Integrated English teaching method and system based on artificial intelligence

Abstract

The invention relates to the technical field of intelligent education, and discloses an integrated English teaching method and system based on artificial intelligence. The method comprises the following steps: constructing a digital resource library; generating pre-class preview data based on the resource library and the initial cognitive level of the student, analyzing the pre-class preview data and updating the cognitive level; generating classroom courseware based on the resource library and the student updating cognitive level, and analyzing classroom learning data to update the cognitive level again; generating personalized after-class homework based on the resource library and the re-updated cognitive level of the student, and analyzing homework data to finally update the cognitive level; and forming a heavy and difficult comment report based on the resource library and the final cognitive level of the student. Through continuous data collection and analysis, dynamic adjustment of teaching content is realized, pre-class preview, classroom teaching and after-class review are closely combined to form a complete teaching closed loop, teaching pertinence and effectiveness are improved, personalized learning and precise teaching are realized, and the overall effect of English teaching is greatly improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent education technology, and in particular to the field of English teaching technology based on artificial intelligence. Background Art

[0002] With the rapid development of educational informatization, the application of artificial intelligence technology in the field of education is becoming more and more extensive. Especially in English teaching, traditional teaching methods can no longer meet the needs of modern education. At present, English teaching faces many challenges and urgently needs innovative solutions.

[0003] First, traditional English teaching often adopts a unified teaching schedule and content, which is difficult to meet the individual needs of different students. Each student has different learning foundations, learning abilities and learning styles. A unified teaching method will inevitably lead to some students finding it difficult to learn, while others find the course content too simple. This "one-size-fits-all" teaching method not only reduces learning efficiency, but may also dampen students' enthusiasm for learning.

[0004] Secondly, teachers invest a lot of time and energy in lesson preparation, teaching, and assessment, but the results are often unsatisfactory. Teachers need to prepare a variety of teaching materials for students of different levels, design classroom activities, assign homework, and correct it. This heavy workload not only consumes teachers' energy, but also limits their ability to focus on individual students' needs.

[0005] Third, existing teaching evaluation methods are often outdated and not comprehensive enough. Usually, teachers can only understand students’ learning situation through midterm and final exams, and it is difficult to find and solve problems in the learning process in a timely manner. This outdated evaluation method is not conducive to students adjusting their learning strategies in a timely manner, and it also makes it difficult for teachers to improve their teaching methods in a targeted manner.

[0006] In addition, although there are various digital learning resources on the market, how to effectively integrate and utilize these resources is still a challenge. Teachers and students are often at a loss when faced with a huge amount of learning materials and find it difficult to find the most suitable learning content. This not only wastes precious educational resources, but also reduces learning efficiency.

[0007] Finally, existing teaching methods lack the ability to adjust dynamically. Once a teaching plan is formulated, it is often difficult to adjust it in a timely manner according to the students' actual learning situation. This rigid teaching model cannot adapt to changes in the students' learning process and it is difficult to provide a continuously optimized learning experience.

[0008] In the face of these challenges, there is an urgent need for an innovative teaching method that can achieve personalized learning, improve teaching efficiency, evaluate learning outcomes in real time, efficiently utilize educational resources, and dynamically adjust teaching content. Summary of the invention

[0009] The purpose of this application is to provide an integrated English teaching method and system based on artificial intelligence to solve the problems raised in the above background technology.

[0010] The present application discloses an integrated English teaching method based on artificial intelligence, comprising the following steps:

[0011] Step A: Build a digital resource library;

[0012] Step B: Based on the main text of the textbook, the digital resource library and the initial cognitive level of the teaching group on the course knowledge, generate the pre-class preview materials with the highest matching degree with each knowledge point of the main text from the pre-class preview material library; collect and analyze the students' learning data on the pre-class preview materials, and update the cognitive level of the teaching group on the course knowledge;

[0013] Step C: Based on the main text, the digital resource library and the updated teaching group's cognitive level of course knowledge, generate classroom courseware with the highest matching degree with each knowledge point of the main text from the knowledge point explanation courseware library; collect and analyze students' learning data on the classroom courseware, and update the teaching group's cognitive level of course knowledge again;

[0014] Step D: Based on the main text, the digital resource library and the updated teaching group's cognitive level of course knowledge, generate homework with the highest matching degree with each knowledge point of the main text from the question bank; collect and analyze students' learning data on the homework, and finally update the teaching group's cognitive level of course knowledge;

[0015] Step E: Based on the knowledge point domain and the final cognitive level of the teaching group on the course knowledge, determine the weak knowledge points of the teaching group, and form a review report on key and difficult points based on the weak knowledge points to dynamically adjust the teaching content.

[0016] Step F: Use the cognitive level of each knowledge point of the teaching group in the learning situation analysis report as the initial cognitive level of the next teaching session, and execute steps B to F in a loop.

[0017] In a preferred example, the digital resource library includes a knowledge point library, a text material library, a pre-class preview material library, a knowledge point explanation courseware library and a test question library, wherein the knowledge point library contains the mastery requirements of each knowledge point in the teaching stage;

[0018] In a preferred example, in step B, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the initial cognitive level of the teaching group on the course knowledge, a preview material content generation model is used to generate the pre-class preview material with the highest matching degree with the main text from the pre-class preview material library, wherein the preview material content generation model is as follows:

[0019]

[0020] in,

[0021] F1 is the matching result between the preview materials and the main text.

[0022] a and b are the number of thematic knowledge points in the preview materials and the main text respectively.

[0023] Min(a,b) is the number of common subject knowledge points between the two.

[0024] Max(a,b) is the maximum number of subject knowledge points between the two.

[0025] E c is the mastery requirement of the cth theme knowledge point in the main text, and the value is divided into three levels according to the mastery requirement: e c ′、e c ″、e c ''', and e c ′>e c > c '''>0.

[0026] K dx is the average frequency of the dth subject knowledge point in the preview material in professional direction x.

[0027] K ex is the average frequency of the e-th theme knowledge point in the main text in professional direction x.

[0028] N1 is the sum of the frequencies of all knowledge points under professional direction x.

[0029] n is the total number of teaching groups.

[0030] m is the total number of knowledge points contained in the main text.

[0031] R 1i , R 2i , R m′i are the initial cognitive levels of the ith student for the 1st, 2nd, and m′th knowledge points respectively.

[0032] Z r The length of the audio and video materials of the preview content in the preview materials.

[0033] Z r ' is the preset threshold for the duration of the audio and video materials of the preview content.

[0034] T r It is the number of words in the text of the preview content in the preview materials.

[0035] T r ′ is the preset threshold of the text length of the preview material.

[0036] S r is the number of exercises in the preview homework in the preview materials.

[0037] S r ′ is the threshold value of the number of exercises in the preview materials.

[0038] α1, α2, α3, ε1, ε2, ε3, μ1, μ2, μ m ,∈1,∈2,∈3 are weight coefficients.

[0039] In a preferred example, in step C, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the updated cognitive level of the teaching group on the course knowledge, a classroom courseware content generation model is used to generate classroom courseware with the highest matching degree with each knowledge point of the main text from the knowledge point explanation courseware library, wherein the design of the classroom courseware content generation model is as follows:

[0040]

[0041] in,

[0042] F2 is the calculation result of the matching degree between the knowledge point courseware and the main text.

[0043] E1, E2, E m′ They are the mastery requirements for the 1st, 2nd and m′ knowledge points of the main text respectively. The values ​​are divided into three levels according to the mastery requirements: e′, e″, e''', and e′>e″>e'''>0.

[0044] Com1, Com2, Comm′ are respectively the degree of detail of the explanation of the 1st, 2nd, and m′th knowledge points in the main text in each knowledge point courseware (the degree of detail can be evaluated from the knowledge point's phonetic symbols, word meanings, usages, examples, etc.).

[0045] K 1y The average frequency of the first knowledge point in the main text in professional direction y.

[0046] K Com1y It is the average frequency of the knowledge point in the knowledge point courseware in professional direction y.

[0047] N2 is the sum of the frequencies of all knowledge points under professional direction y.

[0048] K 2z The average frequency of the second knowledge point in the main text in professional direction z.

[0049] K Com2z It is the average frequency of the knowledge point in the knowledge point courseware in professional direction z.

[0050] N3 is the sum of the frequencies of all knowledge points under professional direction z.

[0051] K m′j is the average frequency of the m′th knowledge point in the main text in professional direction j.

[0052] K Comm′j It is the average frequency of the knowledge point in the knowledge point courseware in professional direction j.

[0053] Nm is the sum of the frequencies of all knowledge points under professional direction j.

[0054] n is the total number of teaching groups.

[0055] m is the total number of knowledge points contained in the main text.

[0056] R′ 1i , R′ 2i , R′ m′i They are respectively the cognitive levels of the 1st, 2nd, and m′th knowledge points after the ith student has previewed the content.

[0057] β1, β2, θ1, θ2, θ m ,π1,π2, ∝1, ∝2, is the weight coefficient.

[0058] In a preferred example, in step D, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the updated cognitive level of the teaching group on the course knowledge, the homework content generation model is used to generate the homework with the highest matching degree with each knowledge point of the main text from the question library, wherein the homework content generation model is designed as follows:

[0059]

[0060] in,

[0061] F3 is the calculation result of the matching degree between the after-class exercises and the main text.

[0062] p is the total number of important and difficult knowledge points in the main text.

[0063] p′ is the number of difficult and important knowledge points in the after-class exercises that are the same as those in the main text.

[0064] E q is the mastery requirement of the qth same difficult knowledge point, and the value is divided into three levels according to the mastery requirement: e q ′、e q ″、e q ''', and e q ′>e q > q '''>0.

[0065] u is the total number of general knowledge points in the main text.

[0066] u′ is the number of general knowledge points in the after-class exercises that are the same as those in the main text.

[0067] E v is the mastery requirement of the vth same general knowledge point, and the value is divided into three levels according to the mastery requirement: e v ′、e v ″、e v ''', and e v ′>e v > v '''>0.

[0068] n is the total number of teaching groups.

[0069] m is the total number of knowledge points contained in the main text.

[0070] R1' i ′、R 2i '′, R m ' ′ ' i They are respectively the cognitive levels of the 1st, 2nd, and m′th knowledge points of the ith student after studying the classroom courseware.

[0071] s means that the exercise is the sth question that contains a certain difficult knowledge point.

[0072] S′ is the preset threshold for the number of questions for each difficult knowledge point.

[0073] t means that the exercise is the tth question that contains a general knowledge point.

[0074] T′ is the preset threshold for the number of questions for each general knowledge point.

[0075] γ1, γ2, γ3, γ4, δ1, δ2, ω1, ω2, σ1, σ2, σ m , τ1, τ2 are weight coefficients.

[0076] In a preferred example, in step E, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the final cognitive level of the teaching group on the course knowledge, the learning situation analysis and key and difficult point review model is used to diagnose the weak knowledge points of the teaching group and form a key and difficult point review report, wherein the learning situation analysis and key and difficult point review model is designed as follows:

[0077] (4)

[0079] in,

[0080] F4 is the result of the learning situation analysis.

[0081] W1, W2, W m′ They are the mastery requirements for the 1st, 2nd, and m′ knowledge points in this teaching stage respectively. The values ​​are divided into three levels according to the mastery requirements: w′, w″, and w’’’, and w′>w″>w’’’>0.

[0082] n is the total number of teaching groups.

[0083] m is the total number of knowledge points contained in the main text.

[0084] R 1i ''′、R2' i '′, R m ' ′i '' are the cognitive levels of the 1st, 2nd, and m′th knowledge points after the i-th student completes his homework; ρ1, ρ2, ρ m is the weight coefficient.

[0085] In a preferred example, the preview material content generation model, classroom courseware content generation model, after-class homework content generation model and learning situation analysis and key points review model are all content generation models based on artificial intelligence. The method updates the cognitive level of different teaching links by real-time analysis of student learning data, and dynamically adjusts the teaching content to achieve personalized learning and precise teaching.

[0086] The present application also discloses an integrated English teaching system based on artificial intelligence, comprising:

[0087] A digital resource library construction module is used to construct a digital resource library;

[0088] A pre-class preview material generation module is used to generate pre-class preview materials with the highest matching degree with each knowledge point of the main text from the pre-class preview material library based on the main text of the textbook, the digital resource library and the initial cognitive level of the teaching group on the course knowledge;

[0089] The first data collection and analysis module is used to collect and analyze students' learning data on the pre-class preview materials and update the teaching group's cognitive level of course knowledge;

[0090] A classroom courseware generation module is used to generate classroom courseware with the highest matching degree with each knowledge point of the main text from the knowledge point explanation courseware library according to the main text, based on the digital resource library and the updated teaching group's cognitive level of course knowledge;

[0091] The second data collection and analysis module is used to collect and analyze students' learning data on the classroom courseware, and to update the teaching group's cognitive level of the course knowledge again;

[0092] A homework generation module is used to generate homework with the highest matching degree with each knowledge point of the main text from the digital resource library based on the mastery requirements of each knowledge point of the teaching stage in the digital resource library and the cognitive level of the teaching group on the course knowledge after being updated again according to the main text;

[0093] The third data collection and analysis module is used to collect and analyze students' learning data on the homework, and finally update the teaching group's cognitive level of course knowledge;

[0094] A learning situation analysis module is used to determine the weak knowledge points of the teaching group based on the main text, the digital resource library and the final cognitive level of the teaching group on the course knowledge, and to form a review report on key and difficult points based on the weak knowledge points, so as to dynamically adjust the teaching content;

[0095] A loop execution module is used to use the cognitive level of each knowledge point of the teaching group in the learning situation analysis report as the initial cognitive level of the next teaching link, and to loop the functions of the pre-class preview material generation module to the learning situation analysis module.

[0096] The present application also discloses an integrated English teaching system based on artificial intelligence, comprising:

[0097] a memory for storing computer executable instructions; and,

[0098] A processor is used to implement the steps in the method described above when executing the computer executable instructions.

[0099] The present application also discloses a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the steps in the method described above are implemented.

[0100] The implementation methods of this application have the following technical effects:

[0101] The integrated English teaching method based on artificial intelligence has brought remarkable technical effects and comprehensively improved the quality and efficiency of English teaching. The most notable feature of this method is that it realizes the whole process of intelligent teaching from pre-class preparation to after-class homework. By continuously collecting and analyzing student data, the system can dynamically adjust the teaching content in real time to ensure the consistency and pertinence of the teaching process. This method not only improves learning effects, but also greatly reduces the workload of teachers.

[0102] The construction of a digital resource library provides a solid foundation for this teaching method. It contains comprehensive teaching resources, including knowledge point library, text material library, pre-class preview material library, knowledge point explanation courseware library and test question library. In particular, the knowledge point library contains the requirements for mastering knowledge points at each teaching stage, ensuring that the teaching content always complies with the syllabus. The application of the preview material content generation model makes the pre-class preview more targeted and greatly improves the preview effect.

[0103] In the entire classroom teaching process, for the pre-class stage, the system first dynamically generates preview materials based on the students' initial cognitive situation. The preview material content generation model ensures that the materials are highly relevant to the course content, which is conducive to improving the effectiveness and efficiency of students' preview. For the in-class stage, the system dynamically generates classroom courseware based on the students' preview situation. The classroom courseware content generation model ensures a high degree of match between the courseware and the text, making the teaching content more in line with students' needs, which greatly improves the pertinence and efficiency of classroom teaching. For the after-class stage, the system generates personalized homework based on the classroom learning situation. The after-class homework content generation model ensures that the homework covers all important knowledge points, improving the pertinence and effectiveness of after-class exercises.

[0104] Learning situation analysis is another important feature of this teaching method. Through learning situation analysis and the key and difficult points review model, the system can accurately diagnose students' weaknesses, provide teachers with reliable data support, and help achieve precise teaching. This not only achieves closed-loop optimization of the teaching process, but also provides a reliable basis for teaching decisions.

[0105] In addition, this method also includes supplementary learning and loop optimization mechanisms. The system will provide supplementary learning materials for the weak knowledge points detected to enhance the learning effect. By looping the teaching process, the teaching quality is continuously improved, ensuring the continuity and systematicness of the teaching process.

[0106] The application of artificial intelligence models is the core of this teaching method. AI technology is used to realize the intelligent generation and optimization of teaching content, and through real-time data analysis, personalized learning and precise teaching are truly realized. This not only greatly improves teaching efficiency and learning effects, but also provides innovative solutions for modern education.

[0107] In general, the integrated English teaching solution based on artificial intelligence proposed in this application is expected to comprehensively improve the quality and efficiency of English teaching through intelligent content generation, real-time data analysis and dynamic adjustment mechanism, and bring revolutionary changes to modern English education. This integrated English teaching method based on artificial intelligence has the characteristics of comprehensiveness, personalization, precision and dynamism. It not only improves teaching efficiency, but also realizes the efficient use of teaching resources. Through continuous data-driven and optimization, this method has the potential to completely change the traditional teaching model and bring revolutionary changes to English education.

[0108] A large number of technical features are recorded in the specification of this application, which are distributed in various technical solutions. If all possible combinations of technical features of this application (i.e., technical solutions) are to be listed, the specification will be too long. In order to avoid this problem, the various technical features disclosed in the above-mentioned invention content of this application, the various technical features disclosed in the various embodiments and examples below, and the various technical features disclosed in the accompanying drawings can be freely combined with each other to form various new technical solutions (these technical solutions are all deemed to have been recorded in this specification), unless the combination of such technical features is technically infeasible. For example, in one example, feature A+B+C is disclosed, and in another example, feature A+B+D+E is disclosed, and features C and D are equivalent technical means that play the same role. Technically, only one can be used, and it is impossible to use them at the same time. Feature E can be combined with feature C technically. Then, the solution of A+B+C+D should not be deemed to have been recorded because it is technically infeasible, and the solution of A+B+C+E should be deemed to have been recorded. BRIEF DESCRIPTION OF THE DRAWINGS

[0109] Figure 1 It is a flowchart of an integrated English teaching method based on artificial intelligence according to the first implementation mode of the present application.

[0110] Figure 2 It is a schematic diagram of the process of generating content for each teaching link of a course in an integrated English teaching method based on artificial intelligence according to the first embodiment of the present application.

[0111] Figure 3 It is an overall schematic diagram of an integrated English teaching system based on artificial intelligence according to the second implementation mode of the present application.

[0112] Figure 4 It is a structural diagram of an integrated English teaching system based on artificial intelligence according to the second implementation mode of the present application. DETAILED DESCRIPTION

[0113] In the following description, many technical details are provided to help readers better understand the present application. However, those skilled in the art can understand that the technical solution claimed in the present application can be implemented even without these technical details and various changes and modifications based on the following embodiments.

[0114] Description of some concepts:

[0115] Digital resource library: In this application, it refers to a database containing a variety of teaching resources, including, optionally, a knowledge point library, a text material library, a pre-class preparation material library, a knowledge point explanation courseware library and a test question library, which are used to support each teaching link before, during and after class.

[0116] Knowledge point library: In this application, it refers to a digital library that stores knowledge points at different teaching stages and marks the teaching stage and mastery requirements of each knowledge point (such as mastering the application, understanding the instructions, and recognizing and understanding different levels).

[0117] Text material library: In this application, it refers to a digital library that collects and stores a large number of different types of text materials, and optionally marks the theme knowledge points, key and difficult knowledge points and general knowledge points in the materials.

[0118] Pre-class preparation material library: In this application, it refers to a digital library that collects and stores various pre-class preparation materials such as audio, video, and text, and optionally marks the subject knowledge points, important and difficult knowledge points, and general knowledge points.

[0119] Knowledge point explanation courseware library: In this application, it refers to a digital library that stores the explanation courseware of each knowledge point, which may optionally include analysis content such as phonetic symbols, word meanings, usage, examples, etc.

[0120] Question Bank: In this application, it refers to a digital library that stores a large number of test questions of different types and optionally annotates the knowledge points in the test questions.

[0121] Pre-class preparation material content generation model: In this application, it refers to an artificial intelligence-based model used to generate pre-class preparation materials that best match the course textbook content from a pre-class preparation material library.

[0122] Classroom courseware content generation model: In this application, it refers to an artificial intelligence-based model that is used to generate classroom courseware that best matches the course material content from a knowledge point explanation courseware library.

[0123] Homework content generation model: In this application, it refers to an artificial intelligence-based model used to generate homework covering all knowledge points in the course textbook content from a question bank.

[0124] Learning situation analysis and key points review model: In this application, it refers to an artificial intelligence-based model used to analyze students' learning situation, diagnose the weak knowledge points of the teaching group, and generate learning situation analysis reports and key points review reports.

[0125] Initial cognitive level: In this application, it refers to the students' initial understanding and mastery of course knowledge before studying a course.

[0126] Teaching group: In this application, it refers to a group of students participating in course learning, whose learning data and cognitive level serve as the basis for analyzing and generating teaching materials.

[0127] Teaching sessions: In this application, it refers to the different stages of a course, including pre-class preparation, classroom teaching, and post-class review.

[0128] Course material content: In this application, it refers to the main text and related knowledge points that need to be learned in the textbook.

[0129] Real-time analysis: In this application, it refers to the immediate collection and processing of data generated by students during the learning process in order to adjust the teaching content based on the latest data.

[0130] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0131] The first implementation mode of the present application relates to an integrated English teaching method based on artificial intelligence, the process of which is as follows: Figure 1 and Figure 2 As shown, the method comprises the following steps:

[0132] Step 100: construct a digital resource library, which includes a knowledge point library, a text material library, a pre-class preparation material library, a knowledge point explanation courseware library and a test question library, wherein the knowledge point library contains the mastery requirements of each knowledge point in this teaching stage.

[0133] Specifically, in step 100, a comprehensive digital resource library is first constructed to support all aspects of English teaching. This resource library consists of five main parts: knowledge point library, text material library, pre-class preparation material library, knowledge point explanation courseware library and test question library.

[0134] The knowledge point library is the core part of the digital resource library. It contains the knowledge points that need to be mastered at each teaching stage, and details the mastery requirements of each knowledge point. These mastery requirements are usually divided into several levels, such as mastering application, understanding instructions and cognition, to ensure that the teaching content can meet the learning needs of different levels.

[0135] The textbook material library collects and stores a large number of textbook materials, which are classified and labeled to indicate the subject knowledge points, key and difficult knowledge points, and general knowledge points contained therein. In this way, when selecting textbook materials, teachers can quickly find content that meets the teaching objectives.

[0136] The pre-class preview material library contains various types of preview materials, including audio and video materials, text materials, etc. These materials are classified and labeled to ensure that students can access materials that are highly relevant to the course content when they preview before class, thereby improving the effectiveness and efficiency of the preview.

[0137] The Knowledge Point Explanation Courseware Library is a resource library specifically used for classroom teaching, which contains detailed explanations of each knowledge point. These explanations include phonetic symbols, word meanings, usages, examples, etc., to help teachers explain knowledge points more effectively in class and improve students' understanding and mastery.

[0138] The question bank contains a large number of exercises that are carefully designed and categorized to cover all important knowledge points. The questions in the question bank can be used for homework and tests to help students consolidate what they have learned and provide teachers with tools to evaluate students' learning effects.

[0139] By building such a comprehensive digital resource library, we can greatly improve the efficiency of teaching resources, ensure the comprehensiveness and systematicness of teaching content, and provide a solid foundation for subsequent teaching links. This not only improves the pertinence and effectiveness of teaching, but also enables personalized learning and precision teaching, ultimately improving the overall effect of English teaching.

[0140] Step 200: Based on the main text of the textbook, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the initial cognitive level of the teaching group on the course knowledge, a pre-class preview material content generation model is used to generate the pre-class preview material with the highest matching degree with the main text from the pre-class preview material library.

[0141] Optionally, the design of the preview material content generation model is as follows:

[0142]

[0143] in,

[0144] F1 is the matching result between the preview materials and the main text.

[0145] a and b are the number of thematic knowledge points in the preview materials and the main text respectively.

[0146] Min(a,b) is the number of common subject knowledge points between the two.

[0147] Max(a,b) is the maximum number of subject knowledge points between the two.

[0148] E c is the mastery requirement of the cth theme knowledge point in the main text, and the value is divided into three levels according to the mastery requirement: e c ′、e c ″、e c ''', and e c ′>e c > c '''>0.

[0149] K dx is the average frequency of the dth subject knowledge point in the preview material in professional direction x.

[0150] K ex is the average frequency of the e-th theme knowledge point in the main text in professional direction x.

[0151] N1 is the sum of the frequencies of all knowledge points under professional direction x.

[0152] n is the total number of teaching groups.

[0153] m is the total number of knowledge points contained in the main text.

[0154] R 1i , R 2i , R m′i are the initial cognitive levels of the ith student for the 1st, 2nd, and m′th knowledge points respectively.

[0155] Z r The length of the audio and video materials of the preview content in the preview materials.

[0156] Z r ' is the preset threshold for the duration of the audio and video materials of the preview content.

[0157] T r It is the number of words in the text of the preview content in the preview materials.

[0158] T r ′ is the preset threshold of the text length of the preview material.

[0159] S r is the number of exercises in the preview homework in the preview materials.

[0160] S r ′ is the threshold value of the number of exercises in the preview materials.

[0161] α1, α2, α3, ε1, ε2, ε3, μ1, μ2, μ m ,∈1,∈2,∈3 are weight coefficients.

[0162] Specifically, the key to step 200 is to use the preview material content generation model to generate the preview material with the highest matching degree with the main text from the pre-class preview material library based on the main text of the textbook, combined with the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the initial cognitive level of the teaching group on the course knowledge. Specifically, this step is to ensure that the preview material is highly relevant to the content of the textbook, thereby improving the effectiveness and pertinence of the preview.

[0163] In the above formula, F1 is the matching result between the preview material and the main text. To calculate this matching result, the model considers several factors:

[0164] Number of knowledge points and matching degree: a and b represent the number of thematic knowledge points in the preview materials and the main text, respectively. The matching degree between the two is evaluated by calculating the number of the same thematic knowledge points and the maximum number of thematic knowledge points through Min(a,b) and Max(a,b), respectively.

[0165] Knowledge point mastery requirements: E c Indicates the requirements for mastering the cth topic knowledge point in the main text, which is divided into three levels: e c ′、e c ″、e c ''', and e c ′>e c > c '''>0. This parameter is used to evaluate students' mastery of different knowledge points during the preview stage.

[0166] Frequency Analysis: K dx and K ex Respectively represent the frequency of occurrence of a certain knowledge point in the preview material and the main text in a specific professional direction x, while N1 represents the total frequency of all knowledge points in this professional direction. Through the ratio of these frequencies, the model can evaluate the matching degree of the preview material in the professional background.

[0167] Students' initial cognitive level: R 1i , R 2i , R m′i They represent the initial cognitive level of the ith student on the 1st, 2nd and m′th knowledge points respectively. These data reflect the students’ understanding of each knowledge point before previewing, and can help the model generate preview materials that are more in line with the students’ actual situation.

[0168] Preview material features: Z r Indicates the duration of audio and video materials in the preview materials, T r The number of words representing the length of the text, S r Represents the number of exercises. The corresponding Z r ′、Tr ′、S r ′ is the preset threshold of these characteristics. Through these ratios, the model can control the content and form of the preview materials to ensure that they are within a reasonable range.

[0169] The above model takes these factors into consideration and generates the preview materials that best match the main text. The preview materials designed in this way can not only help students effectively master the basic knowledge before class, but also lay a solid foundation for subsequent classroom teaching. Ultimately, this step ensures the coherence and efficiency of the overall teaching process by improving the pertinence and effectiveness of the preview.

[0170] Step 300: Collect and analyze students' learning data on the pre-class preparation materials to update the teaching group's cognitive level of course knowledge.

[0171] Specifically, the core of step 300 is to collect and analyze students' learning data on pre-class preview materials, so as to update the teaching group's cognitive level of course knowledge. This step evaluates students' understanding and mastery of the preview materials by conducting a detailed analysis of various data during the students' preview process, and updates students' cognitive level based on these data to ensure the pertinence and effectiveness of subsequent teaching links.

[0172] Optionally, first, the system will automatically collect various data generated by students during the preview process, including but not limited to the following categories:

[0173] Answering data: students’ answers to the exercises in the preview materials, including accuracy, answering time, error types and error frequency, etc. These data can directly reflect students’ understanding and mastery of knowledge points.

[0174] Interaction data: Students’ interactive behaviors when watching preview videos or reading preview texts, such as pausing, replaying, marking, taking notes, etc. By analyzing these behaviors, we can understand which parts students have difficulties or need more time and attention.

[0175] Participation data: The frequency and duration of students’ participation in pre-study activities. These data can reflect students’ learning attitudes and levels of engagement, helping to identify differences in learning initiative and persistence.

[0176] Feedback data: students’ feedback on the materials during the preview process, including evaluations of content difficulty, material format, explanation clarity, etc. This feedback can help adjust and optimize the design of preview materials.

[0177] Through comprehensive analysis of the above data, the system can construct a profile of each student's preparation. These data will be input into the analysis model to update each student's level of understanding of each knowledge point. Specifically, the analysis model will evaluate the student's mastery of different knowledge points based on the student's correct answer rate, error type and error frequency; judge the student's depth of understanding of the material and learning attitude by analyzing the interaction data and participation data; and use feedback data to adjust the presentation of the material and the difficulty of the content.

[0178] The updated cognitive level not only reflects the learning outcomes of students in the pre-study stage, but also serves as an important reference for subsequent teaching. The system will use these updated cognitive levels as constraints for generating classroom courseware, ensuring that classroom teaching content can be adjusted and optimized according to students' actual learning situation, thereby improving the effectiveness and efficiency of classroom teaching.

[0179] Through this process, the system realizes real-time monitoring and dynamic adjustment of students' preview effects, ensuring that each teaching link can be closely integrated with students' actual learning situation. This not only improves the accuracy and pertinence of teaching, but also provides students with a more personalized and efficient learning experience. Finally, step 300 collects and analyzes students' learning data and updates their cognitive level, providing solid technical support for the continuity and effectiveness of the entire teaching process.

[0180] Step 400: Based on the main text, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the updated teaching group's cognitive level of course knowledge, a classroom courseware content generation model is used to generate classroom courseware with the highest matching degree with each knowledge point in the main text from the knowledge point explanation courseware library.

[0181] Optionally, the design of the classroom courseware content generation model is as follows:

[0182]

[0183] in,

[0184] F2 is the calculation result of the matching degree between the knowledge point courseware and the main text.

[0185] E1, E2, E m′ They are the mastery requirements for the 1st, 2nd and m′ knowledge points of the main text respectively. The values ​​are divided into three levels according to the mastery requirements: e′, e″, e''', and e′>e″>e'''>0.

[0186] Com1, Com2, Comm′ are respectively the degree of detail of the explanation of the 1st, 2nd, and m′th knowledge points in the main text in each knowledge point courseware (the degree of detail can be evaluated from the knowledge point's phonetic symbols, word meanings, usages, examples, etc.).

[0187] K 1y The average frequency of the first knowledge point in the main text in professional direction y.

[0188] K Com1y It is the average frequency of the knowledge point in the knowledge point courseware in professional direction y.

[0189] N2 is the sum of the frequencies of all knowledge points under professional direction y.

[0190] K 2z The average frequency of the second knowledge point in the main text in professional direction z.

[0191] K Com2z It is the average frequency of the knowledge point in the knowledge point courseware in professional direction z.

[0192] N3 is the sum of the frequencies of all knowledge points under professional direction z.

[0193] K m′j is the average frequency of the m′th knowledge point in the main text in professional direction j.

[0194] K Comm′j It is the average frequency of the knowledge point in the knowledge point courseware in professional direction j.

[0195] Nm is the sum of the frequencies of all knowledge points under professional direction j.

[0196] n is the total number of teaching groups.

[0197] m is the total number of knowledge points contained in the main text.

[0198] R′ 1i , R′ 2i , R′ m′i They are respectively the cognitive levels of the 1st, 2nd, and m′th knowledge points after the ith student has previewed the content.

[0199] β1, β2, θ1, θ2, θ m ,π1,π2, ∝1, ∝2, is the weight coefficient.

[0200] Specifically, the key to step 400 is to use the classroom courseware content generation model to generate the classroom courseware with the highest matching degree with each knowledge point in the main text from the knowledge point explanation courseware library according to the mastery requirements of each knowledge point in the teaching stage in the main text and the knowledge point library and the updated teaching group's cognitive level of course knowledge. This step is to ensure that the classroom courseware can provide effective classroom teaching support based on the actual learning situation of students.

[0201] In the above formula, F2 is the result of the matching degree calculation between the knowledge point courseware and the main text. In order to calculate this matching degree, the model takes into account multiple factors:

[0202] First, the model evaluates the matching degree by the knowledge point mastery requirements and the detail of the explanation content. m′ They respectively represent the requirements for mastering the 1st, 2nd and m′ knowledge points in the main text, and these requirements are divided into three levels: e′, e″, e''', and e′>e″>e'''>0. At the same time, Com1, Com2, Comm′ respectively represent the degree of detail of the explanation of the 1st, 2nd and m′ knowledge points in the main text by each knowledge point courseware. These degrees of detail can be evaluated by phonetic symbols, word meanings, usage, examples, etc.

[0203] Secondly, the model takes into account the frequency of occurrence of knowledge points in different professional directions. 1y , K 2z and K m′j Respectively represent the average frequency of the first, second and m′th knowledge points in the main text in professional directions y, z and j. Com1y , K Com2z and K Comm′j They represent the frequency of occurrence of the corresponding knowledge points in the knowledge point courseware in these professional directions. N2, N3 and Nm represent the sum of the frequencies of occurrence of all knowledge points in professional directions y, z and j respectively. Through these frequency ratios, the model can evaluate the matching degree of the preview materials in the professional background.

[0204] In addition, the model also takes into account the students’ initial cognitive level. 1i , R′ 2i , R′ m′i They represent the cognitive level of the 1st, 2nd and m′th knowledge points after the i-th student has learned the preview content. These data can reflect the students’ understanding and mastery of each knowledge point during the preview stage, which helps the model generate classroom courseware that is more in line with the students’ actual situation.

[0205] Weight coefficient β1, β2, θ1, θ2, θ m ,π1,π2, ∝1, ∝2, It is used to adjust and optimize the impact of different factors in the matching calculation to ensure that the generated classroom courseware can best match the main text and students' learning needs in terms of content and form.

[0206] Through this model, the system can generate classroom courseware that best matches the knowledge points of the main text. This not only helps teachers to explain knowledge effectively in class and improve students' understanding and mastery, but also ensures the pertinence and efficiency of teaching content, ultimately improving the overall teaching effect.

[0207] Step 500: Collect and analyze students' learning data on the classroom courseware, and update the teaching group's cognitive level of course knowledge again.

[0208] Specifically, the focus of step 500 is to collect and analyze students' learning data on classroom courseware, so as to update the teaching group's cognitive level of course knowledge again. This process ensures that the effect of classroom teaching can be evaluated in a timely manner through detailed monitoring and analysis of students' learning behavior in class, and adjusts students' cognitive level according to the evaluation results, so as to provide accurate data support for subsequent teaching links.

[0209] Optionally, during classroom teaching, the system will collect various types of learning data in real time, including but not limited to the following categories:

[0210] Classroom interaction data: students’ interactions with courseware content in class, such as answering questions, participating in discussions, taking notes, asking questions, etc. By analyzing these interaction data, we can understand students’ participation and understanding of class content.

[0211] Answer data: The answers of students to the quizzes or exercises completed in class, including the correct answer rate, answering time, error types and frequency, etc. These data directly reflect the students' mastery of the content explained in class.

[0212] Behavioral data: students’ concentration, participation, attendance, etc. By analyzing these behavioral data, students’ learning status and classroom effectiveness can be evaluated.

[0213] Feedback data: students’ feedback on the content of the courseware, including evaluations of content difficulty, explanation clarity, class rhythm, etc. This feedback can help teachers adjust and optimize classroom teaching strategies.

[0214] The system constructs a classroom learning profile for each student through comprehensive analysis of the above data. These data will be input into the analysis model to update each student's cognitive level of each knowledge point. Specifically, the analysis model will evaluate the student's understanding and mastery of the classroom content based on the correct answer rate and error type; judge the student's participation and learning status in the classroom by analyzing the interaction data and behavior data; and use the feedback data to adjust and optimize the design and content of the classroom courseware.

[0215] The updated cognitive level not only reflects the learning outcomes of students during the classroom teaching stage, but also serves as an important reference for subsequent teaching. The system will use these updated cognitive levels as constraints for generating homework and further teaching content, ensuring that subsequent teaching content can be adjusted and optimized according to students' actual learning situation, thereby improving the pertinence and effectiveness of teaching.

[0216] Through this process, the system realizes real-time monitoring and dynamic adjustment of students' classroom learning effects, ensuring that each teaching link can be closely integrated with students' actual learning situation. This not only improves the accuracy and pertinence of teaching, but also provides students with a more personalized and efficient learning experience. Finally, step 500 collects and analyzes students' learning data and updates their cognitive level, providing solid technical support for the continuity and effectiveness of the entire teaching process.

[0217] Step 600: Based on the main text, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the updated teaching group's cognitive level of course knowledge, the homework content generation model is used to generate the homework with the highest matching degree with each knowledge point in the main text from the question bank.

[0218] Optionally, the design of the after-class homework content generation model is as follows:

[0219]

[0220] in,

[0221] F3 is the calculation result of the matching degree between the after-class exercises and the main text.

[0222] p is the total number of important and difficult knowledge points in the main text.

[0223] p′ is the number of difficult and important knowledge points in the after-class exercises that are the same as those in the main text.

[0224] E q is the mastery requirement of the qth same difficult knowledge point, and the value is divided into three levels according to the mastery requirement: e q ′、e q ″、e q ''', and e q ′>e q > q '''>0.

[0225] u is the total number of general knowledge points in the main text.

[0226] u′ is the number of general knowledge points in the after-class exercises that are the same as those in the main text.

[0227] E vis the mastery requirement of the vth same general knowledge point, and the value is divided into three levels according to the mastery requirement: e v ′、e v ″、e v ''', and e v ′>e v > v '''>0.

[0228] n is the total number of teaching groups.

[0229] m is the total number of knowledge points contained in the main text.

[0230] R' 1i ′、R' 2i '′、R'′ m′i They are respectively the cognitive levels of the 1st, 2nd, and m′th knowledge points of the ith student after studying the classroom courseware.

[0231] s means that the exercise is the sth question that contains a certain difficult knowledge point.

[0232] S′ is the preset threshold for the number of questions for each difficult knowledge point.

[0233] t means that the exercise is the tth question that contains a general knowledge point.

[0234] T′ is the preset threshold for the number of questions for each general knowledge point.

[0235] γ1, γ2, γ3, γ4, δ1, δ2, ω1, ω2, σ1, σ2, σ m , τ1, τ2 are weight coefficients.

[0236] Specifically, the focus of step 600 is to generate after-school homework with the highest matching degree with each knowledge point in the main text from the question bank based on the content of the main text, combined with the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the cognitive level of the teaching group after the update of the course knowledge, using the after-school homework content generation model. This process ensures that after-school homework can effectively consolidate the classroom teaching content and is personalized according to the actual learning situation of students.

[0237] In the above formula, F3 is the result of the match between the homework and the main text. In order to calculate this match, the model takes into account multiple factors:

[0238] First, the model evaluates the effectiveness of homework by the matching degree between key and difficult knowledge points and general knowledge points. p represents the total number of key and difficult knowledge points in the main text, and p′ represents the number of key and difficult knowledge points in the homework that are the same as those in the main text. and Calculate the matching degree of key and difficult knowledge points, where Eq The requirements for mastering the qth same difficult and important knowledge point are divided into three levels: e q ′、e q ″、e q ''', and e q ′>e q > q '''>0.

[0239] Similarly, the matching degree of general knowledge points is and Calculate, where u is the total number of general knowledge points in the main text, u′ is the number of general knowledge points in the after-class exercises that are the same as the main text, and E v The requirements for mastering the vth same general knowledge point are divided into three levels: e v ′、e v ″、e v ''', and e v ′>e v > v '''>0.

[0240] Secondly, the model takes into account the students’ cognitive level of each knowledge point. 1i ′、R 2i '′、R'′ m′i They represent the cognitive level of the 1st, 2nd and m′th knowledge points of the ith student after learning the courseware. Through the average of these data, we can evaluate the mastery of each knowledge point by the entire teaching group, so as to generate homework that is more in line with the actual level of students.

[0241] Finally, the model also includes the control of the number of questions on key points and general knowledge points. s means that the exercise is the sth question that contains a key point, S′ is the preset threshold for the number of questions on each key point, t means that the exercise is the tth question that contains a general knowledge point, T′ is the preset threshold for the number of questions on each general knowledge point. Through these ratios, the model can ensure that the number of questions in the homework is reasonably distributed.

[0242] Weight coefficient γ1, γ2, γ3, γ4, δ1, δ2, ω1, ω2, σ1, σ2, σ m , τ1, and τ2 are used to adjust and optimize the impact of different factors in the matching calculation to ensure that the generated homework can best match the main text and students' learning needs in terms of content and form.

[0243] Through this model, the system can generate homework that best matches the knowledge points of the main text. This not only helps students consolidate the knowledge they have learned in class, but also improves students' learning effects through targeted exercises, ultimately improving the overall teaching quality.

[0244] Step 700: Collect and analyze students' learning data on the homework, and ultimately update the teaching group's cognitive level of course knowledge.

[0245] Specifically, the core of step 700 is to collect and analyze the data of students' homework, so as to finally update the teaching group's cognitive level of course knowledge. This process identifies the deficiencies in the teaching process through detailed analysis of students' homework data, and provides teachers with targeted improvement suggestions, so as to improve teaching effectiveness.

[0246] Optionally, during after-class teaching, the system will automatically collect various data generated by students when completing homework, including but not limited to the following categories:

[0247] Answering data: The correct answer rate, answering time, error type and error frequency of students in completing homework. These data directly reflect the students' mastery of each knowledge point in the homework.

[0248] Interaction data: Students’ interactive behaviors when completing assignments, such as checking prompts, repeating answers, taking notes, and marking. By analyzing these behaviors, we can understand which questions students have difficulty with.

[0249] Feedback data: students’ feedback on homework, including evaluation of question difficulty, question type, homework amount, etc. This feedback can help optimize homework design.

[0250] Through comprehensive analysis of the above data, the system can construct an overview of each student's after-school learning. These data will be input into the analysis model, and ultimately update each student's cognitive level of each knowledge point. Specifically, the analysis model will evaluate the student's mastery of different knowledge points based on the student's correct answer rate, error type and error frequency; by analyzing the interactive data, it will determine the student's depth of understanding of the homework and learning attitude; and use feedback data to adjust the presentation of the material and the difficulty of the content.

[0251] The updated cognitive level not only reflects the students' learning outcomes during the review phase, but also serves as an important reference for subsequent learning analysis. The system will use these updated cognitive levels as constraints for learning analysis to ensure that each teaching link can be continuously optimized and improve the overall teaching quality.

[0252] Through this process, the system realizes real-time monitoring and dynamic adjustment of students' review effects, ensuring that each teaching link can be closely integrated with students' actual learning situation. This not only improves the accuracy and pertinence of teaching, but also provides students with a more personalized and efficient learning experience. Finally, step 700 provides solid technical support for the continuity and effectiveness of the entire teaching process by collecting and analyzing students' learning data and updating their cognitive levels.

[0253] Step 800: Based on the main text, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the final cognitive level of the teaching group on the course knowledge after being updated again, a learning situation analysis report is generated using the learning situation analysis and key points review model to diagnose the weak knowledge points of the teaching group and form a key points review report.

[0254] Optional, the design of the learning situation analysis and key points review model is as follows:

[0255] (4)

[0257] in,

[0258] F4 is the result of the learning situation analysis.

[0259] W1, W2, W m′ They are the mastery requirements for the 1st, 2nd, and m′ knowledge points in this teaching stage respectively. The values ​​are divided into three levels according to the mastery requirements: w′, w″, and w’’’, and w′>w″>w’’’>0.

[0260] n is the total number of teaching groups.

[0261] m is the total number of knowledge points contained in the main text.

[0262] R 1i ''′、R2' i '′, R m ' ′i '' are the cognitive levels of the 1st, 2nd, and m′th knowledge points after the i-th student completes his homework; ρ1, ρ2, ρ m is the weight coefficient.

[0263] In the above formula, F4 is the result of the learning situation analysis. To achieve this analysis, the model considers the following factors:

[0264] First, the model evaluates the learning situation by matching the knowledge point mastery requirements with the students’ cognitive level. m′They represent the mastery requirements of the 1st, 2nd and m′ knowledge points in this teaching stage respectively. These mastery requirements are divided into three levels: w′, w″, w''', and w′>w″>w'''>0. Through the matching of these levels, the model can evaluate students’ mastery of knowledge points of different difficulty levels.

[0265] Secondly, the model takes into account the students’ cognitive level of each knowledge point. 1i ''′、R2' i '′, R m ' ′i '' respectively represent the cognitive level of the 1st, 2nd and m′th knowledge points of the ith student after completing the homework. Through the average value of these data, the mastery of each knowledge point by the entire teaching group can be evaluated, thereby generating more accurate learning situation analysis results.

[0266] Weight coefficients ρ1, ρ2, ρ m Used to adjust and optimize the impact of different factors in the analysis to ensure that the generated learning situation analysis results can accurately reflect students' actual learning situation.

[0267] Through the learning situation analysis and key and difficult points review model, the system can generate detailed learning situation analysis reports. These reports can not only identify the key and difficult points and weak links encountered by students in the learning process, but also provide specific improvement suggestions. For example, the report can point out which knowledge points need further explanation and practice, which types of questions are challenging for students, etc. Teachers can formulate targeted teaching plans based on these reports to improve the pertinence and effectiveness of classroom teaching.

[0268] Step 900: Based on the review report on key points and difficulties, corresponding supplementary learning materials are selected from the digital resource library for students to strengthen and consolidate their learning.

[0269] Specifically, the core of step 900 is to select corresponding supplementary learning materials from the digital resource library based on the review report of key points and difficulties, so as to strengthen and consolidate students' learning. This step helps students overcome the weak links found in the learning situation analysis and further consolidate and deepen their grasp of knowledge points by providing additional learning resources in a targeted manner.

[0270] First, the system identifies the main problems and weak points that students encounter during the learning process based on the analysis results in the key points review report. These problems may include insufficient understanding of certain knowledge points, high error rates in specific question types, and weak grasp of certain subject knowledge points. The key points review report lists these problems in detail and provides specific analysis and suggestions for each problem.

[0271] Next, the system will select the most suitable supplementary learning materials from the digital resource library. The digital resource library includes the knowledge point library, the text material library, the pre-class preparation material library, the knowledge point explanation courseware library and the test question library. The materials in each resource library are carefully classified and labeled to ensure that they can cover different teaching content and knowledge points.

[0272] Optionally, the system can select supplementary learning materials according to the following technical steps:

[0273] Matching knowledge points: The system first searches the knowledge point database for resources that match the weak knowledge points mentioned in the key and difficult points review report. These resources include detailed knowledge point explanations, example analysis, common error analysis, etc., to help students deeply understand these knowledge points.

[0274] Select appropriate text materials: The system searches for text materials related to weak knowledge points in the text material library. These materials are carefully designed and annotated to help students understand and master knowledge points in practical applications.

[0275] Generate preview and review materials: The system selects appropriate preview and review materials from the pre-class preview material library and test question library. These materials include preview content for weak knowledge points, review exercises, practice questions and simulation tests, etc., to help students consolidate their knowledge through repeated practice.

[0276] Customized classroom courseware: The system selects detailed courseware from the knowledge point explanation courseware library, which includes explanations on phonetic symbols, word meanings, usage, examples, etc. Teachers can use these courseware to focus on weak knowledge points in class.

[0277] Through the above steps, the system can provide each student with tailored supplementary learning materials to ensure that these materials can effectively solve the problems encountered by students in the learning process.

[0278] In terms of technical effects, this step helps students overcome their weak links in learning by providing targeted supplementary learning materials, thereby improving learning efficiency and effectiveness. At the same time, the use of these supplementary learning materials can help students consolidate and deepen their understanding of knowledge points and improve their overall learning level. In addition, by dynamically adjusting and updating learning materials, the system can continuously track students' learning progress, ensuring that each student can obtain the most needed resources at the most appropriate time, thereby achieving personalized learning and precision teaching.

[0279] Finally, step 900 provides additional learning support for students by providing supplementary learning materials based on the review report on key points and difficulties, helping them to further consolidate the knowledge they have learned after class and improve their learning outcomes, thus providing a strong guarantee for the continuity and effectiveness of the entire teaching process.

[0280] Step 1000: Use the cognitive level of each knowledge point of the teaching group in the learning situation analysis report as the initial cognitive level of the next teaching session, and execute steps 200 to 1000 in a loop.

[0281] Specifically, the key to step 1000 is to use the cognitive level of each knowledge point of the teaching group in the learning situation analysis report as the initial cognitive level of the next teaching link, and cyclically execute steps 200 to 1000. This process ensures the continuity and dynamic adjustment of the teaching process, so that each teaching link can be optimized and adjusted based on the latest learning data, thereby achieving personalized and precise teaching.

[0282] Specifically, the learning situation analysis report records in detail each student's cognitive level of each knowledge point. These cognitive levels are obtained through a comprehensive analysis of students' performance in various links such as pre-study, classroom learning, and homework, reflecting the students' understanding and mastery of knowledge points. The system uses these data as the initial cognitive level of the next teaching cycle to guide subsequent teaching design and resource selection.

[0283] Optionally, when entering the next teaching cycle, the system first executes step 200 to generate new preview materials based on the updated initial cognitive level. The generation of preview materials takes into account the students' current mastery of each knowledge point, ensuring that the preview content can be designed for students' weak links and knowledge points that need further consolidation. This process utilizes the preview material content generation model, which selects the most appropriate preview material by analyzing the student's matching degree to the main text, thereby improving the preview effect.

[0284] Next, the system collects and analyzes the student's learning data on the new preview material and updates the student's cognitive level in step 300. The system monitors the student's learning situation in real time, evaluates the preview effect and adjusts the cognitive level by analyzing data such as the correct answer rate, learning behavior and feedback.

[0285] In step 400, the system generates new courseware according to the updated cognitive level. These coursewares select the most suitable content for explanation according to the students' requirements for mastering each knowledge point and cognitive level through the courseware content generation model. The system ensures that the courseware can effectively cover the students' weak knowledge points and key and difficult points, and improve the pertinence and effectiveness of classroom teaching.

[0286] Then, in step 500, the system collects and analyzes the students' learning data on the courseware again to further update the students' cognitive level. These data include classroom interaction, answering status and student feedback. By analyzing these data, the system evaluates the classroom teaching effect and makes corresponding adjustments.

[0287] In step 600, the system generates new homework. Through the homework content generation model, the system selects the most appropriate homework content according to the student's latest cognitive level, ensuring that the after-class exercises can consolidate the knowledge learned in class and help students further master the knowledge points.

[0288] In step 700, the system collects and analyzes students' learning data on homework assignments, and ultimately updates the teaching group's level of understanding of course knowledge.

[0289] In step 800, the system determines the weak knowledge points of the teaching group based on the final level of cognition of the course knowledge of the teaching group, and forms a review report on the key and difficult points based on these weak knowledge points. This report is used to dynamically adjust the teaching content and provide targeted improvement suggestions.

[0290] In step 900, the system selects corresponding supplementary learning materials from the digital resource library according to the review report on key points and difficulties. Through these materials, students can further strengthen and consolidate their learning after class and solve the weak links in their learning.

[0291] Finally, in step 1000, the system uses the latest updated teaching group's cognitive level of course knowledge as the initial cognitive level of the next teaching cycle. Through this cycle, the system can continuously and dynamically adjust and optimize teaching content and strategies to ensure that each teaching link can be closely integrated with students' actual learning situation.

[0292] In terms of technical effects, this cyclic execution method realizes closed-loop management of the teaching process. Through continuous feedback and adjustment, it ensures the continuity and dynamic optimization of teaching, improves the accuracy and personalization of teaching, and ultimately improves the overall teaching quality and students' learning outcomes.

[0293] It should be pointed out that in this embodiment, the preview material content generation model, classroom courseware content generation model, after-class homework content generation model and learning situation analysis and key points review model are all content generation models based on artificial intelligence. By real-time analysis of student learning data, the teaching content is dynamically adjusted to achieve personalized learning and precise teaching.

[0294] The above embodiments have the following technical effects:

[0295] Comprehensiveness and coherence: By constructing a digital resource library that includes a knowledge point library, a text material library, a pre-class preparation material library, a knowledge point explanation courseware library, and a question library, this method covers the entire process of English teaching, ensuring the comprehensiveness of the teaching content and the coherence of each teaching link.

[0296] Personalized learning: Using the preview material content generation model, classroom courseware content generation model and after-class homework content generation model, the most matching learning materials are generated according to students' initial cognitive level and learning progress, realizing personalized customization of teaching content.

[0297] Real-time feedback and dynamic adjustment: By continuously collecting and analyzing students' learning data, the system can update the teaching group's cognitive level of course knowledge in real time, thereby dynamically adjusting subsequent teaching content to ensure the flexibility and adaptability of the teaching process.

[0298] Precision teaching: Using the learning situation analysis and key points review model, the system can accurately diagnose the weak knowledge points of the teaching group and generate corresponding key points review reports to provide teachers with precise teaching guidance.

[0299] Loop optimization: Through the loop execution mechanism of step 1000, the system can continuously optimize teaching content and methods and continuously improve teaching quality.

[0300] Improve teaching efficiency: Since the system automatically generates the content of each teaching link, it greatly reduces the teacher's lesson preparation workload and improves teaching efficiency.

[0301] Data-driven teaching decisions: Through comprehensive analysis of student learning data, the system provides teachers with data-driven teaching decision support, which helps to formulate more scientific and reasonable teaching strategies.

[0302] Efficient use of learning resources: Based on the digital resource library and intelligent matching algorithm, the system can quickly filter out the most suitable content from massive learning resources, thereby improving the efficiency of learning resource utilization.

[0303] Adaptive learning path: By continuously updating students' cognitive levels and dynamically adjusting teaching content, the system provides each student with an adaptive learning path, which helps improve learning outcomes.

[0304] Comprehensive learning assessment: Through data collection and analysis of multiple teaching links, the system provides a comprehensive assessment of students' learning situation, which helps to identify and solve learning problems in a timely manner.

[0305] To sum up, this integrated English teaching method based on artificial intelligence realizes the organic combination of personalized learning and precise teaching, greatly improves the effectiveness and efficiency of English teaching, and provides an innovative solution for modern education.

[0306] In order to better understand the technical solution of the present application, a specific example is provided below for illustration. The details listed in the example are mainly for ease of understanding and are not intended to limit the scope of protection of the present application.

[0307] This example proposes an integrated English teaching system and method based on artificial intelligence, in which the system first constructs a knowledge point library, a text material library, a pre-class preview material library, a knowledge point explanation courseware library, and a question library through a digital resource library construction module to provide teaching resources for each teaching link of the course; secondly, based on the pre-class, in-class, and after-class teaching links of the course, a preview material production and learning module, a classroom courseware production and teaching module, and an after-class homework production and review module are constructed. The data of each module is highly shared and comprehensively analyzed, and the teaching and learning materials are updated in real time through the key designed module content generation model; further, by constructing a learning situation analysis and key and difficult point review module, the weak knowledge points of the teaching group can be accurately diagnosed, and a key and difficult point review report of the course teaching content can be formed for students to strengthen and consolidate their learning. Specific integrated English teaching systems such as Figure 3 shown.

[0308] The specific implementation method includes the following two parts:

[0309] 1. Construction of digital library resource library

[0310] Construct a digital resource library including knowledge point library, text material library, pre-class preparation material library, knowledge point explanation courseware library, and test question library to generate pre-class preparation materials, classroom courseware, and after-class homework required for each teaching link of the course. The specific contents of the construction are as follows:

[0311] (1) Knowledge point database: Based on the knowledge point information in the teaching syllabus and examination syllabus of each teaching stage of the subject, the knowledge point domain of each teaching stage is constructed, and the attributes of the teaching stage and mastery requirements (divided into three levels: mastering application, understanding explanation, and knowing and understanding) of each knowledge point are marked.

[0312] (2) Text material library, pre-class preparation material library, knowledge point explanation courseware library, and test question library: According to the teaching objectives of different teaching stages, a large number of different types of text materials are collected, and the theme knowledge points, key and difficult knowledge points, and general knowledge points in the texts are annotated; various types of pre-class preparation materials such as audio and video, text, etc. are collected, and the theme knowledge points, key and difficult knowledge points, and general knowledge points in the materials are annotated; a courseware library for explaining each knowledge point is collected, including the analysis content such as the phonetic symbols, word meanings, usage, examples, etc. of each knowledge point; a large number of test questions of different question types are collected, and the knowledge points in the test questions are annotated.

[0313] 2. Content generation for each teaching link of the course

[0314] The content generation of each teaching link of the course includes pre-class preview materials, classroom courseware, after-class homework, and review of key points based on learning situation analysis. The content generation of each link is associated with the course textbook content and the feedback data of the previous teaching link, and is optimized and updated in real time. Specifically, the pre-class teaching link of the course designs a preview material content generation model based on the course textbook content and the initial level of understanding of the course knowledge of the teaching group, and generates pre-class preview materials with strong thematic relevance to the course textbook content; the in-class teaching link of the course designs a classroom courseware content generation model based on the course textbook content and the level of understanding of the course knowledge of the teaching group after learning the preview content, and generates classroom courseware that highlights the key and difficult knowledge points of the course textbook content; the after-class teaching link of the course designs a after-class homework content generation model based on the level of understanding of the course knowledge of the teaching group after learning the course textbook content and the classroom courseware content, and generates after-class homework covering all knowledge points of the course textbook content; the learning situation analysis and review of key points model is designed to accurately diagnose the weak knowledge points of the teaching group, and form a review report on the key and difficult points of the course textbook content, which is used for students to strengthen and consolidate their learning.

[0315] It should be noted that in the specific embodiment of the present application, the course teaching material content may be (but is not limited to) the main text that needs to be learned in the teaching material.

[0316] The specific implementation steps are as follows Figure 2 shown.

[0317] Step 1: Preparation of pre-study materials and analysis of pre-class learning

[0318] According to the main text of the textbook, based on the mastery requirements of each knowledge point in the knowledge point domain at this teaching stage, and the initial cognitive level of the teaching group on the course knowledge and other constraints, a preview material content generation model is designed. The preview material with the highest matching degree with the main text can be obtained from the pre-class preview material library to realize the production of preview materials for the pre-class teaching link. The preview material ensures that it has a strong relevance to the theme of the main text and meets the cognitive level of the teaching group, and can be used for students' independent learning before class. The specific design of the preview material content generation model is as follows:

[0319]

[0320] in,

[0321] F1 is the matching result between the preview materials and the main text.

[0322] a and b are the number of thematic knowledge points in the preview materials and the main text respectively.

[0323] Min(a,b) is the number of common subject knowledge points between the two.

[0324] Max(a,b) is the maximum number of subject knowledge points between the two.

[0325] E c is the mastery requirement of the cth theme knowledge point in the main text, and the value is divided into three levels according to the mastery requirement: e c ′、e c ″、e c ''', and e c ′>e c > c '''>0.

[0326] K dx is the average frequency of the dth subject knowledge point in the preview material in professional direction x.

[0327] K ex is the average frequency of the e-th theme knowledge point in the main text in professional direction x.

[0328] N1 is the sum of the frequencies of all knowledge points under professional direction x.

[0329] n is the total number of teaching groups.

[0330] m is the total number of knowledge points contained in the main text.

[0331] R 1i , R 2i , R m′i are the initial cognitive levels of the ith student for the 1st, 2nd, and m′th knowledge points respectively.

[0332] Z r The length of the audio and video materials of the preview content in the preview materials.

[0333] Z r ' is the preset threshold for the duration of the audio and video materials of the preview content.

[0334] T r It is the number of words in the text of the preview content in the preview materials.

[0335] T r ′ is the preset threshold of the text length of the preview material.

[0336] S r is the number of exercises in the preview homework in the preview materials.

[0337] S r ′ is the threshold value of the number of exercises in the preview materials.

[0338] α1, α2, α3, ε1, ε2, ε3, μ1, μ2, μ m ,∈1,∈2,∈3 are weight coefficients.

[0339] It should be pointed out that: 1) by analyzing the pre-class learning situation through the data of students' difficulty mark and answers to preview exercises, the cognitive level of the teaching group on course knowledge after learning the preview content is updated, which serves as a constraint condition for generating classroom courseware in the next step; 2) teachers are allowed to adjust the content of preview materials, such as reducing / increasing the length of audio and video materials, reducing / increasing the length of text, and reducing / increasing the number of preview questions.

[0340] In other words, by analyzing the students' pre-class learning situation based on the data of marking difficult points and answering questions in the preview homework, the teaching group's cognitive level of course knowledge after learning the preview content can be effectively updated. These difficult point marking data refer to the behavior of students marking knowledge points that they do not understand or are not familiar with during the preview process, which reflects the difficulties and problems encountered by students in the preview stage and is a way for students to provide self-feedback. The answering data for the preview homework exercises are the data generated when students complete the exercises in the preview homework, including the correct answer rate, answering time, and the type of errors in the answering process. These data can reflect the students' understanding and mastery of the preview content. By collecting and analyzing the above data, the system can understand the students' learning situation in the preview stage, identify common problems and personalized learning needs, and thus realize the understanding of the overall cognitive level of the teaching group on the course knowledge. According to the results of the pre-class learning situation analysis, the system will update the teaching group's cognitive level of course knowledge. This updated cognitive level reflects the students' learning achievements in the preview stage and is an adjustment and supplement to the initial cognitive level. The updated cognitive level serves as a constraint for generating classroom courseware, which means that the system will take students' actual learning situation and needs into consideration when designing classroom courseware, thereby ensuring the pertinence and effectiveness of the courseware content and helping teachers better explain difficult and key knowledge in class.

[0341] In addition, the system allows teachers to flexibly adjust the content of preview materials to meet students' specific learning situations and teaching needs. Teachers can adjust the length of audio and video in the preview materials based on the preview effect and student feedback to ensure that the content is neither too much nor too little to achieve the best learning effect. At the same time, teachers can also adjust the length of the text in the preview materials based on students' reading speed and comprehension ability to make it more in line with students' learning habits and needs. Teachers can also adjust the number of preview questions based on students' mastery of the preview content, increase moderately difficult exercises to consolidate learning, or reduce excessive exercises to avoid overburdening students. In these ways, teachers can more flexibly control the content and form of preview materials so that they can better serve teaching objectives and students' learning needs, thereby improving the adaptability and personalization of teaching and improving students' learning effects.

[0342] Step 2: Classroom courseware production and in-class teaching situation analysis

[0343] According to the main text of the textbook, based on the mastery requirements of each knowledge point in the knowledge point domain at this teaching stage, and the cognitive level of the teaching group on the course knowledge after learning the preview content, the classroom courseware content generation model is designed. The knowledge point explanation courseware with the highest matching degree with each knowledge point in the main text can be obtained from the knowledge point courseware library to realize the classroom courseware production of the in-class teaching link. This classroom courseware focuses on the important and difficult knowledge points of the main text and meets the cognitive level of the teaching group. It can be used as a teacher's classroom explanation material and a student's classroom learning material. The specific design of the classroom courseware content generation model is as follows:

[0344]

[0345] in,

[0346] F2 is the calculation result of the matching degree between the knowledge point courseware and the main text.

[0347] E1, E2, E m′ They are the mastery requirements for the 1st, 2nd and m′ knowledge points of the main text respectively. The values ​​are divided into three levels according to the mastery requirements: e′, e″, e''', and e′>e″>e'''>0.

[0348] Com1, Com2, Comm′ are respectively the degree of detail of the explanation of the 1st, 2nd, and m′th knowledge points in the main text in each knowledge point courseware (the degree of detail can be evaluated from the knowledge point's phonetic symbols, word meanings, usages, examples, etc.).

[0349] K 1y The average frequency of the first knowledge point in the main text in professional direction y.

[0350] K Com1y It is the average frequency of the knowledge point in the knowledge point courseware in professional direction y.

[0351] N2 is the sum of the frequencies of all knowledge points under professional direction y.

[0352] K 2z The average frequency of the second knowledge point in the main text in professional direction z.

[0353] K Com2z It is the average frequency of the knowledge point in the knowledge point courseware in professional direction z.

[0354] N3 is the sum of the frequencies of all knowledge points under professional direction z.

[0355] K m′jis the average frequency of the m′th knowledge point in the main text in professional direction j.

[0356] K Comm′j It is the average frequency of the knowledge point in the knowledge point courseware in professional direction j.

[0357] Nm is the sum of the frequencies of all knowledge points under professional direction j.

[0358] n is the total number of teaching groups.

[0359] m is the total number of knowledge points contained in the main text.

[0360] R′ 1i , R′2 ′ i , R′ m′i They are respectively the cognitive levels of the 1st, 2nd, and m′th knowledge points after the ith student has previewed the content.

[0361] β1, β2, θ1, θ2, θ m ,π1,π2, ∝1, ∝2, is the weight coefficient.

[0362] It should be pointed out that: ① Through the analysis of the in-class teaching situation based on the data of students' difficulty marking and the data of teachers' explanation time of each knowledge point, the cognitive level of the teaching group on course knowledge after learning the classroom courseware is updated, which serves as the constraint condition for generating homework in the next step; ② For example, the knowledge point "work" has different professional directions such as "work, occupation", "workpiece, machinery, repair" and "engineering" in different knowledge point courseware, and there are multiple coursewares for explaining the knowledge points of the professional direction "work, occupation", and each courseware has different levels of detail in the usage and example sentences of "work"; ③ Teachers are allowed to adjust the content of classroom courseware by adding / deleting difficult knowledge points, adding / deleting general knowledge points, etc.

[0363] In other words, by analyzing the in-class teaching situation of the students' difficult point marking data and the teachers' explanation time data of each knowledge point, the teaching group's cognitive level of course knowledge after learning the classroom courseware can be effectively updated. These difficult point marking data refer to the behavior of students marking knowledge points that they do not understand or are not familiar with during the classroom teaching process, reflecting the difficulties and problems encountered by students in the classroom learning stage, and are a way for students to provide real-time feedback. The data of the teacher's explanation time for each knowledge point refers to the time spent by the teacher on each knowledge point in class. These data can reflect the detailed explanation of each knowledge point and the students' understanding in class. By collecting and analyzing these data, the system can understand the students' learning situation in the classroom teaching stage, identify common problems and personalized learning needs, and thus realize the understanding of the overall cognitive level of the teaching group on the course knowledge. According to the results of the in-class teaching situation analysis, the system will update the teaching group's cognitive level of course knowledge. This updated cognitive level reflects the students' learning achievements in the classroom stage and is an adjustment and supplement to the previous cognitive level. The updated cognitive level serves as a constraint for generating homework, which means that the system will take students' actual learning situation and needs into consideration when designing homework, thereby ensuring the pertinence and effectiveness of the homework content and helping students consolidate what they have learned in class after class.

[0364] For example, the knowledge point "work" is divided into different professional directions such as "work, occupation", "workpiece, machinery, repair", and "engineering" in different knowledge point courseware. There may be multiple coursewares in the knowledge point explanation courseware for the professional direction "work, occupation", and each courseware has different levels of detail in the usage and example description of "work". By analyzing these coursewares, the system can understand the level of detail of the explanation of the knowledge point "work" in different coursewares, so as to provide more targeted exercises when designing homework, helping students further consolidate and understand this knowledge point.

[0365] In addition, the system also allows teachers to flexibly adjust the content of classroom courseware to meet students' specific learning situations and teaching needs. Teachers can add or delete key and difficult knowledge points based on classroom teaching results and student feedback to ensure that the key and difficult points of classroom content are highlighted. At the same time, teachers can also add or delete general knowledge points to make the content of classroom courseware more in line with students' learning habits and needs. Through these methods, teachers can more flexibly control the content and form of classroom courseware to better serve teaching objectives and students' learning needs, thereby improving the adaptability and personalization of teaching and improving students' learning effects.

[0366] Step 3: Analysis of homework preparation and after-class review

[0367] According to the main text of the textbook, based on the mastery requirements of each knowledge point in the knowledge point domain in this teaching stage, and the cognitive level of the teaching group after learning the classroom courseware, the after-class homework content generation model is designed. The after-class exercises with the highest matching degree with each knowledge point of the main text can be obtained from the question bank to realize the after-class homework production of the after-class teaching link. This after-class homework ensures that all knowledge points of the main text are covered and meet the cognitive level of the teaching group, and can be used by students to consolidate the knowledge learned in class. The specific design of the after-class homework content generation model is as follows:

[0368]

[0369] in,

[0370] F3 is the calculation result of the matching degree between the after-class exercises and the main text.

[0371] p is the total number of important and difficult knowledge points in the main text.

[0372] p′ is the number of difficult and important knowledge points in the after-class exercises that are the same as those in the main text.

[0373] E q is the mastery requirement of the qth same difficult knowledge point, and the value is divided into three levels according to the mastery requirement: e q ′、e q ″、e q ''', and e q ′>e q > q '''>0.

[0374] u is the total number of general knowledge points in the main text.

[0375] u′ is the number of general knowledge points in the after-class exercises that are the same as those in the main text.

[0376] E v is the mastery requirement of the vth same general knowledge point, and the value is divided into three levels according to the mastery requirement: e v ′、e v ″、e v ''', and e v ′>e v > v '''>0.

[0377] n is the total number of teaching groups.

[0378] m is the total number of knowledge points contained in the main text.

[0379] R1' i ′、R 2i '′, R m ' ′' i They are respectively the cognitive levels of the 1st, 2nd, and m′th knowledge points of the ith student after studying the classroom courseware.

[0380] s means that the exercise is the sth question that contains a certain difficult knowledge point.

[0381] S′ is the preset threshold for the number of questions for each difficult knowledge point.

[0382] t means that the exercise is the tth question that contains a general knowledge point.

[0383] T′ is the preset threshold for the number of questions for each general knowledge point.

[0384] γ1, γ2, γ3, γ4, δ1, δ2, ω1, ω2, σ1, σ2, σ m , τ1, τ2 are weight coefficients.

[0385] It should be pointed out that: 1) by analyzing the after-class review situation of each student's homework answer data, the teaching group's cognitive level of course knowledge after the homework is completed is updated as a constraint condition for the next step of learning situation analysis; 2) teachers are allowed to make adjustments such as adding / deleting homework exercises.

[0386] In other words, by analyzing the after-class review situation of each student's homework answer data, the teaching group's cognitive level of course knowledge after the homework is completed can be effectively updated. These answer data include the student's answer accuracy, answer time, wrong question type and overall performance when completing the homework. These data can reflect the students' mastery of each knowledge point in the homework, as well as the difficulties and problems they encounter during the review process. By collecting and analyzing these data, the system can understand the students' learning situation during the after-class review stage, identify common problems and personalized learning needs, and thus realize the understanding of the teaching group's overall cognitive level of course knowledge.

[0387] Based on the results of the post-class review analysis, the system will update the teaching group's cognitive level of course knowledge. This updated cognitive level reflects the students' learning outcomes in the post-class homework stage, and is an adjustment and supplement to the cognitive level of the previous classroom learning and preview stages. The updated cognitive level serves as a constraint for the next step of the learning situation analysis, which means that the system will consider the students' actual learning situation and needs when conducting the learning situation analysis, thereby ensuring the accuracy and pertinence of the learning situation analysis, helping teachers better understand the students' learning status, and developing more effective teaching strategies.

[0388] In addition, the system allows teachers to flexibly adjust homework to meet students' specific learning situations and teaching needs. Teachers can add or delete exercises based on students' performance in homework to ensure that the difficulty and quantity of homework are moderate. By adding exercises, teachers can provide more practice opportunities to help students further consolidate their knowledge. By deleting too many or too difficult exercises, students' learning burden can be avoided and their interest and enthusiasm in learning can be improved. In these ways, teachers can more flexibly control the content and form of homework so that it can better serve teaching objectives and students' learning needs, thereby improving the adaptability and personalization of teaching and improving students' learning outcomes.

[0389] Step 4: Analyze the learning situation and review the key points

[0390] According to the main text of the textbook, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point domain, and the teaching group's cognitive level of course knowledge after the completion of homework, the learning situation analysis and key and difficult points review model is designed to conduct a learning situation analysis of the students in the class, diagnose the weak knowledge points of the teaching group, and form a key and difficult points review report on the course textbook content for students to strengthen and consolidate their learning. The specific design of the learning situation analysis and key and difficult points review model is as follows:

[0391]

[0392] in,

[0393] F4 is the result of the learning situation analysis.

[0394] W1, W2, W m′ They are the mastery requirements for the 1st, 2nd, and m′ knowledge points in this teaching stage respectively. The values ​​are divided into three levels according to the mastery requirements: w′, w″, and w’’’, and w′>w″>w’’’>0.

[0395] n is the total number of teaching groups.

[0396] m is the total number of knowledge points contained in the main text.

[0397] R 1i ''′、R2' i '′, R m ' ′i '' are the cognitive levels of the 1st, 2nd, and m′th knowledge points after the i-th student completes his homework; ρ1, ρ2, ρ m is the weight coefficient.

[0398] It should be pointed out that: ① If the cognitive level of the teaching group is low when the requirements for mastering the knowledge points in the syllabus are high, the knowledge point is determined to be the weak knowledge point of the teaching group; ② The cognitive level of each knowledge point obtained from the learning situation analysis is used as the initial cognitive level of the teaching group for each knowledge point when the content of the next teaching session is generated; ③ Based on the review report, teachers can (but not limited to) prepare explanation materials for weak knowledge point questions, so as to facilitate targeted review of the weak knowledge points of the teaching group in the next class; or further generate the same type of questions for weak knowledge points through the system, so as to facilitate the consolidation and review of the teaching group.

[0399] In other words, if the knowledge points required by the syllabus are high, but the cognitive level of the teaching group is low, then the system will identify the knowledge points as weak knowledge points of the teaching group. This situation indicates that students have insufficient grasp of these key knowledge points and may encounter difficulties in subsequent learning and examinations. Therefore, identifying these weak knowledge points is crucial to improving teaching strategies and improving students' learning outcomes.

[0400] The cognitive level of each knowledge point obtained by the learning situation analysis will be used as the initial cognitive level of the teaching group for each knowledge point when the content of the next teaching session is generated. This means that at the beginning of a new teaching cycle, the system will design new teaching content and strategies based on the data obtained from the last learning situation analysis. This ensures that each teaching session can be adjusted and optimized according to the actual learning situation of the students, thereby improving the pertinence and effectiveness of teaching.

[0401] Based on the review report generated by the student situation analysis, teachers can prepare test explanation materials for weak knowledge points so that they can conduct targeted review of the weak knowledge points of the teaching group in the next class. These explanation materials can include detailed problem-solving steps, explanations of key concepts, and analysis of common errors to help students better understand and master these knowledge points. In addition, teachers can also further generate similar question types for weak knowledge points through the system, providing more practice opportunities to help students consolidate and review. These question types can include exercises of various difficulty levels and forms to ensure that students can apply what they have learned in different situations and further improve learning outcomes.

[0402] Through these methods, the system can not only identify and provide feedback on students' weak knowledge points, but also provide teachers with effective teaching tools and resources to help students overcome learning difficulties. In this way, the entire teaching process achieves closed-loop management, from identifying problems to providing solutions, to feedback and adjustments, ensuring that each teaching link can effectively support students' learning needs and improve the overall teaching quality.

[0403] The second embodiment of the present application relates to an integrated English teaching system based on artificial intelligence, the structure of which is as follows: Figure 4As shown, the integrated English teaching system based on artificial intelligence includes:

[0404] A digital resource library construction module is used to construct a digital resource library;

[0405] A pre-class preview material generation module is used to generate pre-class preview materials with the highest matching degree with each knowledge point of the main text from the pre-class preview material library based on the main text of the textbook, the digital resource library and the initial cognitive level of the teaching group on the course knowledge;

[0406] The first data collection and analysis module is used to collect and analyze students' learning data on the pre-class preview materials and update the teaching group's cognitive level of course knowledge;

[0407] A classroom courseware generation module is used to generate classroom courseware with the highest matching degree with each knowledge point of the main text from the knowledge point explanation courseware library according to the main text, based on the digital resource library and the updated teaching group's cognitive level of course knowledge;

[0408] The second data collection and analysis module is used to collect and analyze students' learning data on the classroom courseware, and to update the teaching group's cognitive level of the course knowledge again;

[0409] A homework generation module is used to generate homework with the highest matching degree with each knowledge point of the main text from the question bank based on the mastery requirements of each knowledge point of the teaching stage in the knowledge point library and the cognitive level of the teaching group on the course knowledge after being updated again according to the main text;

[0410] The third data collection and analysis module is used to collect and analyze students' learning data on the homework, and finally update the teaching group's cognitive level of course knowledge;

[0411] A learning situation analysis module is used to determine the weak knowledge points of the teaching group based on the main text, the digital resource library and the final cognitive level of the teaching group on the course knowledge, and to form a review report on key and difficult points based on the weak knowledge points, so as to dynamically adjust the teaching content;

[0412] A loop execution module is used to use the cognitive level of each knowledge point of the teaching group in the learning situation analysis report as the initial cognitive level of the next teaching link, and to loop the functions of the pre-class preview material generation module to the learning situation analysis module.

[0413] The first implementation manner is a method implementation manner corresponding to the present implementation manner. The technical details in the first implementation manner can be applied to the present implementation manner, and the technical details in the present implementation manner can also be applied to the first implementation manner.

[0414] It should be noted that those skilled in the art should understand that the implementation functions of each module shown in the implementation of the above-mentioned integrated English teaching system based on artificial intelligence can be understood by referring to the relevant description of the above-mentioned integrated English teaching method based on artificial intelligence. The functions of each module shown in the implementation of the above-mentioned integrated English teaching system based on artificial intelligence can be realized by a program (executable instruction) running on a processor, or by a specific logic circuit. If the above-mentioned integrated English teaching system based on artificial intelligence in the embodiment of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, ReadOnly Memory), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0415] Accordingly, an embodiment of the present application further provides a computer storage medium, in which computer executable instructions are stored. When the computer executable instructions are executed by a processor, the various method embodiments of the present application are implemented.

[0416] In addition, the embodiment of the present application also provides an integrated English teaching system based on artificial intelligence, which includes a memory for storing computer executable instructions, and a processor; the processor is used to implement the steps in the above-mentioned method implementation when executing the computer executable instructions in the memory. Among them, the processor can be a central processing unit (Central Processing Unit, referred to as "CPU"), or other general-purpose processors, digital signal processors (Digital Signal Processor, referred to as "DSP"), Application Specific Integrated Circuit (Application Specific Integrated Circuit, referred to as "ASIC"), etc. The aforementioned memory can be a read-only memory (read-only memory, referred to as "ROM"), a random access memory (random access memory, referred to as "RAM"), a flash memory (Flash), a hard disk or a solid-state hard disk, etc. The steps of the method disclosed in each embodiment of the present application can be directly embodied as a hardware processor to be executed, or a combination of hardware and software modules in the processor can be executed.

[0417] It should be noted that, in the application documents of the present application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or equipment. In the absence of more restrictions, the elements defined by the sentence "include one" do not exclude the existence of other identical elements in the process, method, article or equipment including the elements. In the application documents of the present application, if it is mentioned that a certain action is performed according to a certain element, it means that at least the action is performed according to the element, which includes two situations: performing the action only according to the element and performing the action according to the element and other elements. Expressions such as multiple, multiple, multiple, etc. include 2, 2 times, 2 kinds and more than 2, more than 2 times, more than 2 kinds.

[0418] All documents mentioned in this application are considered to be included in the disclosure of this application as a whole, so that they can be used as the basis for modification when necessary. In addition, it should be understood that after reading the above disclosure of this application, those skilled in the art can make various changes or modifications to this application, and these equivalent forms also fall within the scope of protection claimed in this application.

Claims

1. An integrated English teaching method based on artificial intelligence, characterized in that: The following steps are involved: Step A: Build a digital resource library; Step B: Based on the main text of the textbook, the digital resource library and the initial cognitive level of the teaching group on the course knowledge, generate the pre-class preview materials with the highest matching degree with each knowledge point of the main text from the pre-class preview material library; Collect and analyze students' learning data on the pre-class preparation materials to update the teaching group's level of understanding of course knowledge; Step C: Based on the main text, the digital resource library and the updated teaching group's cognitive level of course knowledge, generate classroom courseware with the highest matching degree with each knowledge point of the main text from the knowledge point explanation courseware library; Collect and analyze students' learning data on the classroom courseware, and update the teaching group's cognitive level of course knowledge; Step D: generating homework with the highest matching degree with each knowledge point of the main text from the question bank according to the main text, based on the digital resource library and the cognitive level of the teaching group on the course knowledge after the update; Collect and analyze students’ learning data on the homework assignments, and ultimately update the teaching group’s level of knowledge of the course; Step E: Based on the digital resource library and the final cognitive level of the teaching group on the course knowledge, the weak knowledge points of the teaching group are determined, and a review report on key and difficult points is formed according to the weak knowledge points to dynamically adjust the teaching content. Step F: Use the cognitive level of each knowledge point of the teaching group in the learning situation analysis report as the initial cognitive level of the next teaching session, and execute steps B to F in a loop.

2. The method according to claim 1, characterized in that The digital resource library includes a knowledge point library, a text material library, a pre-class preview material library, a knowledge point explanation courseware library and a test question library, wherein the knowledge point library contains the mastery requirements of each knowledge point in the teaching stage.

3. The method according to claim 1, characterized in that In step B, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the initial cognitive level of the teaching group on the course knowledge, a pre-class preview material content generation model is used to generate the pre-class preview material with the highest matching degree with the main text from the pre-class preview material library, wherein the pre-class preview material content generation model is as follows: in, F1 is the matching result between the preview materials and the main text. a and b are the number of thematic knowledge points in the preview materials and the main text respectively. Min(a,b) is the number of common subject knowledge points between the two. Max(a,b) is the maximum number of subject knowledge points between the two. E c is the mastery requirement of the cth theme knowledge point in the main text, and the value is divided into three levels according to the mastery requirement: e c ′、e c ″、e c ''', and e c ′>e c > c '''>0. K dx is the average frequency of the dth subject knowledge point in the preview material in professional direction x. K ex is the average frequency of the e-th theme knowledge point in the main text in professional direction x. N1 is the sum of the frequencies of all knowledge points under professional direction x. n is the total number of teaching groups. m is the total number of knowledge points contained in the main text. R 1i , R 2i , R m′i are the initial cognitive levels of the ith student for the 1st, 2nd, and m′th knowledge points respectively. Z r The length of the audio and video materials of the preview content in the preview materials. Z′ r The preset threshold for the length of audio and video materials for preview content. T r It is the number of words in the text of the preview content in the preview materials. T′ r The preset threshold for the text length of the preview material. S r is the number of exercises in the preview homework in the preview materials. S′ r The threshold value for the number of exercises in the preview homework in the preview materials. α1、α2、α3、ε1、ε2、ε3、μ1、μ2、μ m 、∈1、∈2、∈3 is the power factor.

4. The method according to claim 1, characterized in that In step C, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the updated cognitive level of the teaching group on the course knowledge, a classroom courseware content generation model is used to generate classroom courseware with the highest matching degree with each knowledge point in the main text from the knowledge point explanation courseware library, wherein the design of the classroom courseware content generation model is as follows: in, F2 is the calculation result of the matching degree between the knowledge point courseware and the main text. E1, E2, E m′ They are the mastery requirements for the 1st, 2nd and m′ knowledge points of the main text respectively. The values ​​are divided into three levels according to the mastery requirements: e′, e″, e''', and e′>e″>e'''>0. Com1, Com2, Comm′ are respectively the degree of detail of the explanation of the 1st, 2nd, and m′th knowledge points in the main text in each knowledge point courseware (the degree of detail can be evaluated from the knowledge point's phonetic symbols, word meanings, usages, examples, etc.). K 1y The average frequency of the first knowledge point in the main text in professional direction y. K Com1y It is the average frequency of the knowledge point in the knowledge point courseware in professional direction y. N2 is the sum of the frequencies of all knowledge points under professional direction y. K 2z The average frequency of the second knowledge point in the main text in professional direction z. K Com2z It is the average frequency of the knowledge point in the knowledge point courseware in professional direction z. N3 is the sum of the frequencies of all knowledge points under professional direction z. K m′j is the average frequency of the m′th knowledge point in the main text in professional direction j. K Comm′j It is the average frequency of the knowledge point in the knowledge point courseware in professional direction j. Nm is the sum of the frequencies of all knowledge points under professional direction j. n is the total number of teaching groups. m is the total number of knowledge points contained in the main text. R′ 1i , R′ 2i , R′ m′i They are respectively the cognitive levels of the 1st, 2nd, and m′th knowledge points after the ith student has previewed the content. β1, β2, θ1, θ2, θ m , π1, π2, ∝1, ∝2, are weighting coefficients.

5. The method according to claim 1, characterized in that In the step D, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the updated cognitive level of the teaching group on the course knowledge, the homework content generation model is used to generate the homework with the highest matching degree with each knowledge point of the main text from the question library, wherein the homework content generation model is designed as follows: in, F3 is the calculation result of the matching degree between the after-class exercises and the main text. p is the total number of important and difficult knowledge points in the main text. p′ is the number of difficult and important knowledge points in the after-class exercises that are the same as those in the main text. E q is the mastery requirement of the qth same difficult and important knowledge point, and the value is divided into three levels according to the mastery requirement: e q ′、e q ″、e q ''', and e q ′>e q ′′>e q '''>0. u is the total number of general knowledge points in the main text. u′ is the number of general knowledge points in the after-class exercises that are the same as those in the main text. E v is the mastery requirement of the vth same general knowledge point, and the value is divided into three levels according to the mastery requirement: e v ′、e v ″、e v ''', and e v ′>e v > v '''>0. n is the total number of teaching groups. m is the total number of knowledge points contained in the main text. They are respectively the cognitive levels of the 1st, 2nd, and m′th knowledge points of the ith student after studying the classroom courseware. s means that the exercise is the sth question that contains a certain difficult knowledge point. S′ is the preset threshold for the number of questions for each difficult knowledge point. t means that the exercise is the tth question that contains a general knowledge point. T′ is the preset threshold for the number of questions for each general knowledge point. γ1、γ2、γ3、γ4、δ1、δ2、ω1、ω2、σ1、σ2、σ m 、t1、t2 is the weight coefficient.

6. The method according to claim 1, characterized in that In the step E, based on the mastery requirements of each knowledge point in the teaching stage in the knowledge point library and the final cognitive level of the teaching group on the course knowledge, the learning situation analysis and key and difficult point review model is used to diagnose the weak knowledge points of the teaching group and form a key and difficult point review report, wherein the learning situation analysis and key and difficult point review model is designed as follows: in, F4 is the result of the learning situation analysis. W1, W2, W m′ They are the mastery requirements for the 1st, 2nd and m′ knowledge points in this teaching stage respectively. The values ​​are divided into w′, w′′ and w''' according to the three levels of mastery requirements, and w′>w′′>w'''>0. n is the total number of teaching groups. m is the total number of knowledge points contained in the main text. are the cognitive levels of the 1st, 2nd, and m′th knowledge points after the i-th student completes his homework; ρ1, ρ2, ρ m is the weight coefficient.

7. The method according to any one of claims 3 to 6, characterized in that: The preview material content generation model, classroom courseware content generation model, after-class homework content generation model and learning situation analysis and key points review model are all content generation models based on artificial intelligence. The method updates the cognitive level of different teaching links by real-time analysis of student learning data, and dynamically adjusts the teaching content to achieve personalized learning and precise teaching.

8. An integrated English teaching system based on artificial intelligence, characterized in that: include: A digital resource library construction module is used to construct a digital resource library; A pre-class preview material generation module is used to generate pre-class preview materials with the highest matching degree with each knowledge point of the main text from the pre-class preview material library based on the main text of the textbook, the digital resource library and the initial cognitive level of the teaching group on the course knowledge; The first data collection and analysis module is used to collect and analyze students' learning data on the pre-class preview materials and update the teaching group's cognitive level of course knowledge; A classroom courseware generation module is used to generate classroom courseware with the highest matching degree with each knowledge point of the main text from the knowledge point explanation courseware library based on the main text, the digital resource library and the updated teaching group's cognitive level of course knowledge; The second data collection and analysis module is used to collect and analyze students' learning data on the classroom courseware, and to update the teaching group's cognitive level of the course knowledge again; A homework generation module is used to generate homework with the highest matching degree with each knowledge point of the main text from the digital resource library based on the mastery requirements of each knowledge point of the teaching stage in the digital resource library and the cognitive level of the teaching group on the course knowledge after the update again according to the main text; The third data collection and analysis module is used to collect and analyze students' learning data on the homework, and finally update the teaching group's cognitive level of course knowledge; A learning situation analysis module is used to determine the weak knowledge points of the teaching group based on the main text, the digital resource library and the final cognitive level of the teaching group on the course knowledge, and to form a review report on key and difficult points based on the weak knowledge points, so as to dynamically adjust the teaching content; A cyclic execution module is used to use the cognitive level of the teaching group on each knowledge point in the learning situation analysis report as the initial cognitive level of the next teaching link, and cyclically execute the functions of the pre-class preview material generation module to the learning situation analysis module.

9. An integrated English teaching system based on artificial intelligence, characterized in that: include: A memory for storing computer executable instructions; as well as, A processor, configured to implement the steps in the method according to any one of claims 1 to 6 when executing the computer executable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps in the method according to any one of claims 1 to 6 are implemented.

Images