Digital teaching service method based on large model

Abstract

The invention belongs to the technical field of digital teaching, and particularly relates to a digital teaching service method based on a large model. Through cyclic feedback and continuous optimization, the teaching content can be adjusted according to the actual learning effect of the student, each knowledge point can be effectively taught, the overall teaching quality is improved, personalized teaching content and suggestions can be provided according to the learning behavior and the learning effect of each student by using a large model and data analysis, and the teaching efficiency is improved. The learning requirements of different students are met, the teaching duration is optimized according to the mastering condition of each knowledge point and the teaching duration score of the students, so that the students can master knowledge in the most suitable time, the learning efficiency is improved, the blindness and uncertainty in the teaching are reduced by collecting and analyzing a large amount of teaching data, and the learning efficiency is improved. The setting of the feedback period ensures the continuous improvement of the teaching content, enables the teaching process to be continuously optimized, and adapts to the continuously changing learning demands and environments of students.

Description

Technical Field

[0001] The invention belongs to the technical field of digital teaching, and in particular relates to a digital teaching service method based on a large model. Background Art

[0002] With the rapid development of information technology, digital teaching has become an important trend in the field of education. However, traditional digital teaching mainly relies on pre-made teaching courseware, videos and other resources, which often lack flexibility and interactivity and cannot meet the personalized needs of students. At the same time, traditional digital teaching methods lack real-time tracking and feedback on students' learning status, making it difficult to evaluate and optimize teaching results.

[0003] In recent years, in the modern education system, digital teaching has become an important means to promote educational reform and improve the quality of education. Big model technology has made significant progress in the field of artificial intelligence. Big models usually refer to deep learning models trained based on massive data, which have strong representation and generalization capabilities. In the field of education, big models can be applied to intelligent recommendation of teaching resources, personalized customization of teaching content, and intelligent management of teaching processes.

[0004] Although large model technology has broad application prospects in the field of education, existing technologies still have some shortcomings. Lack of comprehensive data collection and analysis of the entire teaching process makes it difficult to accurately evaluate the teaching quality and students' learning effects. Lack of flexibility makes it difficult to dynamically adjust teaching content and strategies based on real-time data, resulting in unsatisfactory teaching results. Summary of the invention

[0005] The purpose of the present invention is to provide a digital teaching service method based on a large model, which can be carried out more efficiently and personalized, thereby improving the teaching effect and the learning experience of students.

[0006] The technical solution adopted by the present invention is as follows:

[0007] A digital teaching service method based on a large model, comprising:

[0008] Collect digital teaching task data, and generate target teaching service content based on the digital teaching task data;

[0009] Construct a teaching service cycle and obtain the student class behavior data corresponding to each knowledge point in the target teaching service content within the teaching service cycle;

[0010] According to the students' class behavior data, the accuracy of the accompanying exercises corresponding to each knowledge point content is obtained, and the first element value of each knowledge point content is calculated according to the accuracy of the accompanying exercises;

[0011] According to the students' class behavior data, the teaching time score corresponding to each knowledge point is obtained, and the second factor value is calculated according to the teaching time score;

[0012] Obtain teaching quality scores based on the first factor value and the second factor value;

[0013] Determine whether the teaching quality score meets the preset requirements. If not, adjust the teaching time of the corresponding knowledge point content according to the teaching time score and generate new teaching service content;

[0014] Construct a feedback cycle, obtain the digital teaching task data collected during the feedback cycle and new teaching service content, and generate feedback teaching service content;

[0015] The feedback teaching service content is returned as the target teaching service content to the teaching service cycle, and the step of obtaining the student class behavior data corresponding to each knowledge point content in the corresponding target teaching service content within the teaching service cycle is performed.

[0016] In a preferred embodiment, the step of collecting digital teaching task data and generating target teaching service content according to the digital teaching task data includes:

[0017] Obtain syllabus and teaching objectives data;

[0018] Collect teaching-related data from multiple sources through the online platform according to the teaching syllabus and teaching objectives;

[0019] Extract key teaching requirements and objectives based on teaching-related data;

[0020] Based on the extracted teaching requirements and objectives, the target teaching service content is generated through the big model.

[0021] In a preferred solution, the step of constructing a teaching service cycle and obtaining the student class behavior data corresponding to each knowledge point in the target teaching service content corresponding to the teaching service cycle includes:

[0022] Get teaching schedule time;

[0023] According to the teaching plan time and the target teaching service content, obtain the teaching sequence of the knowledge points of the target teaching service content;

[0024] Obtain the current knowledge point teaching in the target teaching service content;

[0025] According to the current knowledge point teaching and the knowledge point teaching sequence, obtain the knowledge point teaching adjacent to the current knowledge point teaching;

[0026] Establish a teaching service cycle based on the current knowledge point teaching and the adjacent knowledge point teaching;

[0027] Obtain the student class behavior data corresponding to each knowledge point in the target teaching service content within the teaching service cycle.

[0028] In a preferred embodiment, the step of obtaining the accuracy of the accompanying practice questions corresponding to each knowledge point content according to the student's class behavior data, and calculating the first element value of each knowledge point content according to the accuracy of the accompanying practice questions includes:

[0029] Obtain the accuracy of the in-class exercises corresponding to each knowledge point based on the students' class behavior data;

[0030] According to the accuracy of the in-class exercise questions, the corresponding accuracy values ​​of multiple in-class exercise questions are obtained;

[0031] Get the first element function;

[0032] The accurate values ​​of multiple in-class exercise questions are input into the first element function, and the output result is marked as the first element value of the knowledge point content.

[0033] In a preferred embodiment, the step of obtaining the teaching time score corresponding to each knowledge point content according to the student's class behavior data, and calculating the second factor value according to the teaching time score includes:

[0034] Obtain the teaching time evaluation direction of the knowledge point content, where the teaching evaluation direction includes fast teaching time evaluation and slow teaching time evaluation;

[0035] According to the quick evaluation of teaching time, multiple corresponding quick scores of teaching time are obtained;

[0036] According to the teaching time slow evaluation, multiple corresponding teaching time slow scores are obtained;

[0037] Get the second factor function;

[0038] A plurality of fast teaching time ratings and a plurality of slow teaching time ratings are input into the second factor function, and the output result is marked as the second factor value.

[0039] In a preferred embodiment, the step of obtaining the teaching quality score according to the first factor value and the second factor value includes:

[0040] Obtain the frequency of student interaction on corresponding knowledge points based on student class behavior data;

[0041] Obtain the corresponding interaction weight coefficient according to the interaction frequency of students;

[0042] Get the scoring function;

[0043] The interaction weight coefficient, the first factor value and the second factor value are input into the scoring function, and the output result is marked as the teaching quality score.

[0044] In a preferred embodiment, the step of obtaining the corresponding interaction weight coefficient according to the interaction frequency of the trainees includes:

[0045] Obtaining an interaction compensation table, wherein the interaction compensation table includes a plurality of student interaction evaluation interval frequencies and an interaction weight coefficient corresponding to each student interaction evaluation interval frequency;

[0046] Obtain the corresponding target student interaction evaluation interval frequency according to the student interaction frequency;

[0047] Obtain the corresponding interaction weight coefficient from the interaction compensation table according to the target student's interaction evaluation interval frequency.

[0048] In a preferred embodiment, the step of judging whether the teaching quality score meets the preset requirements, and if not, adjusting the teaching time of the corresponding knowledge point content according to the teaching time score, and generating new teaching service content, includes:

[0049] Get the standard teaching quality score threshold;

[0050] Determine whether the teaching quality score exceeds the standard teaching quality score threshold;

[0051] If the teaching quality score does not exceed the standard teaching quality score threshold, it is determined that the teaching of the knowledge point corresponding to the teaching quality score does not meet the teaching needs and is marked as a target knowledge point;

[0052] If the teaching quality score exceeds the standard teaching quality score threshold, it is determined that the teaching of the knowledge point corresponding to the teaching quality score meets the teaching needs;

[0053] Obtain the teaching time score corresponding to the target knowledge point, adjust the teaching time according to the teaching time score, and generate new teaching service content.

[0054] In a preferred embodiment, the steps of obtaining the teaching time score corresponding to the target knowledge point, adjusting the teaching time according to the teaching time score, and generating new teaching service content include:

[0055] Obtain multiple fast teaching time scores and multiple slow teaching time scores corresponding to the target knowledge point, and respectively summarize the multiple fast teaching time scores and the multiple slow teaching time scores to obtain a fast teaching time score set and a slow teaching time score set;

[0056] Determine the size of the fast teaching time scoring set and the slow teaching time scoring set;

[0057] If the set of fast teaching time scores is greater than the set of slow teaching time scores, it indicates that the teaching time corresponding to the target knowledge point is fast, and the teaching time of the target knowledge point is extended, and new teaching service content is generated;

[0058] If the fast teaching time score set is smaller than the slow teaching time score set, it indicates that the teaching time corresponding to the target knowledge point is slow, and the teaching time of the target knowledge point is shortened, and new teaching service content is generated.

[0059] And, a digital teaching service method terminal based on a large model, comprising:

[0060] one or more processors;

[0061] a storage device having one or more programs stored thereon;

[0062] When the one or more programs are executed by the one or more processors, the one or more processors implement the large model-based digital teaching service method.

[0063] The technical effects achieved by the present invention are:

[0064] The present invention can adjust the teaching content according to the actual learning effect of the students through cyclic feedback and continuous optimization, ensure that each knowledge point can be effectively taught, and improve the overall teaching quality. By using large models and data analysis, personalized teaching content and suggestions can be provided according to the learning behavior and learning effect of each student to meet the learning needs of different students. The teaching time can be optimized according to the students' mastery of each knowledge point and the teaching time score, so that the students can master the knowledge in the most suitable time and improve the learning efficiency. By collecting and analyzing a large amount of teaching data, more scientific and accurate teaching decisions can be made, reducing the blindness and uncertainty in teaching. The setting of the feedback cycle ensures the continuous improvement of the teaching content, and continuously optimizes the teaching process to adapt to the students' changing learning needs and environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a flow chart of the method provided by the present invention. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0068] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0069] Secondly, the present invention is described in detail in conjunction with schematic diagrams. When describing the embodiments of the present invention in detail, for the convenience of explanation, the schematic diagrams are only examples and should not limit the scope of protection of the present invention.

[0070] Please see attached Figure 1 As shown, a digital teaching service method based on a large model is provided, including:

[0071] S1. Collect digital teaching task data and generate target teaching service content based on the digital teaching task data;

[0072] S2. Construct a teaching service cycle and obtain the student class behavior data corresponding to each knowledge point in the target teaching service content within the teaching service cycle;

[0073] S3, obtaining the accuracy of the accompanying exercises corresponding to each knowledge point content according to the students' class behavior data, and calculating the first element value of each knowledge point content according to the accuracy of the accompanying exercises;

[0074] S4. Obtain the teaching time score corresponding to each knowledge point content according to the students' class behavior data, and calculate the second factor value according to the teaching time score;

[0075] S5. Obtaining a teaching quality score according to the first factor value and the second factor value;

[0076] S6. Determine whether the teaching quality score meets the preset requirements. If not, adjust the teaching time of the corresponding knowledge point content according to the teaching time score, and generate new teaching service content;

[0077] S7, building a feedback cycle, obtaining the digital teaching task data collected within the feedback cycle and new teaching service content, and generating feedback teaching service content;

[0078] S8, returning the feedback teaching service content as the target teaching service content to the teaching service cycle, and obtaining the student class behavior data corresponding to each knowledge point in the target teaching service content within the teaching service cycle.

[0079] As in the above steps S1 to S8, various data related to teaching are collected, such as course content, student information, learning objectives, etc., and the initial target teaching service content is generated. These data can come from the student's learning history, learning preferences, course requirements, and online teaching videos, etc., to determine a teaching service cycle, and obtain the student's class behavior data during this cycle. These data are related to the content of each knowledge point in the course. The behavior data includes the student's participation, learning progress, interaction, etc. The student's mastery of each knowledge point is evaluated based on the student's accuracy in the accompanying exercises, and the accuracy of each knowledge point is calculated accordingly. The first factor value, the accuracy of the exercise questions reflects the students' understanding and mastery of the knowledge point. The rationality of the teaching time is evaluated through the students' learning time and teaching time scores on each knowledge point, and the second factor value is calculated. The teaching time score reflects whether the current teaching time is suitable for the students' learning needs. Combining the first and second factor values, the overall teaching quality score is calculated. This score comprehensively reflects the students' mastery of the knowledge points and the rationality of the teaching time, and judges whether the teaching quality score meets the preset requirements. If the score does not meet the standard, the teaching time of each knowledge point is adjusted according to the teaching time score to generate a new The teaching service content is collected again to further optimize the teaching process. In the feedback cycle, the digital teaching task data and new teaching service content are collected again to generate feedback teaching service content. The purpose of the feedback cycle is to continuously optimize the teaching content based on the new data, take the feedback teaching service content as the new target teaching service content, return to the construction step of the teaching service cycle, and re-acquire the students' class behavior data. This cyclic process continuously optimizes the teaching service and improves the teaching quality. Through cyclic feedback and continuous optimization, the teaching content can be adjusted according to the actual learning effect of the students to ensure that each knowledge point can be effectively taught and improve the overall teaching quality. By using large models and data analysis, personalized teaching content and suggestions can be provided according to the learning behavior and learning effect of each student to meet the learning needs of different students. According to the students' mastery of each knowledge point and the teaching time score, the teaching time is optimized so that students can master the knowledge in the most suitable time and improve learning efficiency. By collecting and analyzing a large amount of teaching data, more scientific and accurate teaching decisions can be made to reduce the blindness and uncertainty in teaching. The setting of the feedback cycle ensures the continuous improvement of the teaching content and the continuous optimization of the teaching process to adapt to the students' changing learning needs and environment.

[0080] In a specific embodiment, the step of collecting digital teaching task data and generating target teaching service content according to the digital teaching task data includes:

[0081] S101, obtaining teaching syllabus and teaching objective data;

[0082] S102. Collect teaching-related data from multiple sources through a network platform based on the teaching syllabus and teaching objective data;

[0083] S103. Extract key teaching requirements and objectives based on teaching-related data;

[0084] S104. Generate target teaching service content through a large model based on the extracted teaching requirements and objectives.

[0085] As in the above steps S101 to S104, first, the core content is obtained from the syllabus and teaching objectives, which include the overall structure of the course, the specific objectives of each unit or chapter, knowledge points and expected learning outcomes. These data are usually provided by educational institutions or teaching designers and are the basis for formulating teaching plans. Network platforms, such as educational resource websites, online libraries, teaching video platforms, etc., are used to collect data related to teaching content from multiple sources. These data may include textbooks, academic articles, teaching videos, courseware, exercise banks, etc. Through multi-channel collection, the richness and diversity of teaching content are ensured. The collected data is processed and analyzed to extract key teaching requirements and objectives related to the syllabus and objectives. This step usually requires Natural language processing (NLP) technology is used to identify and extract important information from texts, such as knowledge points, core concepts, skill requirements, etc. Based on the extracted teaching requirements and goals, the big model is used to generate specific target teaching service content, which includes generating detailed teaching plans, course content, learning activities, evaluation methods, etc. The big model can automatically generate structured and personalized teaching content based on the key requirements and goals input. The big model refers to an advanced machine learning model used to analyze and process large amounts of teaching data. It is usually a neural network model based on deep learning. These models can process complex data sets and extract meaningful features and rules from them, thereby supporting in-depth analysis and prediction of teaching content, teaching strategies, and student behavior. Using multi-layer neural networks The data is processed and analyzed through the network, such as convolutional neural network (CNN), recurrent neural network (RNN) or transformer (Transformers), which can process a large amount of teaching-related data, including student behavior data, course content data, teaching resource data, etc., and has the ability to predict student learning effects, analyze teaching quality and optimize teaching content. Through continuous feedback and training, the model can continuously optimize itself to provide more accurate analysis and prediction results. The collected teaching objectives, teaching outlines, course content, teaching resources and assessment standard data are analyzed through the large model to extract key teaching requirements and objectives, analyze student class behavior data, extract effective behavioral characteristics and rules, calculate teaching quality scores, and Optimize teaching content and strategies based on the results. By using big models, it is possible to more accurately identify and meet teaching needs, improve teaching effectiveness and students' learning experience. Automated data collection and content generation greatly reduce the time and energy of manually organizing and writing teaching content, making the teaching design process more efficient. By collecting data from multiple sources, the comprehensiveness and diversity of teaching content are ensured, making teaching materials richer and more substantial to meet the learning needs of different students. Big models can generate personalized teaching content according to different teaching requirements and goals, ensuring that each knowledge point can be explained in detail to adapt to different teaching situations and student needs. By extracting key teaching requirements and goals, the teaching content generated by the big model can quickly adapt to different teaching outlines and goals.With high flexibility and adaptability, the generated target teaching service content can more accurately reflect the teaching syllabus and objectives, ensure the scientificity and systematicness of the teaching content, improve the overall teaching quality, and use big data and big model technology to make the teaching design process more scientific and data-driven, reducing subjectivity and arbitrariness, and enhancing the reliability and effectiveness of teaching content.

[0086] In a specific embodiment, the step of constructing a teaching service cycle and obtaining the student class behavior data corresponding to each knowledge point content in the target teaching service content corresponding to the teaching service cycle includes:

[0087] S201, obtaining teaching plan time;

[0088] S202, according to the teaching plan time and the target teaching service content, obtaining the teaching sequence of knowledge points of the target teaching service content;

[0089] S203, obtaining the current knowledge point teaching in the target teaching service content;

[0090] S204, obtaining knowledge point teaching adjacent to the current knowledge point teaching according to the current knowledge point teaching and the knowledge point teaching sequence;

[0091] S205, establishing a teaching service cycle according to the current knowledge point teaching and the adjacent knowledge point teaching;

[0092] S206: Obtain the student's class behavior data corresponding to each knowledge point in the target teaching service content corresponding to the teaching service cycle.

[0093] As in the above steps S201 to S206, first, determine the time schedule of the entire teaching plan, including the start time, end time, and teaching time period of each knowledge point of the course. The goal of this step is to clarify the time frame of the teaching activities, and clarify the teaching order of each knowledge point based on the teaching plan time and the target teaching service content. This means knowing the sequence of each knowledge point in the entire teaching process to provide a basis for the subsequent arrangement of teaching activities. In the actual teaching process, obtain the current ongoing knowledge point teaching content, which includes the specific knowledge points and their teaching activities involved in the current class. According to the current knowledge point teaching and its position in the knowledge point teaching sequence, obtain the knowledge point teaching content adjacent to the current knowledge point teaching. According to the time and content arrangement of the current knowledge point teaching and the adjacent knowledge point teaching, establish a teaching service cycle. This cycle can be a class hour, a unit, or a specific time period, depending on the teaching arrangement. During the teaching service cycle, students' class behavior data on various knowledge points are collected. These data may include students' attendance, participation, interaction, homework completion, test scores, etc. Through clear teaching plan time and knowledge point teaching sequence, teachers can accurately grasp the teaching progress, ensure that each knowledge point is taught at the right time, obtain the teaching content of current and adjacent knowledge points, help teachers optimize teaching arrangements, ensure the connection and coherence of knowledge points, and avoid gaps or repetitions in knowledge point teaching. Based on students' class behavior data, teachers can understand students' mastery of current knowledge points in real time, adjust teaching strategies, and improve the pertinence and effectiveness of teaching. Detailed students' class behavior data are collected to support data-driven teaching decisions. Teachers can adjust teaching content and methods based on data to improve teaching effectiveness. By optimizing the teaching service cycle, teachers can ensure the reasonable arrangement of knowledge point teaching, improve students' learning experience and participation, and promote better learning results.

[0094] In a specific embodiment, the step of obtaining the accuracy of the accompanying practice questions corresponding to each knowledge point content according to the student's class behavior data, and calculating the first element value of each knowledge point content according to the accuracy of the accompanying practice questions includes:

[0095] S301, obtaining the accuracy of the in-class exercises corresponding to each knowledge point content according to the student's class behavior data;

[0096] S302, obtaining corresponding accuracy values ​​of multiple in-class exercise questions according to the accuracy of the in-class exercise questions;

[0097] S303, obtaining a first element function;

[0098] S304, inputting the accurate values ​​of a plurality of accompanying exercise questions into the first element function, and marking the output result as the first element value of the knowledge point content.

[0099] As in the above steps S301 to S304, based on the students' class behavior data, the accuracy of the accompanying exercises corresponding to each knowledge point content is extracted. These accuracy data reflect the students' performance in the exercises and indicate their understanding and mastery of the knowledge point. For each knowledge point content, the accuracy values ​​corresponding to multiple accompanying exercises are collected. These data points may come from multiple exercises, tests at different time points, or the grades of different students. The function used to calculate the first factor value, i.e., the first factor function, is determined. The function may be a predefined mathematical formula or algorithm for integrating multiple accuracy values ​​into a comprehensive evaluation value. The first factor function is In the formula, Y represents the first factor value, U represents the accuracy value of the accompanying exercises, n represents the total number of the accuracy values ​​of the accompanying exercises, and i represents the number of the accuracy values ​​of the accompanying exercises. The collected accuracy values ​​of multiple accompanying exercises are input into the first factor function, and the result is calculated and output. The result is the first factor value of the content of the knowledge point, which represents the students' mastery of the knowledge point. By analyzing the accuracy of multiple accompanying exercises, it is possible to more comprehensively evaluate the students' mastery of each knowledge point and avoid the one-sidedness of the evaluation of a single exercise question. Multiple accuracy values ​​are integrated to provide more scientific and objective evaluation indicators to support teachers in making teaching decisions based on data. By calculating the first factor value, teachers can promptly discover students' learning difficulties in certain knowledge points and adjust the teaching content and methods in a targeted manner to help students improve their learning effects. According to the first factor value, teachers can evaluate the effectiveness of teaching content and methods, optimize teaching design, and improve teaching quality. Through data analysis and accurate evaluation, teachers can more effectively guide students to learn and improve learning effects and efficiency.

[0100] In a specific embodiment, the step of obtaining the teaching time score corresponding to each knowledge point content according to the student's class behavior data, and calculating the second factor value according to the teaching time score includes:

[0101] S401, obtaining a teaching time evaluation direction of a knowledge point content, wherein the teaching evaluation direction includes a fast teaching time evaluation and a slow teaching time evaluation;

[0102] S402, obtaining corresponding multiple teaching time quick scores according to the teaching time quick evaluation;

[0103] S403, obtaining corresponding multiple teaching time slow scores according to the teaching time slow evaluation;

[0104] S404, obtaining a second factor function;

[0105] S405. Input a plurality of fast teaching time scores and a plurality of slow teaching time scores into the second factor function, and mark the output result as the second factor value.

[0106] As in the above steps S401 to S405, the evaluation direction of the teaching time of the knowledge point content is determined, including the fast evaluation of the teaching time and the slow evaluation of the teaching time, which means that the teaching time is divided into two types: fast and slow, so as to more specifically evaluate the rationality of the teaching time. According to the fast evaluation of the teaching time, a plurality of fast teaching time scores are collected. These scores can come from the feedback of the students on whether the teaching time is too fast, such as questionnaires, classroom performance, test scores, etc. According to the slow evaluation of the teaching time, a plurality of slow teaching time scores are collected. These scores can come from the feedback of the students on whether the teaching time is too slow, which can also be obtained in a variety of ways. The function used to calculate the second factor value, that is, the second factor function, is determined. The function can be a predefined mathematical model or algorithm for integrating the fast score and the slow score into a comprehensive evaluation value. The second factor function is In the formula, E represents the second factor value, K represents the fast score of teaching time, L represents the slow score of teaching time, m represents the total number of fast scores of teaching time and the total number of slow scores of teaching time, and h represents the number of fast scores of teaching time and the number of slow scores of teaching time. The collected multiple fast scores and slow scores of teaching time are input into the second factor function, and the results are calculated and output. The result is the second factor value, which represents the rationality of teaching time and the adaptability of students. By dividing the teaching time into fast and slow directions for evaluation, the rationality of teaching time can be evaluated more comprehensively, ensuring that the teaching time of each knowledge point is appropriate and in line with the learning rhythm of students. The fast scores and slow scores are integrated to provide scientific and objective evaluation. The value indicator supports teachers to adjust teaching time based on data and improve teaching effect. By calculating the value of the second factor, teachers can promptly discover unreasonable teaching time and adjust teaching strategies in a targeted manner to ensure that students can keep up with the teaching progress. According to the value of the second factor, teachers can optimize the teaching process, reasonably allocate the teaching time of each knowledge point, avoid teaching time that is too fast or too slow, and improve the overall teaching quality. Accurate teaching time evaluation helps to provide teaching arrangements that are more in line with students' learning needs, enhance students' learning experience, and promote better learning effects. Through data analysis and precise evaluation, teachers can manage teaching time more effectively, improve teaching efficiency, and ensure that each knowledge point can be fully understood and mastered by students.

[0107] In a specific embodiment, the step of obtaining the teaching quality score according to the first factor value and the second factor value includes:

[0108] S501, obtaining the student interaction frequency of corresponding knowledge points according to the student class behavior data;

[0109] S502, obtaining a corresponding interaction weight coefficient according to the interaction frequency of the trainees;

[0110] S503, obtaining a scoring function;

[0111] S504: Input the interaction weight coefficient, the first factor value and the second factor value into the scoring function, and mark the output result as the teaching quality score.

[0112] As in the above steps S501 to S504, the student interaction frequency corresponding to each knowledge point is obtained based on the student's class behavior data, which includes the number of times the student asks questions, answers questions, participates in discussions, etc. in class. These data reflect the student's participation and initiative. The interaction weight coefficient is calculated based on the student's interaction frequency. The interaction weight coefficient is used to measure the importance of the interaction frequency in the overall teaching quality score. The weight coefficient can be set according to actual needs. For example, high-frequency interaction may indicate better participation and understanding. A function for calculating the teaching quality score, i.e., a scoring function, is determined. The function can be a predefined mathematical model or algorithm for integrating the interaction weight coefficient, the first factor value, and the second factor value into a comprehensive score. The scoring function is P=B×Y×E, where P represents the teaching quality score, B represents the interaction weight coefficient, Y represents the first factor value, and E represents the second factor value. The weight coefficient, the first factor value and the second factor value are input into the scoring function, and the result is calculated and output. The result is the teaching quality score, which represents the overall teaching effect and quality. By comprehensively considering the frequency of student interaction, the first factor value and the second factor value, a comprehensive teaching quality evaluation indicator is provided, which reflects the influence of various important factors in the teaching process, integrates various factors, and provides scientific and objective evaluation indicators to support teachers to improve and optimize teaching based on data and improve teaching effectiveness. By incorporating the frequency of student interaction into the evaluation system, students are encouraged to actively participate in classroom interaction and enhance learning experience and learning effects. According to the teaching quality score, teachers can identify the advantages and disadvantages of the teaching process, optimize teaching design and strategies, and improve the overall teaching quality. Through data analysis and precise evaluation, teachers can manage the teaching process more effectively, improve teaching efficiency, and ensure that every knowledge point can be fully understood and mastered by students.

[0113] In a specific embodiment, the step of obtaining the corresponding interaction weight coefficient according to the interaction frequency of the trainees includes:

[0114] S5021, obtaining an interaction compensation table, wherein the interaction compensation table includes a plurality of student interaction evaluation interval frequencies and an interaction weight coefficient corresponding to each student interaction evaluation interval frequency;

[0115] S5022. Obtain the corresponding target student interaction evaluation interval frequency according to the student interaction frequency;

[0116] S65023. Obtain the corresponding interaction weight coefficient from the interaction compensation table according to the target student's interaction evaluation interval frequency.

[0117] As in the above steps S5021 to S5023, an interaction compensation table is established to define multiple student interaction evaluation interval frequencies and the interaction weight coefficient corresponding to each interval. The interaction compensation table can be set according to historical data, teaching experience or specific teaching needs. Each interval represents an interaction frequency within a certain range. For example, 0-5 interactions, a weight coefficient of 0.5, 6-10 interactions, a weight coefficient of 0.7, etc. Each interval corresponds to a weight coefficient, which is used to reflect the degree of influence of the frequency on the teaching quality. According to the actual interaction frequency of the students, the interaction evaluation interval frequency of the target students is determined. For example, if the interaction frequency of a student at a certain knowledge point is 7 times, then the frequency of the evaluation interval may be 6-10 times. According to the interaction evaluation interval frequency of the target students, the corresponding interaction weight coefficient of 0.7 is obtained from the interaction compensation table. The weight coefficient reflects the influence of the student's interaction frequency on the teaching quality. The relative importance in the quality score can be reflected more accurately by setting up an interaction compensation table to convert the students' interaction frequency into a specific weight coefficient, which can reflect the impact of students' participation on teaching quality. The interaction compensation table can be adjusted according to different teaching needs and student characteristics to achieve personalized evaluation and weight setting, and adapt to different teaching scenarios. By using the interaction weight coefficient, teachers can improve teaching based on data, adjust teaching strategies, improve students' participation and overall teaching effectiveness, incorporate students' interaction frequency into the evaluation system, encourage students to actively participate in classroom interaction, and improve learning experience and effectiveness. According to the changes in the interaction weight coefficient, teachers can optimize teaching design, arrange teaching activities reasonably, and promote students' active participation and interaction. By comprehensively considering students' interaction frequency and other factors, the teaching quality can be comprehensively evaluated, a scientific evaluation basis can be provided, and the overall teaching quality and students' learning experience can be improved.

[0118] In a specific embodiment, the step of judging whether the teaching quality score meets the preset requirements, and if not, adjusting the teaching time of the corresponding knowledge point content according to the teaching time score, and generating new teaching service content, includes:

[0119] S601, obtaining a standard teaching quality scoring threshold;

[0120] S602, determining whether the teaching quality score exceeds the standard teaching quality score threshold;

[0121] If the teaching quality score does not exceed the standard teaching quality score threshold, it is determined that the teaching of the knowledge point corresponding to the teaching quality score does not meet the teaching needs and is marked as a target knowledge point;

[0122] If the teaching quality score exceeds the standard teaching quality score threshold, it is determined that the teaching of the knowledge point corresponding to the teaching quality score meets the teaching needs;

[0123] S603: Obtain the teaching time score corresponding to the target knowledge point, adjust the teaching time according to the teaching time score, and generate new teaching service content.

[0124] As in the above steps S601 to S603, a standard teaching quality score threshold is set, which represents the minimum acceptable teaching quality level, which can be determined by historical data, teaching objectives or educational standards. If the teaching quality score does not exceed the standard threshold, it is determined that the teaching of the knowledge point does not meet the teaching needs, and the knowledge point is marked as a target knowledge point. If the teaching quality score exceeds the standard threshold, it is determined that the teaching of the knowledge point meets the teaching needs. For the content marked as the target knowledge point, the corresponding teaching time score is obtained, and the teaching time of the knowledge point is adjusted according to the score. For example, if the score shows that the teaching time is too short, the teaching time is extended; if it is too long, the teaching time is shortened, and the teaching time is adjusted according to the adjusted teaching time. The duration generates new teaching service content. By setting and comparing standard thresholds, it can ensure that the teaching quality of all knowledge points reaches the preset minimum standard, thereby ensuring the overall teaching quality. According to the feedback of teaching quality scores and teaching duration scores, the teaching duration and content are dynamically adjusted to make teaching more adaptive and flexible, meet the learning needs of different students, make reasonable adjustments to the teaching duration, avoid waste and uneven distribution of teaching resources, and improve the utilization efficiency of teaching resources. By adjusting the teaching duration, it ensures that students have enough time to understand and master each knowledge point, thereby improving learning effects. Through data analysis and feedback, teachers can obtain specific information about teaching quality and duration, guide teaching improvements, and improve teaching effects and quality.

[0125] In a specific embodiment, the steps of obtaining the teaching time score corresponding to the target knowledge point, adjusting the teaching time according to the teaching time score, and generating new teaching service content include:

[0126] S6031, obtaining multiple fast teaching time scores and multiple slow teaching time scores corresponding to the target knowledge point, and summarizing the multiple fast teaching time scores and the multiple slow teaching time scores respectively to obtain a fast teaching time score set and a slow teaching time score set;

[0127] S6032, determining the size of the fast teaching time scoring set and the slow teaching time scoring set;

[0128] If the set of fast teaching time scores is greater than the set of slow teaching time scores, it indicates that the teaching time corresponding to the target knowledge point is fast, and the teaching time of the target knowledge point is extended, and new teaching service content is generated;

[0129] If the teaching time score set is smaller than the teaching time score set, it indicates that the teaching time corresponding to the target knowledge point is slow, and the teaching time of the target knowledge point is shortened, and new teaching service content is generated.

[0130] As in the above steps S6031 to S6032, multiple fast teaching time scores and multiple slow teaching time scores corresponding to the target knowledge point are collected, and these scores are summarized to obtain two sets: a fast teaching time score set and a slow teaching time score set. If the total score of the fast teaching time score set is greater than the total score of the slow teaching time score set, it indicates that the teaching time of the target knowledge point is short, so the teaching time of the target knowledge point is extended, and new teaching service content is generated. If the total score of the fast teaching time score set is less than the total score of the slow teaching time score set, it indicates that the target knowledge point is short. If the teaching time is long, the teaching time of the target knowledge point will be shortened, and new teaching service content will be generated. By analyzing the teaching time speed score in detail, the teaching time can be adjusted more accurately to ensure that the teaching time of each knowledge point meets the students' learning needs. Specific scoring data will be used for adjustments to make teaching improvements based on evidence, improve the scientificity and accuracy of teaching decisions, dynamically adjust the teaching time based on students' feedback, optimize the teaching process, improve teaching efficiency and quality, and adjust the teaching time to ensure that students have appropriate time to study each knowledge point, thereby improving students' learning experience and effectiveness.

[0131] And, a digital teaching service method terminal based on a large model, comprising:

[0132] one or more processors;

[0133] a storage device having one or more programs stored thereon;

[0134] When the one or more programs are executed by the one or more processors, the one or more processors implement the large model-based digital teaching service method.

[0135] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A digital teaching service method based on a large model, characterized in that: include: Collect digital teaching task data, and generate target teaching service content based on the digital teaching task data; Construct a teaching service cycle and obtain the student class behavior data corresponding to each knowledge point in the target teaching service content within the teaching service cycle; Obtain the accuracy of the accompanying exercises corresponding to each knowledge point content according to the students' class behavior data, and calculate the first element value of each knowledge point content according to the accuracy of the accompanying exercises; According to the students' class behavior data, the teaching time score corresponding to each knowledge point is obtained, and the second factor value is calculated according to the teaching time score; Obtain teaching quality scores based on the first factor value and the second factor value; Determine whether the teaching quality score meets the preset requirements. If not, adjust the teaching time of the corresponding knowledge point content according to the teaching time score and generate new teaching service content; Construct a feedback cycle, obtain the digital teaching task data collected during the feedback cycle and new teaching service content, and generate feedback teaching service content; The feedback teaching service content is returned as the target teaching service content to the teaching service cycle, and the step of obtaining the student class behavior data corresponding to each knowledge point content in the corresponding target teaching service content within the teaching service cycle is performed.

2. The digital teaching service method based on a large model according to claim 1 is characterized in that: The step of collecting digital teaching task data and generating target teaching service content according to the digital teaching task data includes: Obtain syllabus and teaching objectives data; Collect teaching-related data from multiple sources through the online platform according to the teaching syllabus and teaching objectives; Extract key teaching requirements and objectives based on teaching-related data; Based on the extracted teaching requirements and objectives, the target teaching service content is generated through the big model.

3. The digital teaching service method based on a large model according to claim 1 is characterized in that: The step of constructing a teaching service cycle and obtaining the student's class behavior data corresponding to each knowledge point in the target teaching service content corresponding to the teaching service cycle includes: Get teaching schedule time; According to the teaching plan time and the target teaching service content, obtain the teaching sequence of the knowledge points of the target teaching service content; Obtain the current knowledge point teaching in the target teaching service content; According to the current knowledge point teaching and the knowledge point teaching sequence, obtain the knowledge point teaching adjacent to the current knowledge point teaching; Establish a teaching service cycle based on the current knowledge point teaching and the adjacent knowledge point teaching; Obtain the student class behavior data corresponding to each knowledge point in the target teaching service content within the teaching service cycle.

4. The digital teaching service method based on a large model according to claim 1 is characterized in that: The step of obtaining the accuracy of the accompanying practice questions corresponding to each knowledge point content according to the student's class behavior data, and calculating the first element value of each knowledge point content according to the accuracy of the accompanying practice questions includes: Obtain the accuracy of the in-class exercises corresponding to each knowledge point based on the students' class behavior data; According to the accuracy of the in-class exercise questions, the corresponding accuracy values ​​of multiple in-class exercise questions are obtained; Get the first element function; The accurate values ​​of multiple in-class exercise questions are input into the first element function, and the output result is marked as the first element value of the knowledge point content.

5. The digital teaching service method based on a large model according to claim 1 is characterized in that: The step of obtaining the teaching time score corresponding to each knowledge point content according to the student's class behavior data, and calculating the second factor value according to the teaching time score includes: Obtain the teaching time evaluation direction of the knowledge point content, where the teaching evaluation direction includes fast teaching time evaluation and slow teaching time evaluation; According to the quick evaluation of teaching time, multiple corresponding quick scores of teaching time are obtained; According to the teaching time slow evaluation, multiple corresponding teaching time slow scores are obtained; Get the second factor function; A plurality of fast teaching time ratings and a plurality of slow teaching time ratings are input into the second factor function, and the output result is marked as the second factor value.

6. The digital teaching service method based on a large model according to claim 1 is characterized in that: The step of obtaining the teaching quality score according to the first factor value and the second factor value includes: Obtain the frequency of student interaction on corresponding knowledge points based on student class behavior data; Obtain the corresponding interaction weight coefficient according to the interaction frequency of students; Get the scoring function; The interaction weight coefficient, the first factor value and the second factor value are input into the scoring function, and the output result is marked as the teaching quality score.

7. The digital teaching service method based on a large model according to claim 1 is characterized in that: The step of obtaining the corresponding interaction weight coefficient according to the interaction frequency of the trainees includes: Obtaining an interaction compensation table, wherein the interaction compensation table includes a plurality of student interaction evaluation interval frequencies and an interaction weight coefficient corresponding to each student interaction evaluation interval frequency; Obtain the corresponding target student interaction evaluation interval frequency according to the student interaction frequency; Obtain the corresponding interaction weight coefficient from the interaction compensation table according to the target student's interaction evaluation interval frequency.

8. The digital teaching service method based on a large model according to claim 1 is characterized in that: The step of judging whether the teaching quality score meets the preset requirements, and if not, adjusting the teaching time of the corresponding knowledge point content according to the teaching time score, and generating new teaching service content, includes: Get the standard teaching quality score threshold; Determine whether the teaching quality score exceeds the standard teaching quality score threshold; If the teaching quality score does not exceed the standard teaching quality score threshold, it is determined that the teaching of the knowledge point corresponding to the teaching quality score does not meet the teaching needs and is marked as a target knowledge point; If the teaching quality score exceeds the standard teaching quality score threshold, it is determined that the teaching of the knowledge point corresponding to the teaching quality score meets the teaching needs; Obtain the teaching time score corresponding to the target knowledge point, adjust the teaching time according to the teaching time score, and generate new teaching service content.

9. The digital teaching service method based on a large model according to claim 8 is characterized in that: The steps of obtaining the teaching time score corresponding to the target knowledge point, adjusting the teaching time according to the teaching time score, and generating new teaching service content include: Obtain multiple fast teaching time scores and multiple slow teaching time scores corresponding to the target knowledge point, and respectively summarize the multiple fast teaching time scores and the multiple slow teaching time scores to obtain a fast teaching time score set and a slow teaching time score set; Determine the size of the fast teaching time scoring set and the slow teaching time scoring set; If the set of fast teaching time scores is greater than the set of slow teaching time scores, it indicates that the teaching time corresponding to the target knowledge point is fast, and the teaching time of the target knowledge point is extended, and new teaching service content is generated; If the fast teaching time score set is smaller than the slow teaching time score set, it indicates that the teaching time corresponding to the target knowledge point is slow, and the teaching time of the target knowledge point is shortened, and new teaching service content is generated.

10. A digital teaching service method terminal based on a large model, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the large model-based digital teaching service method described in any one of claims 1-9.

Images