can help educators and system designers understand the impact of reminder strategies on students' learning progress, emotional tendencies, and learning experiences, so as to optimize or adjust the scheme; These feedbacks can directly reflect whether the reminder program has a positive impact on students. If the questionnaire feedback shows that most students think the reminder frequency is appropriate, the content is helpful, and it improves learning efficiency, then the reminder program is effective. If the feedback shows that students feel more stressed or the reminder frequency is too high, then the reminder program may need to be optimized.

[0090] In one embodiment, a computer device is provided, the computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented: Obtaining college student information, including basic information and learning behavior data, and obtaining the school's course schedule, including course content and teaching plans; Obtain the learning progress of college students and their learning attitudes, including emotional tendencies, and use classification models to conduct multi-dimensional comprehensive evaluations; Obtain the evaluation results, classify the evaluation results, obtain the corresponding teaching intervention strategies, and perform differentiated management according to the teaching intervention; Obtain learning progress improvement plans under different management conditions, and make personalized learning resource recommendations and adjust the course rhythm based on the plans.

[0091] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor performs the following steps: Obtaining college student information, including basic information and learning behavior data, and obtaining the school's course schedule, including course content and teaching plans; Obtain the learning progress of college students and their learning attitudes, including emotional tendencies, and use classification models to conduct multi-dimensional comprehensive evaluations; Obtain the evaluation results, classify the evaluation results, obtain the corresponding teaching intervention strategies, and perform differentiated management according to the teaching intervention; Obtain learning progress improvement plans under different management conditions, and make personalized learning resource recommendations and adjust the course rhythm based on the plans.

[0092] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0093] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0094] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0096] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for college student education assessment management based on deep learning, characterized in that: The method comprises: Obtaining college student information, including basic information and learning behavior data, and obtaining the school's course schedule, including course content and teaching plans; Obtain the learning progress of college students and their learning attitudes, including emotional tendencies, and use classification models to conduct multi-dimensional comprehensive evaluations; Obtain the evaluation results, classify the evaluation results, obtain the corresponding teaching intervention strategies, and perform differentiated management according to the teaching intervention; Obtain learning progress improvement plans under different management conditions, and make personalized learning resource recommendations and adjust the course rhythm based on the plans.

2. According to a method for college student education assessment management based on deep learning according to claim 1, it is characterized in that: The steps of obtaining the learning progress of college students, obtaining the learning attitude of students, wherein the learning attitude includes emotional tendency, and using a classification model to conduct a multi-dimensional comprehensive evaluation specifically include: Obtaining online learning platform data, wherein the online learning platform data is used to record the learning status of students, and obtaining the learning progress of college students according to the online learning platform data; Obtain student feedback data, determine student learning attitudes based on the feedback data, obtain camera data, and analyze student emotional tendencies through camera data; Comprehensive evaluation is conducted based on learning progress, learning attitude and emotional tendency, and classification model is used for multi-dimensional evaluation.

3. According to a method for college student education assessment management based on deep learning according to claim 1, it is characterized in that: The steps of obtaining the evaluation results, classifying the evaluation results, obtaining the teaching intervention strategies corresponding to the classifications, and performing differentiated management according to the teaching interventions specifically include: Obtain the evaluation results, obtain the interval classification of the evaluation results, and classify the evaluation results according to the interval classification; Obtaining classification results, including learning progress, emotional tendency and comprehensive performance, and obtaining teaching intervention strategies corresponding to the classification, including adjustment of teaching methods and optimization of learning resources; Differentiated management is carried out according to teaching intervention, and differentiated management is achieved through differentiated management, which includes stratified teaching.

4. According to a method for college student education assessment management based on deep learning according to claim 1, it is characterized in that: The steps of obtaining learning progress improvement plans under different management conditions, and recommending personalized learning resources and adjusting the course rhythm according to the plans specifically include: Obtain learning progress improvement plans under different management conditions and obtain students' learning behaviors, including video watching speed, test completion time and wrong question analysis; Recommend personalized learning resources based on the plan and adjust the course rhythm according to the plan, including accelerating the learning process, slowing down the learning process and adjusting the course tasks; The improvement effect of the reminder scheme is obtained, and the improvement effect is obtained through a questionnaire.

5. According to a method for college student education assessment management based on deep learning according to claim 1, it is characterized in that: The learning status includes class attendance, class tests and examination scores.

6. A college student education assessment management system based on deep learning, characterized in that: The system comprises: An information acquisition module is used to acquire college student information, including basic information and learning behavior data, and to acquire the school's course schedule, including course content and teaching plans; The evaluation module obtains the learning progress and learning attitude of college students, including emotional tendencies, and uses a classification model to conduct a comprehensive multi-dimensional evaluation; The partition management module obtains the evaluation results, classifies the evaluation results, obtains the corresponding teaching intervention strategies, and performs differentiated management according to the teaching intervention; The improvement plan module obtains learning progress improvement plans under different management conditions, and recommends personalized learning resources and adjusts the course rhythm based on the plans.

7. According to claim 6, a college student education assessment management system based on deep learning is characterized in that: The evaluation module includes: A learning progress unit, which obtains online learning platform data, wherein the online learning platform data is used to record the learning status of students, and obtains the learning progress of college students according to the online learning platform data; Learning attitude unit, obtains student feedback data, determines student learning attitude based on the feedback data, obtains camera data, and analyzes student emotional tendencies through camera data; The assessment unit conducts a comprehensive assessment based on learning progress, learning attitude and emotional tendency, and uses a classification model to conduct multi-dimensional assessment.

8. According to the deep learning-based college student education assessment management system of claim 7, it is characterized in that: The partition management module includes: A classification unit, which obtains the evaluation results, obtains the interval classification of the evaluation results, and classifies the evaluation results according to the interval classification; The teaching intervention unit obtains classification results, including learning progress, emotional tendency and comprehensive performance, and obtains teaching intervention strategies corresponding to the classification, including adjustment of teaching methods and optimization of learning resources; The zoning management unit performs differentiated management according to the teaching intervention, and realizes differentiated management through differentiated management, wherein the differentiated management includes stratified teaching.

9. A deep learning-based college student education assessment management system according to claim 8, characterized in that: The improvement scheme module includes: Learning behavior unit, which obtains learning progress improvement plans under different management conditions and obtains students' learning behaviors, including video watching speed, test completion time and wrong question analysis; Improve the plan unit, recommend personalized learning resources according to the plan, and adjust the course rhythm according to the plan, including accelerating the learning process, slowing down the learning process, and adjusting the course tasks; The effect unit obtains the improvement effect of the reminder scheme, wherein the improvement effect is obtained through a questionnaire.

10. A college student education assessment management system based on deep learning according to claim 9, characterized in that: The learning status includes class attendance, class tests and examination scores.

Images