Intelligent multi-dimensional college teaching quality improvement and evaluation system

Abstract

The invention relates to the technical field of college teaching, in particular to an intelligent multi-dimensional college teaching quality improvement and evaluation system, which comprises a data acquisition module, a data processing module, an intelligent analysis module, a strategy recommendation module and an effect evaluation module, and is characterized in that the data acquisition module is used for acquiring original data in a teaching process from multiple dimensions; the data processing module is used for processing the collected original data to form a standardized and structured data set; the intelligent analysis module is used for carrying out deep analysis on the processed data by applying an intelligent algorithm and carrying out multi-dimensional quantitative evaluation on the teaching quality; the strategy recommendation module is used for providing personalized teaching strategy recommendation for teachers based on the analysis and evaluation result in combination with a preset teaching quality improvement model; and the effect evaluation module is used for tracking and evaluating the teaching effect after the teaching strategy is implemented in real time. The system realizes comprehensive, objective and accurate evaluation and improvement of teaching quality of colleges and universities.

Description

Technical Field

[0001] The present invention relates to the field of university teaching technology, and in particular to an intelligent multi-dimensional university teaching quality improvement and evaluation system. Background Art

[0002] With the popularization and in-depth development of higher education, teaching quality has become one of the core indicators for measuring the level of higher education. However, traditional teaching quality evaluation often relies on a single test score or student satisfaction survey, which is difficult to fully and objectively reflect the multi-dimensional information in the teaching process, such as the effectiveness of teaching methods, the quality of teacher-student interaction, and the efficiency of teaching resources. In addition, measures to improve teaching quality are often blind and inefficient due to the lack of accurate data support and scientific analysis tools.

[0003] In recent years, with the rapid development of technologies such as big data, artificial intelligence, and cloud computing, the field of education has ushered in a wave of intelligent transformation. Intelligent teaching management systems have begun to be gradually applied to colleges and universities, aiming to optimize the allocation of teaching resources through data-driven methods, improve the scientificity and accuracy of teaching quality evaluation, and promote continuous improvement of teaching quality. However, existing systems mostly focus on single-dimensional data collection or analysis, and lack a comprehensive intelligent multi-dimensional teaching quality improvement and evaluation platform.

[0004] Based on this, the present invention proposes an intelligent multi-dimensional university teaching quality improvement and evaluation system. Summary of the invention

[0005] In order to solve the above problems, the present invention provides an intelligent multi-dimensional college teaching quality improvement and evaluation system, which realizes a comprehensive, objective and accurate evaluation and improvement of college teaching quality, and has significant technical effects and practical value.

[0006] The technical solution of the present invention is as follows: An intelligent multi-dimensional college teaching quality improvement and evaluation system includes a data acquisition module, a data processing module, an intelligent analysis module, a strategy recommendation module and an effect evaluation module, among which: The data collection module is used to collect raw data from multiple dimensions during the teaching process; The data processing module is used to process the collected raw data to form a standardized and structured data set; The intelligent analysis module is used to apply intelligent algorithms to conduct in-depth analysis of processed data and conduct multi-dimensional quantitative evaluation of teaching quality; The strategy recommendation module is used to provide teachers with personalized teaching strategy recommendations based on the analysis and evaluation results and the preset teaching quality improvement model; The effect evaluation module is used to track and evaluate the teaching effect after the implementation of the teaching strategy in real time.

[0007] The data collection sources of the data collection module include student data, teacher data, teaching resource data and teaching environment data.

[0008] The data collection methods of the data collection module include automatic collection and manual collection.

[0009] The data processing flow of the data processing module includes the following steps: data reception, data preprocessing, data integration, data storage, data optimization and data verification.

[0010] The intelligent analysis process of the intelligent analysis module includes data preparation, feature extraction, model selection, model training, evaluation execution, structure interpretation and feedback optimization. The intelligent evaluation of the intelligent analysis module includes at least one or more of the following evaluations: total score evaluation of teaching quality satisfaction, evaluation of teacher-student interaction quality, evaluation of teaching resource utilization efficiency, evaluation of student learning participation, evaluation of teaching content mastery, evaluation of teaching method effectiveness, and evaluation of teaching environment satisfaction.

[0011] The total evaluation formula for teaching quality satisfaction is: , Where S is the total score of teaching quality satisfaction, n is the number of evaluation dimensions, wi is the weight of the i-th evaluation dimension, and si is the satisfaction score of the i-th evaluation dimension.

[0012] The evaluation formula for teacher-student interaction quality is: , Where I is the teacher-student interaction quality evaluation index, C is the total number of teacher-student interactions, T is the total teaching time, Q is the number of high-quality interactions (such as in-depth discussions, effective questions, etc.), R is the interaction response speed (which can be measured by calculating the time interval from students asking questions to teachers answering), and α and β are weight coefficients.

[0013] The strategy recommendation process of the strategy recommendation module includes data reception and preprocessing, strategy matching and screening, personalized recommendation generation, recommendation result display and feedback, and strategy optimization and update.

[0014] The effect evaluation module adopts a quantitative evaluation method based on performance changes, and the steps include: data collection, data processing, comparative analysis and result display; Or adopt student feedback evaluation based on questionnaire survey, the steps include: questionnaire design, data collection, data processing and analysis and result feedback.

[0015] The beneficial effects of the present invention are: 1. The present invention discloses an intelligent multi-dimensional system for improving and evaluating the teaching quality of colleges and universities. The intelligent multi-dimensional system for improving and evaluating the teaching quality of colleges and universities can comprehensively collect original data from multiple dimensions such as students, teachers, teaching resources and teaching environment through a data acquisition module, thereby ensuring the comprehensiveness and accuracy of the data and providing a solid foundation for subsequent data processing and intelligent analysis.

[0016] 2. The present invention discloses an intelligent multi-dimensional system for improving and evaluating the teaching quality of colleges and universities. Through the data processing module, the system can standardize and structure the collected raw data to form a data set in a unified format, which is convenient for subsequent data analysis and mining.

[0017] 3. The present invention discloses an intelligent multi-dimensional college teaching quality improvement and evaluation system. The intelligent analysis module of the intelligent multi-dimensional college teaching quality improvement and evaluation system can use advanced intelligent algorithms to conduct in-depth analysis of processed data, thereby realizing multi-dimensional quantitative evaluation of teaching quality. This evaluation method is more scientific, objective and accurate than traditional methods.

[0018] 4. The present invention discloses an intelligent multi-dimensional college teaching quality improvement and evaluation system. The intelligent multi-dimensional college teaching quality improvement and evaluation system is based on the results of intelligent analysis. The strategy recommendation module can provide teachers with personalized teaching strategy recommendations, helping teachers to improve teaching methods in a targeted manner and improve teaching quality.

[0019] 5. The present invention discloses an intelligent multi-dimensional system for improving and evaluating the teaching quality of colleges and universities. The effect evaluation module of the intelligent multi-dimensional system for improving and evaluating the teaching quality of colleges and universities can track and evaluate the teaching effect after the implementation of teaching strategies in real time, providing strong data support for the continuous improvement of teaching quality.

[0020] 6. The present invention discloses an intelligent multi-dimensional system for improving and evaluating the teaching quality of colleges and universities. Through the application of this system, colleges and universities can more accurately identify problems and improvement points in the teaching process, thereby improving teaching efficiency and student satisfaction, and promoting the overall improvement of education quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the detailed description of the preferred embodiment below, the scheme and advantages of the present application will become clear to those skilled in the art. The accompanying drawings are only for the purpose of illustrating the preferred embodiment and are not to be considered as limiting the present invention.

[0022] In the attached picture: Figure 1This is a workflow diagram of an intelligent multi-dimensional university teaching quality improvement and evaluation system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The intelligent multi-dimensional college teaching quality improvement and evaluation system includes data collection module, data processing module, intelligent analysis module, strategy recommendation module and effect evaluation module.

[0024] like Figure 1 As shown, the data acquisition module is used to collect raw data in the teaching process from multiple dimensions; The data processing module is used to process the collected raw data to form a standardized and structured data set; The intelligent analysis module is used to apply intelligent algorithms to conduct in-depth analysis of processed data and conduct multi-dimensional quantitative evaluation of teaching quality; The strategy recommendation module is used to provide teachers with personalized teaching strategy recommendations based on the analysis and evaluation results and the preset teaching quality improvement model; The effect evaluation module is used to track and evaluate the teaching effect after the implementation of the teaching strategy in real time.

[0025] The data collection module is the primary link of the intelligent multi-dimensional college teaching quality improvement and evaluation system, responsible for comprehensively and systematically collecting various raw data generated in the teaching process. These data cover multiple dimensions of the teaching process, including but not limited to student performance, teacher behavior, teaching resource utilization, and teaching environment, and are the basis for subsequent data processing, intelligent analysis, strategy recommendation, and effect evaluation.

[0026] The data collection sources and scope are as follows: A. Student Data: Grade data: including regular grades, midterm exams, final exams and other grade records.

[0027] Behavioral data: online learning duration, number of resource accesses, interactive participation (such as questions, answers, discussions, etc.).

[0028] Feedback data: students’ satisfaction evaluation and suggestions on courses, teachers and teaching resources.

[0029] B. Teacher data: Teaching plan: teaching syllabus, lesson plans, courseware and other teaching preparation materials.

[0030] Classroom behavior: duration of lectures, teaching methods (such as lectures, discussions, experiments, etc.), and classroom interaction.

[0031] Self-evaluation: Teacher’s self-reflection report, including teaching highlights, shortcomings and directions for improvement.

[0032] C. Teaching resource data: Textbook usage: textbook version, frequency of use, student feedback, etc.

[0033] Multimedia resources: production, use and feedback of video, audio, PPT and other teaching materials.

[0034] Extracurricular learning materials: extracurricular books, articles, websites and other resources recommended by teachers.

[0035] D. Teaching environment data: Classroom facilities: environmental parameters such as temperature, humidity, light, noise, etc.

[0036] Network stability: speed, stability and fault records of classroom network.

[0037] Classroom layout and equipment: seating arrangement, configuration and use of teaching equipment such as blackboard / whiteboard and projector.

[0038] The data collection methods and techniques are as follows: A. Automatic collection: API interface connection: Establish API interfaces with existing systems such as the academic affairs system, learning management system (LMS), and student information system to automatically capture and synchronize information such as student grades, behavioral data, and teaching resource usage.

[0039] Internet of Things technology: Use sensors, RFID and other technologies to automatically collect classroom environmental parameters (such as temperature, humidity, light, etc.) and student behavior data (such as seat occupancy, attendance rate, etc.).

[0040] Log analysis: Obtain data on user behavior, system performance, etc. by analyzing server logs, application logs, etc.

[0041] B. Manual collection: Questionnaire survey: Design and distribute paper or online questionnaires to collect students’ and teachers’ feedback on courses, teachers, and teaching resources. The questionnaire content should cover multiple dimensions to ensure the comprehensiveness of the data.

[0042] Classroom observation: Organize specialized personnel or use cameras to observe the classroom, record the teacher's teaching behavior, classroom interaction and students' reactions. The observation records should be detailed and objective to provide strong support for subsequent analysis.

[0043] Data entry: For data that cannot be collected automatically, such as teacher self-evaluation reports, special case records, etc., a dedicated person needs to be assigned to manually enter the data. The accuracy and completeness of the data should be ensured during the entry process.

[0044] The data processing module is a key link in the intelligent multi-dimensional university teaching quality improvement and evaluation system. It is responsible for receiving the original data from the data acquisition module and performing a series of processing operations on it to form a standardized and structured data set, providing a high-quality data foundation for subsequent intelligent analysis and strategy recommendation.

[0045] The data processing flow includes the following steps: A. Data reception: Receive raw data from the data collection module, including data on multiple dimensions such as student performance, teacher behavior, teaching resource utilization, and teaching environment.

[0046] B. Data preprocessing: 1. Data cleaning: Check the missing values, outliers, duplicate values, etc. in the data, and process them by filling, deleting, correcting, etc.

[0047] 2. Data conversion: convert unstructured or semi-structured data (such as text, images) into structured data (such as numerical data, categorical data, etc.).

[0048] 3. Data standardization: unify the format, unit, coding, etc. of data to ensure the comparability of data.

[0049] C. Data Integration: 1. Data association: According to the logical relationship of the data (such as time, student number, course number, etc.), the data from different data sources are associated and integrated.

[0050] 2. Data aggregation: Summarize and compile statistics of similar data to form a higher-level data view.

[0051] D. Data storage: Store the processed data in the database, establish a reasonable index and query mechanism, and improve data access efficiency.

[0052] E. Data optimization: 1. Data compression: Use data compression algorithm to reduce data storage space.

[0053] 2. Index construction: Create indexes for key fields in the database to improve query speed.

[0054] F. Data verification: Verify the data to ensure that the quality of the processed data meets the expected requirements.

[0055] Key technologies used A. Data cleaning technology: 1. Missing value processing: Use mean filling, mode filling, interpolation and other methods to handle missing values.

[0056] 2. Outlier detection: Use statistical methods (such as Z-score, IQR, etc.) or machine learning algorithms (such as isolation forest) to detect and handle outliers.

[0057] 3. Duplicate value processing: Identify and delete duplicate records by comparing multiple fields of data records.

[0058] B. Data conversion technology: 1. Text processing: Use natural language processing technology to perform operations such as word segmentation, stop word removal, and stem extraction on the text, and convert it into numerical or vectorized representation.

[0059] 2. Image recognition: Use computer vision technology to identify key information in images, such as student expressions, classroom environment, etc., and convert them into structured data.

[0060] C.Data standardization technology: 1. Unified format: Establish unified data format standards, such as date format, time format, numerical format, etc.

[0061] 2. Unit conversion: Convert data in different units to the same unit, such as converting temperature from Celsius to Fahrenheit.

[0062] D.Data integration technology: 1. Database connection: Use database connection tools (such as JDBC, ODBC) to connect to different database systems.

[0063] 2. Data extraction, transformation, loading (ETL): Automatically complete the data extraction, transformation and loading process through ETL tools.

[0064] E.Data storage and optimization technology: 1. Database design: Design a reasonable database table structure and index strategy based on data characteristics and query requirements.

[0065] 2. Data compression algorithm: Select a suitable compression algorithm, such as GZIP, LZ4, etc., to compress the stored data.

[0066] The intelligent analysis module is one of the core components of the intelligent multi-dimensional university teaching quality improvement and evaluation system. It uses advanced intelligent algorithms to conduct in-depth analysis of standardized and structured data sets processed by the data processing module, aiming to quantitatively evaluate teaching quality from multiple dimensions.

[0067] Intelligent analysis process: 1. Data preparation: Receive the standardized and structured data sets output by the data processing module, and perform necessary data cleaning and preprocessing to ensure that the data quality meets the analysis requirements.

[0068] Specifically, use Python's Pandas library to clean the data and write scripts to automate the processing flow.

[0069] 2. Feature extraction: Extract features that are valuable for teaching quality evaluation from the data set, such as course difficulty coefficient, student satisfaction score, frequency of teacher-student interaction, etc.

[0070] Specifically, according to teaching needs, key features such as student satisfaction, course participation, homework completion, etc. are determined, and the scikit-learn library is used for feature selection and preprocessing.

[0071] 3. Model selection: Select appropriate intelligent algorithms and models, such as decision trees, random forests, neural networks, etc., based on the evaluation objectives and data types.

[0072] For satisfaction and learning effectiveness evaluation, models such as random forest and gradient boosting tree can be used.

[0073] For the analysis of teacher-student interaction, time series analysis and natural language processing techniques can be combined.

[0074] Use frameworks such as TensorFlow or PyTorch to develop and train deep learning models.

[0075] 4. Model training: Use historical data and labeled samples to train the selected model, adjust model parameters, and optimize model performance.

[0076] 5. Evaluation execution: Apply the trained model to the current data set to perform a multi-dimensional quantitative evaluation of teaching quality.

[0077] 6. Result interpretation: Interpret and analyze the evaluation results to extract valuable information and insights to provide support for strategy recommendations and effect evaluation.

[0078] 7. Feedback optimization: Based on the evaluation results and actual effects, continuously optimize the model algorithm and evaluation process to improve analysis accuracy and efficiency.

[0079] In order to comprehensively and objectively evaluate the teaching quality, this program proposes the following three evaluation formulas and their advantages: A. Weighted average satisfaction evaluation formula , Where S is the total score of teaching quality satisfaction, n is the number of evaluation dimensions, wi is the weight of the i-th evaluation dimension, and si is the satisfaction score of the i-th evaluation dimension (which can be obtained through questionnaires, student feedback, etc.).

[0080] Advantages: This formula is simple and intuitive, and can comprehensively consider the impact of multiple evaluation dimensions. By adjusting the weights, it can flexibly reflect the importance of different dimensions. At the same time, the satisfaction score is easy to obtain and quantify, which facilitates statistical analysis and comparison.

[0081] In addition to the basic weighted average, a time decay factor can be introduced to take into account the greater impact of recent satisfaction ratings on the overall assessment.

[0082]

[0083] Where T is the current time, t i is the acquisition time of the i-th satisfactory reading score, and λ is the time decay coefficient.

[0084] Here are some ways to determine λ: Empirical method: Based on historical data and business experience, choose an appropriate lambda value. This usually requires adjustment through trial and error and observation of results.

[0085] You can start with a smaller λ value and gradually increase it to observe its impact on the overall evaluation until you find a satisfactory balance.

[0086] Data Analysis: Use statistical methods or machine learning models to predict or optimize the value of λ.

[0087] For example, you can analyze historical rating data to observe the changing trends of the overall evaluation under different λ values ​​and how these changes are related to business goals.

[0088] Expert consultation: Consult industry experts or professionals in the field to learn their views and recommendations on time decay coefficient.

[0089] A / B Testing: Conduct A / B testing in an actual business environment, compare the evaluation results under different λ values, and select the one with the best performance.

[0090] B. Learning Outcome Prediction Model A learning effectiveness prediction model is built based on machine learning (such as random forest, gradient boosting tree, etc.). The input features include students' basic level, learning engagement, teaching resource utilization rate, etc., and the output is the student's final exam score or learning effectiveness score.

[0091] Advantages: The model can use a large amount of historical data to learn the complex relationship between student performance and various factors in the learning process, and the prediction results are highly accurate and reliable. At the same time, the model can automatically adapt to data changes and continuously optimize prediction performance. In addition, by predicting learning outcomes, potential learning problems can be discovered in a timely manner, providing a basis for recommending personalized teaching strategies.

[0092] C. Teacher-student interaction quality evaluation index formula:

[0093] Among them, I is the teacher-student interaction quality evaluation index, C is the total number of teacher-student interactions, T is the total teaching time, Q is the number of high-quality interactions (such as in-depth discussions, effective questions, etc.), R is the interaction response speed (which can be measured by calculating the time interval from students asking questions to teachers answering), α and β are weight coefficients, which are adjusted according to teaching needs.

[0094] Advantages: The index comprehensively considers the frequency, quality and efficiency of teacher-student interaction, and can fully reflect the quality level of teacher-student interaction. By adjusting the weight coefficient, it can flexibly reflect the evaluation focus in different teaching scenarios. At the same time, the index is easy to calculate, implement and monitor, and can provide teachers with intuitive feedback on the quality of interaction, promoting the optimization and improvement of teaching interaction. Specific application of the evaluation formula: Weighted average satisfaction evaluation formula: This formula is suitable for comprehensive evaluation of the satisfaction of students, teachers and the course itself. In practical applications, the weights of each evaluation dimension can be flexibly set according to teaching needs and student feedback. For example, for courses that focus on teacher-student interaction, the weight of the teacher-student interaction dimension can be appropriately increased; for courses that emphasize learning outcomes, more attention can be paid to the scoring of the learning outcomes dimension.

[0095] Learning effectiveness prediction model: This model can be applied to predicting students' final exam scores, tracking learning progress, and identifying learning obstacles. By inputting students' basic information, learning behavior data, and teaching resource utilization, the model can predict students' future learning outcomes. This is of great significance for teachers to promptly identify learning problems, adjust teaching strategies, and provide personalized tutoring.

[0096] Teacher-student interaction quality evaluation index: This index can be used to monitor and evaluate the quality of classroom teaching. By counting indicators such as the number, quality, and response speed of teacher-student interactions, it can objectively reflect the teacher's interactive performance in classroom teaching. This index not only helps teachers reflect on themselves and improve their teaching level, but also provides strong decision-making support for teaching management departments.

[0097] In addition to the above formulas, a variety of evaluation formulas can be designed to quantify the teaching quality of different dimensions. These evaluation formulas can be customized according to specific teaching objectives and evaluation requirements. The following are some examples of evaluation formulas: D. Evaluation of teaching resource utilization efficiency: The utilization efficiency of teaching resources (such as textbooks, courseware, experimental equipment, etc.) can be evaluated based on factors such as the number of times resources are used, student satisfaction and resource costs.

[0098]

[0099] Among them, E is the efficiency of teaching resource utilization, U is the number of times the resource is used, S is the student satisfaction score with the resource (may need to be normalized), and C is the cost of the resource or the difficulty coefficient of obtaining it.

[0100] U (number of resource usage): can be automatically collected through teaching management systems, library borrowing records, experimental equipment usage records, etc.

[0101] S (student satisfaction score with resources): can be manually collected through questionnaires, online evaluation systems, etc., and then normalized.

[0102] C (cost or difficulty of obtaining the resource): This is usually a preset value that may be provided by the school's finance department or resource management department and may vary depending on the resource.

[0103] E. Student Learning Engagement Assessment: Assessing students' participation in the learning process can be based on student attendance, class interactions, assignment submissions, etc.

[0104]

[0105] Among them, P is the student learning participation, A is the attendance rate (expressed as a percentage), I is the number of classroom interactions (such as questions, answers, etc.), H is the number of homework submissions or quality scores (weighted processing may be required), and T is the total teaching time or total number of class hours.

[0106] A (Attendance rate): can be automatically collected through teaching management systems, classroom roll calls, etc.

[0107] I (number of classroom interactions): can be collected manually or automatically through classroom observation, interaction records in the teaching management system, etc.

[0108] H (number of homework submissions or quality scores): The homework submission status can be automatically collected through the teaching management system. The quality score may need to be given manually by the teacher or obtained through an automatic scoring system (such as automatic testing of programming homework).

[0109] T (total teaching time or total number of class hours): This is a preset value, usually determined according to the teaching plan or course outline.

[0110] F. Teaching content mastery assessment: The assessment of students’ mastery of teaching content can be based on their test scores, homework accuracy, project completion, etc.

[0111]

[0112] Among them, M is the mastery of teaching content, n is the number of assessment items (such as the number of tests, the number of homework, etc.), wi is the weight of the i-th assessment item, and si is the student's score on the i-th assessment item (which may need to be normalized).

[0113] n (number of assessment items): determined according to the teaching plan and assessment needs.

[0114] wi (the weight of the ith assessment item): set by the teaching management department or teacher based on the assessment objectives.

[0115] si (student’s score on the i-th assessment item): obtained through tests, assignments, projects, etc., which may require manual grading by teachers or obtained through an automatic grading system.

[0116] G. Evaluation of the effectiveness of teaching methods: The impact of teaching methods on students' learning outcomes can be evaluated based on changes in students' grades and learning motivation under different teaching methods.

[0117]

[0118] Among them, V is the teaching method effectiveness evaluation value (expressed in percentage), Ga is the average score of students after adopting the new method, and Gb is the average score of students before adopting the new method (or when adopting other methods). Note that this formula assumes that other conditions remain unchanged and only the teaching method has changed.

[0119] Ga (average score of students after adopting the new method): obtain the student scores after adopting the new method through the teaching management system or score statistics system, and calculate the average value.

[0120] Gb (average student scores before adopting the new method (or when other methods are adopted)): also obtained through the teaching management system or the score statistics system, but corresponds to the student scores before adopting the new method or when other methods are adopted.

[0121] H. Teaching environment satisfaction evaluation: Assessing students' satisfaction with the teaching environment can include aspects such as classroom facilities, learning atmosphere, and technical support.

[0122]

[0123] Among them, SE is the total score of satisfaction with the teaching environment, m is the number of evaluation dimensions (such as classroom facilities, learning atmosphere, technical support, etc.), wi is the weight of the i-th evaluation dimension, and si is the satisfaction score of the i-th evaluation dimension (which may need to be normalized).

[0124] m (number of evaluation dimensions): determined based on evaluation requirements.

[0125] wi (weight of the ith evaluation dimension): set by the teaching management department or teacher based on the evaluation objectives.

[0126] si (satisfaction score of the ith evaluation dimension): manually collected through questionnaires, online evaluation systems, etc., and normalized.

[0127] The technical effects and advantages of the above evaluation formula are mainly reflected in the following aspects: Technical Effects Objectivity and accuracy: The evaluation formula is based on a large amount of data input and the results are calculated through mathematical and statistical methods, which reduces the subjectivity and bias caused by human factors and improves the objectivity and accuracy of the evaluation.

[0128] Comprehensiveness and multi-dimensionality: The evaluation formula covers multiple dimensions such as the efficiency of teaching resource utilization, student learning participation, mastery of teaching content, effectiveness of teaching methods, and satisfaction with the teaching environment, and can comprehensively reflect different aspects of teaching quality.

[0129] Real-time and dynamic: Through real-time data collection of the data acquisition module and real-time tracking and evaluation of the effect evaluation module, the evaluation formula can dynamically reflect changes in teaching quality and provide a basis for teachers to adjust teaching strategies in a timely manner.

[0130] Predictive and forward-looking: Certain evaluation formulas, such as those based on students’ learning process and changes in academic performance, can not only evaluate the current teaching quality, but also predict future development trends, providing a reference for education administrators and teachers to formulate long-term teaching plans.

[0131] advantage Scientificity: The design of the evaluation formula is based on scientific educational theories and statistical principles, and can objectively and accurately reflect the actual situation of teaching quality.

[0132] Operability: The evaluation formula is simple and clear, easy to understand and operate. Through the automated processing of the data acquisition module and the data processing module, teachers can easily obtain the evaluation results and adjust the teaching strategy according to the results.

[0133] Targeted: The strategy recommendation module provides teachers with personalized teaching strategy recommendations based on the evaluation results. These recommendations are targeted and can help teachers better meet students’ learning needs and improve teaching quality.

[0134] Continuous improvement: The effect evaluation module tracks and evaluates the teaching effect after the implementation of the teaching strategy in real time, forming a closed-loop feedback mechanism. This mechanism helps teachers to continuously improve their teaching strategies and achieve continuous improvement in teaching quality.

[0135] Resource optimization: The evaluation formula can also help education administrators optimize resource allocation. For example, by evaluating the efficiency of teaching resource utilization, it is possible to discover bottlenecks and waste in resource use, and thus take measures to improve resource utilization efficiency.

[0136] Promoting educational equity: Through multi-dimensional teaching quality evaluation, we can find the learning differences and needs differences among different student groups. This helps education administrators and teachers take targeted measures to narrow the learning gap and promote educational equity.

[0137] 4. Strategy Recommendation Module As the core component of the intelligent multi-dimensional college teaching quality improvement and evaluation system, the strategy recommendation module mainly provides customized teaching strategy recommendations for teachers based on the teaching quality evaluation results provided by the intelligent analysis module, combined with the preset teaching quality improvement model and personalized teaching strategy library. This module aims to help teachers identify the advantages and disadvantages of the teaching process through scientific data analysis and intelligent algorithms, so as to adopt more effective teaching strategies and promote the continuous improvement of teaching quality.

[0138] The technical architecture of the strategy recommendation module mainly includes five parts: data source layer, strategy model layer, recommendation algorithm layer, strategy library management layer and interactive interface layer.

[0139] Data source layer: Receives teaching quality evaluation results from the intelligent analysis module, including but not limited to multi-dimensional evaluation data such as student satisfaction, learning outcomes, and teacher-student interaction quality. At the same time, this layer is also responsible for integrating auxiliary data such as teacher basic information, course characteristics, and student background to provide comprehensive support for strategy recommendations.

[0140] Strategy model layer: Build and maintain a teaching quality improvement model based on multidisciplinary theories such as pedagogy, psychology, statistics, and historical teaching data to form a scientific teaching strategy recommendation logic. The model associates the evaluation results with the preset teaching strategies to provide a decision-making basis for the recommendation algorithm.

[0141] Recommendation algorithm layer: Use advanced machine learning or deep learning algorithms to conduct in-depth analysis of the evaluation results, combined with the guidance of the strategy model layer, to generate personalized teaching strategy recommendations for teachers. The algorithm must be efficient, accurate, and highly interpretable to ensure the effectiveness and credibility of the recommendation results.

[0142] Strategy Library Management: Responsible for the construction, updating and maintenance of the teaching strategy library. The strategy library should contain a rich variety of teaching strategies, covering effective methods in different subjects, grades and teaching scenarios. The management needs to regularly evaluate the effectiveness of the strategy library and update and optimize it based on feedback from teaching practice.

[0143] Interactive interface layer: Provides a friendly user interface or API interface, allowing teachers to easily view the recommended teaching strategies and select and adjust them according to their own needs. At the same time, this layer is also responsible for collecting teachers' feedback on the recommended strategies, providing data support for the optimization of the strategy library and the improvement of the recommendation algorithm.

[0144] Strategy recommendation process: A. Data reception and preprocessing: Data source integration: Collect teaching quality evaluation data from multiple data sources (such as teaching management system, student evaluation system, teacher feedback system, etc.).

[0145] Data cleaning: Identify and handle missing values, outliers, duplicate data, and other issues to ensure data accuracy and completeness.

[0146] Data conversion: Convert data of different formats and standards into a unified format for subsequent processing and analysis.

[0147] Feature extraction: Extract key features from the raw data, such as student satisfaction, learning effectiveness improvement rate, number of interactions between teachers and students, etc. These features will serve as input for the recommendation algorithm.

[0148] Data standardization / normalization: The extracted features are standardized or normalized to eliminate the impact of different dimensions on the analysis results.

[0149] B. Strategy matching and screening Strategy library retrieval: Based on the extracted features, the strategy library is searched for potentially applicable teaching strategies, which usually involves comparing with the matching rules of the strategies in the strategy library.

[0150] Similarity calculation: Calculate the similarity between the current teaching situation and each strategy in the strategy library. Algorithms such as cosine similarity and Euclidean distance can be used.

[0151] Preliminary strategy screening: Based on the similarity calculation results, strategies with higher similarity are selected as candidate strategies. At the same time, further screening is carried out considering factors such as the applicability of the strategy, the teacher's personal style, and the characteristics of the course.

[0152] Strategy prioritization: Prioritize the selected strategies based on factors such as strategy effectiveness, implementation difficulty, and student acceptance.

[0153] C. Personalized recommendation generation Application of recommendation algorithm: Use personalized recommendation algorithms (such as collaborative filtering, content-based recommendation, hybrid recommendation, etc.) and combine factors such as teachers’ history teaching strategies, student feedback, and course progress to generate a personalized teaching strategy recommendation list.

[0154] Optimize recommendation results: Make fine adjustments to the recommendation results to ensure that the recommendation strategy not only meets the individual needs of teachers, but also effectively improves the teaching quality. This includes adjusting the expression of the recommendation strategy and providing implementation suggestions.

[0155] Recommendation result evaluation: After generating the recommendation results, the effectiveness and feasibility of the recommendation strategy are evaluated through simulation testing or expert review.

[0156] D. Recommendation result display and feedback Result visualization: The recommendation results are presented to teachers in the form of charts, lists, etc. to ensure that the information is intuitive and easy to read.

[0157] Detailed Description: Provide detailed descriptions and expected results for each recommended strategy to help teachers understand the reasons for the recommendation and how to implement it.

[0158] Feedback mechanism: Establish convenient feedback channels, such as online surveys, chatbots, etc., to encourage teachers to provide feedback after implementing recommended strategies.

[0159] Real-time update: Based on teachers’ feedback and actual evaluation results of teaching effectiveness, the recommendation results and strategy library are updated in real time to ensure the accuracy and timeliness of the recommendation system.

[0160] E. Strategy optimization and update Effect evaluation model: Build a scientific effect evaluation model to quantitatively evaluate the implementation effect of the recommended strategy, including collecting teaching effect data and analyzing data change trends.

[0161] Strategy optimization: Based on the evaluation results, the recommendation algorithm and strategy library are continuously optimized. Poorly performing strategies are improved or replaced; excellent strategies are promoted and reused.

[0162] Strategy library update: New teaching strategies are continuously introduced into the strategy library to enrich its diversity and adaptability. At the same time, outdated or ineffective strategies are cleaned up and eliminated.

[0163] Knowledge sharing and inheritance: Through internal training, experience sharing and other means, we promote the sharing and inheritance of teaching strategy knowledge and improve teachers' teaching level and quality.

[0164] 5. Effect Evaluation Module As the core component of the intelligent multi-dimensional university teaching quality improvement and evaluation system, the effect evaluation module aims to track and evaluate the teaching effect after the implementation of teaching strategies in real time, and provide feedback basis for the continuous optimization of the system.

[0165] In order to achieve the above goals, this module will adopt the following three main effect evaluation methods.

[0166] Method 1: Quantitative evaluation based on performance changes Implementation steps: Data collection: Use the data collection module to regularly collect data such as students' test scores, homework completion status, etc.

[0167] Data processing: The data processing module is used to clean and organize the data, calculate the mean, standard deviation and other statistics of the students' scores, and form a standardized data set.

[0168] Comparative analysis: Compare and analyze the students’ scores before and after the implementation of the teaching strategy, and calculate indicators such as the improvement in scores, pass rate, and excellent rate.

[0169] Result presentation: The evaluation results are presented in the form of charts to intuitively reflect the quantitative changes in teaching effectiveness.

[0170] Relationship with other modules: Data collection module: provides original data such as student scores.

[0171] Data processing module: processes the raw data to form analyzable data sets.

[0172] Intelligent Analysis Module: Although this method focuses on quantitative evaluation, the intelligent analysis module can provide support such as historical trend analysis and predictive analysis to help understand the deep-seated reasons behind changes in performance.

[0173] Strategy recommendation module: adjust teaching strategy recommendations based on performance improvement and provide targeted suggestions for weak links.

[0174] Method 2: Student feedback evaluation based on questionnaire survey Implementation steps: Questionnaire design: Design a questionnaire covering multiple dimensions including learning attitude, learning interest, teacher-student interaction, and satisfaction with teaching resources.

[0175] Data collection: Questionnaires are distributed to students online or offline, and the completed questionnaire data are collected.

[0176] Data processing and analysis: Use data analysis tools to conduct statistical analysis on questionnaire data and calculate satisfaction levels and improvement suggestions for each dimension.

[0177] Result feedback: The evaluation results will be summarized into a report and fed back to relevant teachers and administrators as a basis for adjusting teaching strategies.

[0178] Relationship with other modules: Data collection module: Although it does not directly collect questionnaire data, it provides demand input for questionnaire design to ensure the pertinence and effectiveness of the questionnaire content.

[0179] Data processing module: Process the questionnaire data and extract valuable information for analysis.

[0180] Intelligent analysis module: Through text analysis, sentiment analysis and other technologies, it deeply explores the key information in student feedback and provides in-depth insights for adjusting teaching strategies.

[0181] Strategy recommendation module: adjust teaching strategy recommendations and improve teaching quality based on student satisfaction feedback and improvement suggestions.

[0182] Method 3: Qualitative evaluation based on observation of teaching behavior Implementation steps: Observation design: Develop a detailed teaching behavior observation plan, clarify observation objectives, observation points, observation time, etc.

[0183] On-site observation: Organize professionals or teacher colleagues to enter the classroom to conduct field observations and record key behaviors and student reactions during the teaching process.

[0184] Behavioral analysis: Organize and analyze observation records, identify effective and ineffective teaching behaviors, and evaluate their impact on teaching effectiveness.

[0185] Feedback and suggestions: Feedback the analysis results to the observed teachers in written form and provide suggestions for improvement.

[0186] Relationship with other modules: Data collection module: Although it does not directly collect observation data, it provides teaching background and demand information for observation design.

[0187] Data processing module: Indirect association, because observation records may need to be sorted and analyzed to a certain extent.

[0188] Intelligent analysis module: Although this method focuses more on qualitative evaluation, the intelligent analysis module can provide support for data analysis techniques, such as behavioral pattern recognition and trend prediction.

[0189] Strategy recommendation module: Based on the results of qualitative evaluation, it provides teachers with more targeted teaching strategy recommendations, especially qualitative evaluation based on teaching behavior observation in terms of teaching method innovation and personalized teaching.

[0190] 4. Feedback loops and iterations Feedback mechanism: Establish a feedback mechanism to ensure that the observation results and suggestions can be conveyed to the observed teachers in a timely and accurate manner. At the same time, teachers are encouraged to put forward their own opinions and feedback to form a good atmosphere of two-way communication.

[0191] Iterative optimization: After the teacher adjusts the teaching strategy according to the feedback, the effect evaluation module needs to conduct a follow-up evaluation again to verify the improvement effect. Through multiple iterations, the teaching strategy is continuously optimized to achieve continuous improvement of teaching quality.

[0192] Relationship with other modules: Intelligent analysis module: Although qualitative evaluation mainly relies on manual observation and judgment, the intelligent analysis module can assist in data analysis, such as analyzing the text content of student feedback through natural language processing technology, extracting key opinions and suggestions, and providing data support for qualitative evaluation.

[0193] Strategy recommendation module: Qualitative evaluation results can often reveal deep-seated problems and individual needs in the teaching process. Based on these results, the strategy recommendation module can provide teachers with more accurate and personalized teaching strategy suggestions to promote innovation in teaching methods and the development of students' personalized learning.

Claims

1. An intelligent multi-dimensional university teaching quality improvement and evaluation system, characterized by: It includes data collection module, data processing module, intelligent analysis module, strategy recommendation module and effect evaluation module, among which, The data acquisition module is used to collect raw data from multiple dimensions during the teaching process; The data processing module is used to process the collected raw data to form a standardized and structured data set; The intelligent analysis module is used to apply intelligent algorithms to conduct in-depth analysis of processed data and conduct multi-dimensional quantitative evaluation of teaching quality; The strategy recommendation module is used to provide teachers with personalized teaching strategy recommendations based on analysis and evaluation results and the preset teaching quality improvement model; The effect evaluation module is used to track and evaluate the teaching effect after the implementation of the teaching strategy in real time.

2. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 1 is characterized in that: The data acquisition sources of the data acquisition module include student data, teacher data, teaching resource data and teaching environment data.

3. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 2 is characterized in that: The data acquisition method of the data acquisition module includes automatic acquisition and manual acquisition.

4. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 1 is characterized in that: The data processing flow of the data processing module includes the following steps: data reception, data preprocessing, data integration, data storage, data optimization and data verification.

5. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 1 is characterized in that: The intelligent analysis process of the intelligent analysis module includes data preparation, feature extraction, model selection, model training, evaluation execution, structure interpretation and feedback optimization.

6. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 5 is characterized in that: The intelligent evaluation of the intelligent analysis module includes at least one or more evaluations of the total score of teaching quality satisfaction, teacher-student interaction quality evaluation, teaching resource utilization efficiency evaluation, student learning participation evaluation, teaching content mastery evaluation, teaching method effectiveness evaluation, and teaching environment satisfaction evaluation.

7. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 6 is characterized in that: The evaluation formula for the total score of teaching quality satisfaction is: , Where S is the total score of teaching quality satisfaction, n is the number of evaluation dimensions, wi is the weight of the i-th evaluation dimension, and si is the satisfaction score of the i-th evaluation dimension.

8. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 6 is characterized in that: The teacher-student interaction quality evaluation formula is: , Where I is the teacher-student interaction quality evaluation index, C is the total number of teacher-student interactions, T is the total teaching time, Q is the number of high-quality interactions, R is the interaction response speed, and α and β are weight coefficients.

9. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 1 is characterized in that: The strategy recommendation process of the strategy recommendation module includes data reception and preprocessing, strategy matching and screening, personalized recommendation generation, recommendation result display and feedback, and strategy optimization and update.

10. The intelligent multi-dimensional university teaching quality improvement and evaluation system according to claim 1 is characterized in that: The effect evaluation module adopts a quantitative evaluation method based on performance changes, and the steps include: data collection, data processing, comparative analysis and result display; Or adopt student feedback evaluation based on questionnaire survey, the steps include: questionnaire design, data collection, data processing and analysis and result feedback.

Images