English teaching management method and system based on semantic comprehension and cloud service

Through the English teaching management method based on semantic understanding and cloud services, combined with cloud teaching resource library and student data, personalized teaching solutions are generated, and the existing English teaching lacks personalization and flexibility are solved, and teaching efficiency and quality are improved.

CN120163688AActive Publication Date: 2025-06-17INNER MONGOLIA AGRICULTURAL UNIVERSITY
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202510225991.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-27
Publication Date
2025-06-17
Estimated Expiration
2045-02-27

AI Technical Summary

Technical Problem

The existing English teaching methods lack personalization and flexibility, and cannot be adjusted according to students' learning progress and personal needs, resulting in low teaching efficiency and quality.

Method used

Using the English teaching management method based on semantic understanding and cloud services, by establishing a cloud teaching resource library, students' learning model tendency data, English proficiency level data and interest point weight graph models are obtained, students' grouping and basic teaching plans are generated, and supplementary push content is generated based on real-time relevant information.

Benefits of technology

It realizes the personalization and pertinence of teaching content, improves teaching efficiency and quality, and enhances students' interest and participation in learning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120163688A_ABST
    Figure CN120163688A_ABST
Patent Text Reader

Abstract

The invention provides an English teaching management method and system based on semantic comprehension and cloud service, and relates to the field of electric data processing, and the method comprises the steps: building a cloud teaching resource library; determining a plurality of student groups according to the learning mode tendency data, the English ability level data and the interest point weight map model of the plurality of students, and generating a basic teaching scheme corresponding to the student groups; calling teaching resources from a cloud teaching resource library according to the basic teaching scheme corresponding to the student group, and pushing the corresponding teaching resources to the student terminals corresponding to the student group according to the teaching progress of the basic teaching scheme of the student group; and on the basis of the real-time related information and the learning mode tendency data, the English ability level data and the interest point weight map model of the plurality of students included in the student group, generating supplementary push content corresponding to the student group by using a semantic understanding technology, and pushing the supplementary push content to a student terminal corresponding to the student group. The device has the advantage of improving English teaching efficiency and quality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of electrical data processing, and in particular, to an English teaching management method and system based on semantic understanding and cloud services. Background Art

[0002] English is a universal language in the world. As one of the most widely spread official languages globally, it is the most advantageous tool for communicating with other countries. Therefore, with the development of society and the progress of economy, people's demand for English learning is increasing day by day.

[0003] The existing English teaching often adopts the most traditional teacher - led manual teaching, using textbooks for teaching. This teaching method requires a large number of English teachers and has high requirements for the teachers' own qualities. Teaching is restricted by factors such as venue, and cannot be more widely popularized and carried out. Moreover, the existing English teaching management may only focus on certain aspects of English learning, such as grammar or vocabulary, lacking flexibility and personalization, unable to be adjusted according to the students' learning progress and individual needs, and lacking comprehensive support for English learning, resulting in low efficiency and quality of English teaching.

[0004] Therefore, it is necessary to provide an English teaching management method and system based on semantic understanding and cloud services to improve the efficiency and quality of English teaching. Summary of the Invention

[0005] The present invention provides an English teaching management method based on semantic understanding and cloud services, including: establishing a cloud teaching resource library; obtaining learning mode preference data, English proficiency level data, and interest point weight graph models of multiple students; grouping the multiple students according to the learning mode preference data, English proficiency level data, and interest point weight graph models of the multiple students to determine multiple student groups; for each student group, generating a corresponding basic teaching plan according to the learning mode preference data, English proficiency level data, and interest point weight graph models of the multiple students included in the student group; for each student group, retrieving teaching resources from the cloud teaching resource library according to the basic teaching plan corresponding to the student group, and pushing the corresponding teaching resources to the student terminals corresponding to the student group according to the teaching progress of the basic teaching plan of the student group; obtaining real - time relevant information, where the real - time relevant information at least includes campus activity information and / or real - time news; for each student group, generating supplementary push content corresponding to the student group by using semantic understanding technology based on the real - time relevant information, the learning mode preference data, English proficiency level data, and interest point weight graph models of the multiple students included in the student group, and pushing the supplementary push content to the student terminals corresponding to the student group.

[0006] Further, obtain the learning mode preference data, English proficiency level data, and interest point weight map models of multiple students, including: obtaining the English learning test data of multiple students under various teaching methods, and generating the learning mode preference data of the students based on the English learning test data of the students; obtaining the vocabulary test data, reading test data, speaking test data, and writing test data of multiple students, and generating the English proficiency level data of the students based on the vocabulary test data, reading test data, speaking test data, and writing test data of the students; establishing the interest point weight map models of multiple sample students; obtaining the interest point test data of multiple students, and establishing the interest point weight map model of the students according to the interest point test data of the students and the interest point weight map models of multiple sample students.

[0007] Further, establish the interest point weight map models of multiple sample students, including: obtaining the interest point test data of multiple test students; dividing the multiple test students into multiple test student groups according to the interest point test data of the multiple test students; for each test student group, establishing the interest point weight map model of the sample students corresponding to the test student group based on the interest point test data of the multiple test students included in the test student group; establishing the interest point weight map model of the students according to the interest point test data of the students and the interest point weight map models of multiple sample students, including: establishing the initial interest point weight map model of the students according to the interest point test data of the students; determining the similar test student groups according to the interest point test data of the students and the interest point test data of the multiple test students included in each test student group; and complementing the initial interest point weight map model of the students based on the interest point weight map models of the sample students corresponding to the similar test student groups to establish the interest point weight map model of the students.

[0008] Furthermore, the oral test data of the student includes an oral pronunciation test audio and an oral dialogue test audio; based on the student's vocabulary test data, reading test data, oral test data, and writing test data, English proficiency level data of the student is generated, including: performing variational mode decomposition on the student's oral pronunciation test audio to extract the student's key voice features and pronunciation key features; based on the student's key voice features, obtaining a similar standard oral pronunciation audio from a standard oral pronunciation audio library; performing variational mode decomposition on the similar standard oral pronunciation audio to extract the standard pronunciation key features; determining the student's oral pronunciation level based on the student's pronunciation key features and the standard pronunciation key features; determining the student's oral vocabulary features through a vocabulary recognition model according to the student's oral dialogue test audio; determining the student's oral grammar features through a grammar recognition model according to the student's oral dialogue test audio; determining the dialogue emotion features of the student through an emotion recognition model according to the student's oral dialogue test audio; determining the student's oral dialogue level according to the student's oral vocabulary features, oral grammar features, and dialogue emotion features, wherein the English proficiency level data of the student at least includes the student's oral pronunciation level and oral dialogue level.

[0009] Furthermore, according to the learning mode preference data, English proficiency level data, and interest point weight map model of multiple students, the multiple students are grouped to determine multiple student groups, including: for any two students, calculating the similarity of the interest point weight map models of the two students according to the interest point weight map models of the two students; performing a first grouping on the multiple students according to the similarity of the interest point weight map models of any two students to determine multiple first student groups; for each first student group, calculating the similarity of the English proficiency levels of any two students according to the English proficiency level data of any two students included in the first student group, and performing a second grouping on the multiple students included in the first student group according to the similarity of the English proficiency levels of any two students to determine multiple second student groups; for each second student group, calculating the similarity of the learning mode preferences of any two students according to the learning mode preference data of any two students included in the second student group, and performing a third grouping on the multiple students included in the second student group according to the similarity of the learning mode preferences of any two students to determine multiple student groups.

[0010] Further, based on the learning mode preference data, English proficiency level data, and interest point weight map model of multiple students included in the student group, a basic teaching plan corresponding to the student group is generated, including: determining the target teaching method corresponding to the student group according to the learning mode preference data of multiple student terminals included in the student group; determining multiple target English knowledge points corresponding to the student group according to the English proficiency level data of multiple student terminals included in the student group; generating the basic teaching plan corresponding to the student group according to the interest point weight map model and multiple target English knowledge points of multiple students included in the student group, where the basic teaching plan at least includes the target English knowledge points, target teaching methods, and teaching objectives at multiple teaching time nodes.

[0011] Further, real-time relevant information is obtained, including: determining a first target website, and obtaining candidate campus activity information from the first target website based on web crawler technology; determining a second target website, and obtaining candidate real-time news from the second target website based on web crawler technology; screening the candidate campus activity information and candidate real-time news to determine effective campus activity information and effective real-time news.

[0012] Further, screening the candidate campus activity information and candidate real-time news to determine effective campus activity information and effective real-time news includes: for each student group, generating a group interest point weight map model corresponding to the student group according to the interest point weight map model of multiple students included in the student group; determining the interest points corresponding to the candidate campus activity information; determining the interest points corresponding to the candidate real-time news; screening the candidate campus activity information and candidate real-time news according to the group interest point weight map model corresponding to each student group, the interest points corresponding to the candidate campus activity information, and the interest points corresponding to the candidate real-time news to determine effective campus activity information and effective real-time news.

[0013] Further, based on the real-time relevant information and the learning mode preference data, English proficiency level data, and interest point weight map model of multiple students included in the student group, supplementary push content corresponding to the student group is generated using semantic understanding technology and pushed to the student terminals corresponding to the student group, including: for each student group, determining target campus activity information or target real-time news based on the interest points corresponding to the effective campus activity information or the interest points corresponding to the effective real-time news, generating an English reading article based on the target campus activity information or target real-time news using semantic understanding technology based on the English proficiency level data of multiple students included in the student group, converting the English reading article into supplementary push content based on the learning mode preference data of multiple students included in the student group, and pushing the supplementary push content to the student terminals corresponding to the student group.

[0014] The present invention provides an English teaching management system based on semantic understanding and cloud services, which is applied to the above-mentioned English teaching management method based on semantic understanding and cloud services, and includes: a resource management module for establishing a cloud teaching resource library; a teaching management module for obtaining learning mode preference data, English proficiency level data, and interest point weight map models of multiple students; grouping the multiple students according to the learning mode preference data, English proficiency level data, and interest point weight map models of the multiple students to determine multiple student groups; for each student group, generating a corresponding basic teaching plan according to the learning mode preference data, English proficiency level data, and interest point weight map models of the multiple students included in the student group; for each student group, retrieving teaching resources from the cloud teaching resource library according to the corresponding basic teaching plan of the student group, and pushing the corresponding teaching resources to the student terminals corresponding to the student group according to the teaching progress of the basic teaching plan of the student group; an information acquisition module for obtaining real-time relevant information, where the real-time relevant information at least includes campus activity information and / or real-time news; the teaching management module is further configured to, for each student group, generate supplementary push content corresponding to the student group by using semantic understanding technology based on the real-time relevant information and the learning mode preference data, English proficiency level data, and interest point weight map models of the multiple students included in the student group, and push the supplementary push content to the student terminals corresponding to the student group.

[0015] Compared with the prior art, the English teaching management method and system based on semantic understanding and cloud services provided by the present invention at least have the following beneficial effects: 1. By collecting students' learning habits, English proficiency levels, and interest point data, it is possible to more accurately understand the needs of each student. Grouping students based on these data and formulating a basic teaching plan for each group makes teaching more in line with the actual situation of students, improving the personalization and pertinence of teaching. The establishment of the cloud teaching resource library enables centralized management and efficient utilization of teaching resources. It can automatically retrieve appropriate teaching resources from the resource library according to the basic teaching plans of each student group, avoiding waste of resources and repetitive labor. By pushing teaching resources that conform to the basic teaching plans of different student groups to the student terminals, it can ensure that each student can obtain teaching content that matches their ability level, thereby effectively improving the learning effect. The introduction of real-time relevant information, such as campus activity information and real-time news, can enrich teaching content and enhance students' learning interest and participation.

[0016] 2. By integrating test data in multiple aspects such as vocabulary, reading, speaking, and writing, the comprehensive English ability of students can be evaluated more comprehensively, avoiding the one-sidedness brought by a single test. By performing variational mode decomposition on the audio of students' spoken pronunciation tests, the key voice features and pronunciation key features of students can be accurately extracted, thus helping students and teachers quickly locate pronunciation problems, such as deficiencies in pitch, volume, speech rate, etc. By comparing the pronunciation key features of students with the standard pronunciation key features, the spoken pronunciation level of students can be objectively and quantitatively evaluated, providing a scientific basis for teaching. Using vocabulary recognition, grammar recognition, and emotion recognition models, the spoken vocabulary features, grammar features, and dialogue emotion features of students can be further analyzed, thereby comprehensively evaluating the spoken dialogue level of students. This helps students improve the fluency, accuracy, and authenticity of their spoken expressions.

[0017] 3. According to the test data of students' interest points, an initial interest point weight map model of students is established; according to the test data of students' interest points and the test data of the interest points of multiple test students included in each test student group, similar test student groups are determined; based on the interest point weight map model of the sample students corresponding to the similar test student groups, the initial interest point weight map model of students can be complemented to establish a more accurate and complete interest point weight map model of students, providing more accurate data support for subsequent grouping and the generation of English teaching plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] This specification will be further described in the form of exemplary embodiments, and these exemplary embodiments will be described in detail through the drawings. These embodiments are not restrictive. In these embodiments, the same numbers represent the same structures, where: Figure 1 is a schematic flowchart of an English teaching management method based on semantic understanding and cloud services according to some embodiments of this specification; Figure 2 is a schematic diagram of an interest point weight map model according to some embodiments of this specification; Figure 3 is a schematic diagram of the modules of an English teaching management system based on semantic understanding and cloud services according to some embodiments of this specification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] To more clearly illustrate the technical solutions of the embodiments of this specification, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the drawings represent the same structure or operation.

[0020] Figure 1 It is a schematic flowchart of a method for English teaching management based on semantic understanding and cloud services shown in some embodiments of this specification. As Figure 1 shown, a method for English teaching management based on semantic understanding and cloud services may include the following steps.

[0021] Step 110, establish a cloud teaching resource library.

[0022] Specifically, the cloud teaching resource library is a collection covering a variety of resources and tools, aiming to help teachers teach English more effectively, and at the same time provide students with richer and more diverse learning materials. The cloud teaching resource library can run based on cloud services.

[0023] Only as an example, the cloud teaching resource library may include the following resources: 1. Textbooks and course materials: Official English textbooks: including various English textbooks published at home and abroad, such as Oxford English, New Concept English, etc.

[0024] Self-compiled or customized textbooks: textbooks written according to specific teaching objectives and student needs.

[0025] Course outlines and lesson plans: documents that detail teaching objectives, teaching steps, assessment methods, etc.

[0026] 2. Multimedia teaching resources: Video materials: such as English movies, documentaries, TED talks, English teaching videos, etc.

[0027] Audio materials: English songs, podcasts, listening practice materials, voice textbooks, etc.

[0028] Interactive software and applications: online English learning platforms, grammar practice software, pronunciation training tools, etc.

[0029] 3. Reading and writing resources: Extra-curricular reading materials: English novels, essays, news reports, popular science articles, etc.

[0030] Writing templates and model essays: templates for various English writing genres, as well as excellent English writing examples.

[0031] Vocabulary and Grammar Workbook: Materials containing vocabulary memorization, grammar explanations, and exercises.

[0032] 4. Listening and Speaking Resources: Listening Training Materials: Dialogue recordings, news broadcasts, simulated phone conversations, etc.

[0033] Oral Practice Activities: Interactive oral practice such as role-playing, group discussions, debates, etc.

[0034] Pronunciation and Intonation Training: Professional guidance and practice for English pronunciation and intonation.

[0035] 5. Testing and Evaluation Tools: Unit Tests and Final Exam Papers: Papers used to test students' phased learning achievements.

[0036] Proficiency Tests: Sample questions and analyses of international standard English tests such as TOEFL and IELTS.

[0037] Oral and Listening Evaluation Software: An online testing tool that can automatically score and give feedback.

[0038] Step 120: Obtain data on the learning mode preferences, English proficiency levels, and interest point weight maps of multiple students.

[0039] In some embodiments, Step 120 specifically includes: Obtain the English learning test data of multiple students under various teaching methods, and generate data on the learning mode preferences of students based on the English learning test data of the students; Obtain the vocabulary test data, reading test data, oral test data, and writing test data of multiple students, and generate data on the English proficiency levels of students based on the vocabulary test data, reading test data, oral test data, and writing test data of the students. Among them, the oral test data of the students includes the oral pronunciation test audio and the oral dialogue test audio. An English short passage to be read aloud can be displayed, and the oral pronunciation test audio of the students reading the displayed English short passage can be obtained through an audio acquisition device. The oral dialogue test audio during the oral dialogue process can be obtained through an oral dialogue model and by having a conversation with the students through an audio acquisition device; Establish an interest point weight map model for multiple sample students; Obtain the interest point test data of multiple students, and establish an interest point weight map for the students based on the interest point test data of the students and the interest point weight map model of multiple sample students. For example, the interest point test data of the students can be obtained through a questionnaire.

[0040] As an example, the English learning test data of multiple students under various teaching methods can be obtained through the following steps, and based on the English learning test data of the students, the learning mode preference data of the students can be generated: S11. Determine the test content and methods: Design English test questions covering multiple aspects such as listening, speaking, reading, and writing to ensure that the English abilities of students can be comprehensively evaluated.

[0041] According to different teaching methods (such as traditional lectures, group discussions, project-based learning, etc.), design corresponding test scenarios and tasks.

[0042] S12. Organize the test: Conduct English learning tests on multiple students under different teaching methods.

[0043] Ensure the standardization of the test process to reduce errors.

[0044] S13. Collect data: Record the performance of students in various tests, including scores, answering times, error types, etc.

[0045] S14. Data preprocessing: Clean and organize the collected data to remove invalid or abnormal data.

[0046] Standardize the data for subsequent analysis.

[0047] S15. Analysis of learning mode preference: Analyze the learning mode preference of students based on their test performance under different teaching methods.

[0048] For example, by observing the participation and performance of students in group discussions, it can be judged whether they tend to cooperative learning; by analyzing the completion of students in project-based learning, their autonomous learning and problem-solving abilities can be evaluated.

[0049] S16. Generate learning mode preference data: Use data analysis tools (such as SPSS, Excel, etc.) to quantitatively process the learning mode preference of students.

[0050] According to the quantification results, students are divided into different learning mode preference types, such as self-directed learning type, cooperative learning type, inquiry learning type, etc. Among them, self-directed learning type students tend to study independently and like to explore new knowledge by themselves. In tests, they may show strong problem-solving abilities and high accuracy rates. Cooperative learning type students are good at cooperating with others and deepening their understanding of knowledge through discussion and communication. In group discussions or team projects, they may show high participation and collaboration abilities. Inquiry learning type students like to explore new knowledge through practice, focusing on hands-on operation and experimental verification. In project-based learning, they may show strong innovation abilities and problem-solving abilities.

[0051] The vocabulary test data, reading test data, speaking test data, and writing test data of multiple students can be obtained in the following ways. Based on the vocabulary test data, reading test data, speaking test data, and writing test data of students, the English proficiency level data of students can be generated: 1. Vocabulary test data Test tool: Use standardized vocabulary test tools, such as vocabulary scales or online test platforms.

[0052] Test method: Let students identify or explain the meanings of given words, or require students to select words that match a specific definition or picture from a group of words.

[0053] Data record: Record the number of words correctly identified by students and their performance at different difficulty levels.

[0054] 2. Reading test data Test materials: Select reading materials suitable for students' levels, covering different types of texts (such as stories, expository texts, argumentative texts, etc.).

[0055] Test method: Set reading comprehension questions and require students to answer questions about the content of the article, or perform information extraction and reasoning judgments.

[0056] Data record: Record the students' answering speed and accuracy rate, as well as their performance on different types of questions.

[0057] 3. Speaking test data Test form: Adopt forms such as role-playing, impromptu speech, and dialogue simulation.

[0058] Scoring criteria: Evaluate according to aspects such as pronunciation, fluency, grammar accuracy, vocabulary richness, and language organization ability.

[0059] Data record: Use a recording device to record the students' speaking performance, and have teachers or speaking scoring models score according to the scoring criteria.

[0060] 4. Writing Test Data Test task: Assign writing topics and require students to write short essays, argumentative essays, stories, etc.

[0061] Scoring criteria: Evaluate according to aspects such as content quality, structural clarity, language expression accuracy, vocabulary richness, and creativity.

[0062] Data recording: Collect students' written works and have teachers or writing scoring models score them according to the scoring criteria.

[0063] Integrate the performance data of students in vocabulary tests, reading tests, speaking tests, and writing tests into a database. If the data dimensions of different tests are different (such as the vocabulary test is a quantity, while the speaking test is a score), standardization processing is required for comparison and comprehensive analysis. According to the importance of the tests and the overall assessment requirements of students' English abilities, assign appropriate weights to the data of each test. Based on the weight assignment and students' performance in each test, calculate the comprehensive English proficiency score of students.

[0064] Preferably, based on the vocabulary test data, reading test data, speaking test data, and writing test data of students, generate students' English proficiency data, including: Perform variational mode decomposition on the speaking pronunciation test audio of students to extract the key voice features and pronunciation key features of students; Based on the key voice features of students, obtain similar standard speaking pronunciation audio from the standard speaking pronunciation audio library, where the standard speaking pronunciation audio library includes the standard speaking pronunciation audio of different professional language teachers and phoneticians, containing the speaking pronunciation demonstrations of clear and accurate English short passages to be read aloud; Perform variational mode decomposition on the similar standard speaking pronunciation audio to extract the standard pronunciation key features; Based on the pronunciation key features of students and the standard pronunciation key features, determine the speaking pronunciation level of students; Determine the speaking vocabulary features of students through a vocabulary recognition model according to the speaking dialogue test audio of students; Determine the speaking grammar features of students through a grammar recognition model according to the speaking dialogue test audio of students; Determine the dialogue emotion features of students through an emotion recognition model according to the speaking dialogue test audio of students; According to the speaking vocabulary features, speaking grammar features, and dialogue emotion features of students, determine the speaking dialogue level of students, where the English proficiency data of students includes at least the speaking pronunciation level and the speaking dialogue level of students.

[0065] Specifically, the key voice features of students can be extracted according to the following formula: S21. For each standard spoken pronunciation audio, perform variational mode decomposition on the standard spoken pronunciation audio to generate multiple intrinsic mode functions corresponding to the standard spoken pronunciation audio; S22. Determine multiple candidate variational mode decomposition factors (for example, mean of central frequency, standard deviation of central frequency, mean of bandwidth, standard deviation of bandwidth, mean of instantaneous frequency change rate, standard deviation of instantaneous frequency change rate, etc.); S23. For each standard spoken pronunciation audio, determine the eigenvalue corresponding to each candidate variational mode decomposition factor according to the multiple intrinsic mode functions corresponding to the standard spoken pronunciation audio; S24. For each candidate variational mode decomposition factor, calculate the factor difference value corresponding to the candidate variational mode decomposition factor according to the eigenvalue of each standard spoken pronunciation audio corresponding to the candidate variational mode decomposition factor, and use the candidate variational mode decomposition factor with the factor difference value greater than the factor difference value threshold as the key variational mode decomposition factor; S25. Perform variational mode decomposition on the student's spoken pronunciation test audio to generate multiple intrinsic mode functions corresponding to the student's spoken pronunciation test audio; S26. Determine the eigenvalue corresponding to each key variational mode decomposition factor according to the multiple intrinsic mode functions corresponding to the student's spoken pronunciation test audio, where the student's key voice features may include the eigenvalues corresponding to each key variational mode decomposition factor.

[0066] For example, the factor difference value corresponding to the candidate variational mode decomposition factor can be calculated according to the following formula: , where, is the factor difference value corresponding to the th candidate variational mode decomposition factor, is the eigenvalue of the nth standard spoken pronunciation audio corresponding to the ith candidate variational mode decomposition factor, is the total number of standard spoken pronunciation audios.

[0067] The voice similarity between the standard spoken pronunciation audio and the student's spoken pronunciation test audio can be calculated according to the following formula: , where, is the voice similarity between the mth standard spoken pronunciation audio and the student's spoken pronunciation test audio, is the eigenvalue of the mth standard spoken pronunciation audio corresponding to the ith key variational mode decomposition factor, is the eigenvalue of the student's spoken pronunciation test audio corresponding to the ith key variational mode decomposition factor, is the total number of key variational mode decomposition factors.

[0068] The standard spoken pronunciation audio with the greatest voice similarity can be used as the similar standard spoken pronunciation audio.

[0069] Specifically, multiple intrinsic mode function characteristic factors (such as center frequency, bandwidth, energy distribution, amplitude, phase, instantaneous frequency, etc.) can be determined. According to the multiple intrinsic mode function characteristic factors, key pronunciation features are extracted from the student's spoken pronunciation test audio. Among them, the key pronunciation features can include the eigenvalues of each intrinsic mode function of the student's spoken pronunciation test audio corresponding to each intrinsic mode function characteristic factor. According to the multiple intrinsic mode function characteristic factors, standard pronunciation key features are extracted from the similar standard spoken pronunciation audio. The standard pronunciation key features can include the eigenvalues of each intrinsic mode function of the similar standard spoken pronunciation audio corresponding to each intrinsic mode function characteristic factor.

[0070] The spoken pronunciation level of the student can be determined by a spoken pronunciation level recognition model based on the student's key pronunciation features and standard pronunciation key features. Among them, the spoken pronunciation level recognition model can be a convolutional neural network model.

[0071] Specifically, variational mode decomposition can decompose the spoken pronunciation test audio into multiple intrinsic mode functions, and each intrinsic mode function corresponds to a specific frequency component or voice feature. By determining the key variational mode decomposition factors and determining the similar standard spoken pronunciation audio according to the key variational mode decomposition factors, the standard spoken pronunciation audio that is relatively similar to the student's voice can be determined. The interference information of the subsequent spoken pronunciation level is reduced, and the accuracy of the spoken pronunciation level evaluation is improved.

[0072] Moreover, through variational mode decomposition, the student's key voice features and key pronunciation features can be accurately extracted, such as the clarity of vowels, the pronunciation strength of consonants, the ups and downs of intonation, etc. The standard spoken pronunciation audio library consists of the standard spoken pronunciation audios of different professional language teachers and phoneticians, and these audios are clear and accurate and can be used as the benchmark for evaluation. Through the comparative analysis with the standard pronunciation audio, the spoken pronunciation level of the student can be objectively and accurately evaluated, and it is easier to find the problems existing in the student's pronunciation, such as inaccurate pronunciation of certain vowels, too heavy or too light pronunciation of consonants, etc.

[0073] The spoken vocabulary recognition model is located between acoustic signal segmentation and concept access. It is a process of establishing connections between segmented acoustic signals and vocabulary in long-term memory to recognize vocabulary. In the audio of students' spoken dialogue tests, the vocabulary recognition model can recognize the vocabulary used by students and classify and count them. Through the vocabulary recognition model, the total vocabulary used by students in spoken dialogue can be counted, as well as the number of vocabulary in different categories (such as nouns, verbs, adjectives, etc.). Analyze whether the vocabulary used by students is rich and diverse, and whether it contains advanced vocabulary or technical terms. Evaluate whether the vocabulary used by students is accurate and whether there are any misuses or confusions.

[0074] The grammar recognition model can analyze the sentence structure, grammar rules, word order, etc. in students' spoken dialogue. Through tools such as syntax trees and dependency trees, the spoken dialogue of students can be converted into sentences with clear grammar structures for further analysis. Analyze the types of sentences used by students (such as simple sentences, compound sentences, etc.) and the complexity of sentence structures. Evaluate whether students follow correct grammar rules, such as tenses, voices, subject-verb agreement, etc. Check whether the word order of students is correct and whether it conforms to the grammar habits of Chinese.

[0075] The emotion recognition model can analyze the emotional expressions in students' spoken dialogue, such as nervousness, calmness, excitement, embarrassment, etc. The emotion recognition model can identify the emotional tendency of students in the dialogue through methods such as vocabulary-based methods (such as sentiment dictionary method), sentence structure analysis, dependency analysis, and machine learning algorithms. Among them, the spoken vocabulary recognition model, grammar recognition model, and emotion recognition model can all be long short-term memory network models.

[0076] The spoken language evaluation model can determine the spoken dialogue level of students based on the spoken vocabulary features output by the spoken vocabulary recognition model, the spoken grammar features output by the grammar recognition model, and the dialogue emotion features output by the emotion recognition model. Among them, the spoken language evaluation model can be a convolutional neural network model.

[0077] In some embodiments, an interest point weight map model of multiple sample students is established, including: Obtain the interest point test data of multiple test students; According to the interest point test data of multiple test students, divide the multiple test students into multiple test student groups; For each test student group, based on the interest point test data of multiple test students included in the test student group, establish an interest point weight map model of the corresponding sample students of the test student group.

[0078] Specifically, first, it is necessary to clarify the specific meaning and scope of "points of interest", which can include academic fields (such as mathematics, science, literature, art, etc.), extracurricular activities (such as sports, music, programming, etc.), specific topics (such as environmental protection, space exploration, etc.) or any other aspects related to students' interests. According to the definition of points of interest, design a questionnaire or scale that contains a series of questions or statements related to these points of interest. The questions can be in the form of multiple-choice questions, ranking questions, rating questions, etc., in order to test students' preference levels for different points of interest. Distribute the designed questionnaire to the test students through channels such as schools, classes, online platforms, etc. Ensure that the distribution scope of the questionnaire covers all student groups to be tested. The questionnaire data collected needs to be entered into a spreadsheet or database for subsequent analysis and processing. During the data entry process, pay attention to maintaining the accuracy and integrity of the data. Check whether there are problems such as missing values, outliers or duplicate values in the data. For missing values, methods such as interpolation, mean substitution or deletion can be tried; for outliers, it is necessary to determine whether they are data that truly reflect students' interests or are caused by misoperations or data entry errors. Quantify the preference levels of the test students for different points of interest into numerical values, and determine the preference values of the test students for different points of interest.

[0079] For any two test students, the interest preference similarity between the two test students can be calculated based on the preference values of the two test students for different points of interest.

[0080] For example, the interest preference similarity between two test students can be calculated according to the following formula: , where, is the interest preference similarity between the i-th test student and the j-th test student, is the interest preference similarity of the i-th test student for the k-th point of interest, is the interest preference similarity of the j-th test student for the k-th point of interest, is the total number of points of interest.

[0081] Through the mean clustering algorithm, cluster multiple test students according to the interest preference similarity between any two test students, and divide the multiple test students into multiple test student groups.

[0082] For each test student group, the weight corresponding to each point of interest can be calculated according to the following formula: , where, is the weight corresponding to the g-th point of interest, is the preference value of the e-th test student included in the test student group for the g-th point of interest, To test the total number of test students included in the student group, is the total number of points of interest.

[0083] By way of example only, Figure 2 is a schematic diagram of the point-of-interest weight graph model shown in some embodiments of this specification. As Figure 2 shown, the point-of-interest weight graph model may include nodes representing points of interest and nodes representing students. The nodes representing points of interest and the nodes representing students are connected by edges, and the weight of the edge represents the weight corresponding to the point of interest.

[0084] In some embodiments, based on the point-of-interest test data of the student and the point-of-interest weight graph models of multiple sample students, a point-of-interest weight graph model of the student is established, including: Based on the point-of-interest test data of the student, an initial point-of-interest weight graph model of the student is established; Based on the point-of-interest test data of the student and the point-of-interest test data of multiple test students included in each test student group, a similar test student group is determined; Based on the point-of-interest weight graph models of the sample students corresponding to the similar test student groups, the initial point-of-interest weight graph model of the student is complemented to establish a point-of-interest weight graph model of the student.

[0085] Specifically, based on the point-of-interest test data of the student, the preference values of the student for different points of interest are determined, and the points of interest with preference values greater than the preference value threshold are used as the target points of interest of the student. According to the preference value of the student for the target points of interest and the average preference value of multiple test students included in the test student group for the target points of interest, the matching value of the test student group is calculated, and the test student group with a matching value greater than the matching value threshold is used as the similar test student group. The calculation method of the matching value is similar to the calculation method of the interest preference similarity of two test students, and will not be elaborated here.

[0086] Based on the point-of-interest weight graph models of the sample students corresponding to the similar test student groups and the matching value of each test student group, the initial point-of-interest weight graph model of the student is complemented by a weight graph complementation model to establish a point-of-interest weight graph model of the student, where the weight graph complementation model may be a convolutional neural network model.

[0087] Step 130, based on the learning mode preference data, English proficiency level data, and point-of-interest weight graph models of multiple students, group the multiple students to determine multiple student groups.

[0088] In some embodiments, step 130 specifically includes: For any two students, based on the point-of-interest weight graph models of the two students, calculate the similarity of the point-of-interest weight graph models of the two students; Group multiple students for the first time according to the similarity of the interest point weight graph models of any two students, and determine multiple first student groups. For example, the K-means clustering algorithm can be used to group multiple students for the first time according to the similarity of the interest point weight graph models of any two students, and determine multiple first student groups; For each first student group, calculate the English proficiency similarity of any two students according to the English proficiency data of any two students included in the first student group. According to the English proficiency similarity of any two students, group the multiple students included in the first student group for the second time, and determine multiple second student groups. For example, the K-means clustering algorithm can be used to group the multiple students included in the first student group for the second time according to the English proficiency similarity of any two students included in the first student group, and determine multiple second student groups; For each second student group, calculate the learning mode preference similarity of any two students according to the learning mode preference data of any two students included in the second student group. According to the learning mode preference similarity of any two students, group the multiple students included in the second student group for the third time, and determine multiple student groups. For example, the K-means clustering algorithm can be used to group the multiple students included in the second student group for the third time according to the learning mode preference similarity of any two students included in the second student group, and determine multiple student groups.

[0089] For example, the similarity of the interest point weight graph models of two students can be calculated according to the following formula: , where, is the similarity of the interest point weight graph models of the i-th student and the j-th student, is the weight corresponding to the g-th interest point in the interest point weight graph model of the i-th student, is the weight corresponding to the g-th interest point in the interest point weight graph model of the j-th student.

[0090] Step 140: For each student group, generate a corresponding basic teaching plan according to the learning mode preference data, English proficiency data, and interest point weight graph models of the multiple students included in the student group.

[0091] In some embodiments, step 140 specifically includes: Determine the target teaching method corresponding to the student group according to the learning mode preference data of the multiple student terminals included in the student group; Determine multiple target English knowledge points corresponding to the student group according to the English proficiency data of the multiple student terminals included in the student group; Generate a basic teaching plan corresponding to the student group based on the interest point weight map model of multiple students included in the student group and multiple target English knowledge points. The basic teaching plan includes at least the target English knowledge points, target teaching methods, and teaching objectives at multiple teaching time nodes.

[0092] Specifically, determine the most suitable teaching method for the entire student group according to the learning mode preference data of each member in the student group (i.e., multiple student terminals). Learning mode preferences may include different types such as visual learners, auditory learners, and hands-on practitioners. For example, if most students in a student group are visual learners, the teaching method may focus on visual materials such as charts and videos.

[0093] Determine the specific English knowledge points that they need to master or improve together according to the English proficiency level data of each student in the student group. These knowledge points may include grammar rules, vocabulary expansion, reading comprehension skills, etc. By analyzing the students' proficiency levels, the system can identify the common weaknesses or areas that need to be strengthened in the student group, and thus use these areas as target English knowledge points. After determining the target teaching method and target English knowledge points, Generate a basic teaching plan through a plan generation model based on the interest point weight map model of the students and these knowledge points. By combining the students' interest points with the target knowledge points, design a teaching plan that not only meets the learning objectives but also stimulates the students' interest. This plan includes at least the target English knowledge points arranged at different teaching time nodes, the corresponding teaching methods, and the expected teaching objectives. Among them, the plan generation model can be a convolutional neural network model.

[0094] Step 150, for each student group, retrieve teaching resources from the cloud teaching resource library according to the basic teaching plan corresponding to the student group, and push the corresponding teaching resources to the student terminals corresponding to the student group according to the teaching progress of the basic teaching plan of the student group.

[0095] Specifically, formulate a reasonable push plan according to the teaching progress of the basic teaching plan of the student group. The push plan will clarify the teaching resources to be pushed at each teaching time node, their types, quantities, etc. Automatically push the corresponding teaching resources to the student terminals according to the push plan to ensure that students can obtain the required learning materials in a timely manner.

[0096] Step 160, obtain real-time relevant information.

[0097] The real-time relevant information includes at least campus activity information and / or real-time news.

[0098] In some embodiments, step 160 specifically includes: Determine the first target website, and obtain candidate campus activity information from the first target website (e.g., the campus official website) based on web crawler technology; Determine the second target website, and obtain candidate real-time news from the second target website (e.g., the news release website) based on web crawler technology; Screen the candidate campus activity information and the candidate real-time news to determine the valid campus activity information and the valid real-time news.

[0099] In some embodiments, screening the candidate campus activity information and the candidate real-time news to determine the valid campus activity information and the valid real-time news includes: For each student group, generate a group interest point weight graph model corresponding to the student group according to the interest point weight graph models of multiple students included in the student group, and perform weighted summation on the interest point weight graph models of multiple students included in the student group to generate a group interest point weight graph model corresponding to the student group; Determine the interest points corresponding to the candidate campus activity information; Determine the interest points corresponding to the candidate real-time news; According to the group interest point weight graph model corresponding to each student group, the interest points corresponding to the candidate campus activity information, and the interest points corresponding to the candidate real-time news, screen the candidate campus activity information and the candidate real-time news to determine the valid campus activity information and the valid real-time news.

[0100] Specifically, determine whether there is a weight of the interest points corresponding to the candidate campus activity information and the interest points corresponding to the candidate real-time news in at least one group interest point weight graph model corresponding to the student group that is greater than the weight threshold. If so, determine them as the valid campus activity information and the valid real-time news.

[0101] Step 170, for each student group, based on the real-time relevant information, the learning mode preference data, the English proficiency level data, and the interest point weight graph model of multiple students included in the student group, use semantic understanding technology to generate supplementary push content corresponding to the student group, and push the supplementary push content to the student terminals corresponding to the student group.

[0102] In some embodiments, step 170 specifically includes: For each student group, based on the interest points corresponding to the valid campus activity information or the interest points corresponding to the valid real-time news, determine the target campus activity information or the target real-time news, use semantic understanding technology based on the English proficiency level data of multiple students included in the student group, generate an English reading article according to the target campus activity information or the target real-time news, and based on the learning mode preference data of multiple students included in the student group, convert the English reading article into supplementary push content, and push the supplementary push content to the student terminals corresponding to the student group.

[0103] Specifically, advanced semantic understanding technology is utilized to process target campus activity information or target real-time news. The semantic understanding technology can deeply analyze the text content, extract key information, and generate a coherent and logical English reading article based on this information. When generating the article, the English proficiency level data of the student group is fully considered. According to factors such as the students' vocabulary and grammar mastery, the difficulty of the article is adjusted to ensure that the article is both challenging and easy to understand.

[0104] After generating the English reading article, it is transformed into supplementary push content suitable for different learning methods according to the learning mode preference data of the student group. For example, for visual learners, the article is transformed into the form of charts, pictures or videos; for auditory learners, an audio reading version may be provided, etc.

[0105] The generated supplementary push content is pushed to the corresponding student terminals of the student group through appropriate means (such as online download, email sending, in-app notification, etc.). The pushing process should ensure the timeliness and accuracy of the content so that students can obtain and read these supplementary materials in a timely manner.

[0106] Figure 3 It is a schematic diagram of the modules of an English teaching management system based on semantic understanding and cloud services shown in some embodiments of this specification. As Figure 3 shown, an English teaching management system based on semantic understanding and cloud services may include a resource management module, a teaching management module, and an information acquisition module.

[0107] The resource management module is used to establish a cloud teaching resource library; The teaching management module is used to obtain the learning mode preference data, English proficiency level data, and interest point weight map models of multiple students; group the multiple students according to the learning mode preference data, English proficiency level data, and interest point weight map models of the multiple students to determine multiple student groups; for each student group, generate a corresponding basic teaching plan for the student group according to the learning mode preference data, English proficiency level data, and interest point weight map models of the multiple students included in the student group; for each student group, retrieve teaching resources from the cloud teaching resource library according to the corresponding basic teaching plan of the student group, and push the corresponding teaching resources to the corresponding student terminals of the student group according to the teaching progress of the basic teaching plan of the student group; The information acquisition module is used to obtain real-time relevant information, where the real-time relevant information at least includes campus activity information and / or real-time news; The teaching management module is also used for each student group to generate corresponding supplementary push content for the student group by using semantic understanding technology based on the real-time relevant information and the learning mode preference data, English proficiency level data, and interest point weight map models of the multiple students included in the student group, and push the supplementary push content to the corresponding student terminals of the student group.

[0108] An English teaching management system based on semantic understanding and cloud services can be used to execute an English teaching management method based on semantic understanding and cloud services, which will not be elaborated here.

[0109] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. An English teaching management method based on semantic understanding and cloud services, characterized in that: include: Establish a cloud-based teaching resource library; Obtain learning pattern tendency data, English proficiency level data and interest point weight graph model of multiple students; According to the learning pattern tendency data, English proficiency level data and interest point weight graph model of the plurality of students, the plurality of students are grouped to determine a plurality of student groups; For each student group, a basic teaching plan corresponding to the student group is generated according to the learning pattern tendency data, English proficiency level data and interest point weight graph model of the multiple students included in the student group; For each student group, the teaching resources are retrieved from the cloud teaching resource library according to the basic teaching plan corresponding to the student group, and the corresponding teaching resources are pushed to the student terminal corresponding to the student group according to the teaching progress of the basic teaching plan of the student group; Acquire real-time related information, wherein the real-time related information at least includes campus activity information and / or real-time news; For each student group, based on real-time relevant information and the learning pattern tendency data, English proficiency level data and interest point weight graph model of multiple students included in the student group, semantic understanding technology is used to generate supplementary push content corresponding to the student group, and the supplementary push content is pushed to the student end corresponding to the student group.

2. The English teaching management method based on semantic understanding and cloud service according to claim 1 is characterized in that: Obtain learning pattern tendency data, English proficiency level data and interest point weight graph model of multiple students, including: Obtain English learning test data of multiple students under various teaching methods, and generate students' learning pattern tendency data based on the students' English learning test data; Acquire vocabulary test data, reading test data, oral test data and writing test data of multiple students, and generate English proficiency level data of the students based on the vocabulary test data, reading test data, oral test data and writing test data of the students; Establish a weighted graph model of interest points for multiple sample students; The interest point test data of multiple students are obtained, and the interest point weight map model of the students is established according to the interest point test data of the students and the interest point weight map models of multiple sample students.

3. The English teaching management method based on semantic understanding and cloud service according to claim 2 is characterized in that: Establish a weighted graph model of interest points of multiple sample students, including: Obtain interest point test data of multiple test students; According to the interest point test data of the multiple test students, the multiple test students are divided into multiple test student groups; For each test student group, based on the interest point test data of multiple test students included in the test student group, a weighted graph model of interest points of sample students corresponding to the test student group is established; According to the students' interest point test data and the interest point weight map models of multiple sample students, the students' interest point weight map model is established, including: According to the students' interest point test data, establish the students' initial interest point weight graph model; Determine similar test student groups according to the students' interest point test data and the interest point test data of multiple test students included in each test student group; Based on the interest point weighted graph model of sample students corresponding to the similar test student group, the student's initial interest point weighted graph model is completed to establish the student's interest point weighted graph model.

4. The English teaching management method based on semantic understanding and cloud service according to claim 2 is characterized in that: The student's oral test data includes oral pronunciation test audio and oral dialogue test audio; Based on students' vocabulary test data, reading test data, oral test data and writing test data, generate students' English proficiency level data, including: Perform variational mode decomposition on students’ oral pronunciation test audio to extract students’ key sound features and pronunciation key features; Based on the key sound features of the students, similar standard spoken pronunciation audio is obtained from the standard spoken pronunciation audio library; Perform variational mode decomposition on similar standard spoken pronunciation audio to extract key features of standard pronunciation; Determine the student's oral pronunciation level based on the student's pronunciation key features and the standard pronunciation key features; Determine the student's oral vocabulary characteristics based on the student's oral dialogue test audio through the vocabulary recognition model; Using the grammar recognition model to test the audio of students’ spoken conversations, the grammar characteristics of students’ spoken language are determined; Determine the emotional characteristics of students’ conversations based on the students’ spoken conversation test audio using an emotion recognition model; The student's oral conversation level is determined according to the student's oral vocabulary features, oral grammar features and conversation emotion features, wherein the student's English proficiency level data at least includes the student's oral pronunciation level and oral conversation level.

5. The English teaching management method based on semantic understanding and cloud service according to any one of claims 2 to 4, characterized in that: According to the learning pattern tendency data, English proficiency level data and interest point weight graph model of the plurality of students, the plurality of students are grouped to determine a plurality of student groups, including: For any two students, the similarity of the weighted graph models of the two students' interest points is calculated according to the weighted graph models of the two students' interest points; According to the similarity of the weighted graph model of interest points of any two students, a plurality of students are grouped for the first time to determine a plurality of first student groups; For each first student group, according to the English proficiency level data of any two students included in the first student group, calculate the similarity of the English proficiency levels of any two students, and according to the similarity of the English proficiency levels of any two students, perform a second grouping on the multiple students included in the first student group to determine multiple second student groups; For each second student group, based on the learning pattern tendency data of any two students included in the second student group, the similarity of the learning pattern tendencies of any two students is calculated, and based on the similarity of the learning pattern tendencies of any two students, the multiple students included in the second student group are grouped for the third time to determine multiple student groups.

6. The English teaching management method based on semantic understanding and cloud service according to any one of claims 2 to 4, characterized in that: According to the learning pattern tendency data, English proficiency level data and interest point weight graph model of the multiple students included in the student group, a basic teaching plan corresponding to the student group is generated, including: Determining a target teaching method corresponding to the student group according to the learning mode tendency data of the multiple student terminals included in the student group; Determining a plurality of target English knowledge points corresponding to the student group according to the English proficiency level data of the plurality of student terminals included in the student group; According to the interest point weight graph model of multiple students included in the student group and multiple target English knowledge points, a basic teaching plan corresponding to the student group is generated, wherein the basic teaching plan at least includes target English knowledge points, target teaching methods and teaching objectives at multiple teaching time nodes.

7. An English teaching management method based on semantic understanding and cloud service according to any one of claims 1 to 4, characterized in that: Get real-time, relevant information, including: Determine a first target website, and obtain candidate campus activity information from the first target website based on crawler technology; Determine a second target website, and obtain candidate real-time news from the second target website based on crawler technology; The candidate campus activity information and candidate real-time news are screened to determine the effective campus activity information and effective real-time news.

8. The English teaching management method based on semantic understanding and cloud service according to claim 7 is characterized in that: Screen candidate campus event information and candidate real-time news to determine valid campus event information and valid real-time news, including: For each student group, generating a group interest point weighted graph model corresponding to the student group according to interest point weighted graph models of a plurality of students included in the student group; Determine points of interest corresponding to candidate campus activity information; Determine points of interest corresponding to candidate real-time news; According to the group interest point weight graph model corresponding to each student group, the interest points corresponding to the candidate campus activity information and the interest points corresponding to the candidate real-time news, the candidate campus activity information and the candidate real-time news are screened to determine the effective campus activity information and the effective real-time news.

9. The English teaching management method based on semantic understanding and cloud service according to claim 8, characterized in that: Based on the real-time relevant information and the learning mode tendency data, English proficiency level data and interest point weight graph model of the multiple students included in the student group, the semantic understanding technology is used to generate the supplementary push content corresponding to the student group, and the supplementary push content is pushed to the student terminal corresponding to the student group, including: For each student group, based on the interest points corresponding to the valid campus activity information or the interest points corresponding to the valid real-time news, the target campus activity information or the target real-time news is determined, and based on the English proficiency level data of the multiple students included in the student group using semantic understanding technology, an English reading article is generated according to the target campus activity information or the target real-time news, and based on the learning pattern tendency data of the multiple students included in the student group, the English reading article is converted into supplementary push content, and the supplementary push content is pushed to the student terminal corresponding to the student group.

10. An English teaching management system based on semantic understanding and cloud services, applied to an English teaching management method based on semantic understanding and cloud services as claimed in any one of claims 1 to 9, characterized in that: include: Resource management module, used to establish a cloud-based teaching resource library; A teaching management module is used to obtain learning pattern tendency data, English proficiency level data and interest point weight graph model of multiple students; group the multiple students according to the learning pattern tendency data, English proficiency level data and interest point weight graph model of the multiple students to determine multiple student groups; for each student group, generate a basic teaching plan corresponding to the student group according to the learning pattern tendency data, English proficiency level data and interest point weight graph model of the multiple students included in the student group; for each student group, retrieve teaching resources from the cloud teaching resource library according to the basic teaching plan corresponding to the student group, and push corresponding teaching resources to the student terminal corresponding to the student group according to the teaching progress of the basic teaching plan of the student group; An information acquisition module, used to acquire real-time related information, wherein the real-time related information at least includes campus activity information and / or real-time news; The teaching management module is also used to generate supplementary push content corresponding to each student group based on real-time relevant information and the learning pattern tendency data, English proficiency level data and interest point weight graph model of multiple students included in the student group using semantic understanding technology, and push the supplementary push content to the student terminal corresponding to the student group.

Citation Information

Patent Citations

  • Variable-scale self-adaptive denoising method for acoustic differential intelligent bearing and acoustic intelligent bearing

    CN113887369A

  • Project recommendation method and system based on multiple preference degrees

    CN115936939A

  • Online education resource group recommendation method based on graph convolutional neural network

    CN117131285A

  • Personalized teaching plan design method and system based on large language model

    CN118504774A

  • Self-adaptive education method based on artificial intelligence

    CN119204723A