English personalized learning recommendation method based on big data

Abstract

The invention relates to the technical field of education, in particular to an English personalized learning recommendation method based on big data, which comprises the following steps: collecting original data of English homework completion speed and answer accuracy of a learner, calculating average completion time and accuracy by using a statistical analysis method, identifying the deviation between learning ability and interest points, and recommending the learning ability to the learner. And obtaining a learning ability evaluation result. According to the invention, through predicting learning content demands, not only is the progress of a learner captured, but also future demands can be predicted, so that education resources are prepared in advance, prospective matching of teaching contents is realized, and through optimizing a teaching material sequence and contents, high matching of teaching materials and personalized learning demands is ensured; the use efficiency of educational resources and the maximization of the learning effect are remarkably improved, the learning path is dynamically adjusted, the learning adaptability is evaluated, the learning process is optimized, the flexible application of course content is enhanced, and more personalized learning experience and higher learning achievement are achieved.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to a method for recommending personalized English learning based on big data. Background Art

[0002] The field of educational technology encompasses various methods and practices that apply information technology to improve educational quality and efficiency. This area encompasses educational software development, online learning platforms, digitized instructional content, and personalized learning solutions. Its core focus is on leveraging modern technology, particularly information technology, to promote the dissemination and absorption of knowledge, improve educational accessibility, and personalize the learning experience. Through systematic technology integration, the field of educational technology aims to provide learners with diverse needs with more customized learning paths and resources to accommodate various learning styles and speeds.

[0003] The patent application, titled "Big Data-Based Personalized English Learning Recommendation Method," utilizes big data analysis techniques to precisely recommend English learning resources and strategies tailored to individual learners. The patent involves data collection, analysis, and application, focusing on how to customize learning content based on learners' historical learning data, performance, and preferences. This approach primarily uses data mining techniques to identify learners' needs and progress, providing recommendations for the most appropriate learning materials and activities to support the learning process.

[0004] While the existing educational technology sector widely utilizes information technology to improve educational quality and efficiency, it lacks precise assessments of individual learners' in-depth learning abilities and interests. These limitations prevent educational resource recommendations from fully matching learners' individual needs, impacting learning outcomes. For example, traditional instructional content is uniform and lacks the flexibility to adjust the learning pace based on each learner's specific performance and interests. Existing methods are not proactive or dynamic enough in tracking and predicting learners' progress, leading to a mismatch between educational resource allocation and learners' actual needs, impacting learning motivation and efficiency. Summary of the Invention

[0005] In order to solve the problem that the existing technology lacks accurate assessment of individual learners' in-depth learning ability and interest deviations, and the limitations lead to educational resource recommendations that cannot fully match learners' personalized needs, affecting learning outcomes. For example, traditional teaching content is consistent and lacks the flexibility to adjust the learning pace according to each learner's specific performance and interests. Existing methods are not forward-looking and dynamic enough in tracking and predicting learners' learning progress, resulting in a mismatch between educational resource allocation and learners' actual needs, affecting learning motivation and efficiency. The embodiment of the present invention provides a method for personalized English learning recommendation based on big data. The technical solution is as follows:

[0006] On the one hand, a method for personalized English learning recommendation based on big data is provided, which includes:

[0007] S1: Collect the original data of learners' English homework completion speed and answer accuracy, use statistical analysis methods to calculate the average completion time and accuracy, identify the deviations between learning ability and interest points, and obtain learning ability assessment results;

[0008] S2: Analyze the learning ability assessment results, use big data to identify the time series trend of English learning performance, predict the demand for English learning content, and output potential demand prediction results;

[0009] S3: Based on the potential demand prediction results, screen English teaching resources that match the learner's interests, analyze and recommend personalized English learning materials that match the learner based on text fit, and obtain a matching content selection;

[0010] S4: Utilizing the matching content selection and combining it with the learner's personalized English learning needs, optimizing the order and content of the English teaching materials, analyzing the degree of matching between the English teaching materials and the learning needs, and obtaining a personalized English learning path;

[0011] S5: Based on the personalized English learning path, collect the learner's real-time English learning data, adjust the English teaching material content and learning pace, and optimize the path by comparing the English learning data with the preset goals to obtain a dynamic adjustment result of the learning path;

[0012] S6: Using the dynamic adjustment results of the learning path, evaluate the personalized English learning effect, monitor the learner's progress changes, compare the learning data before and after the learning path adjustment, and obtain the personalized learning adaptability evaluation results.

[0013] As a further solution of the present invention, the learning ability assessment results include the average homework completion time, homework accuracy, and deviation of interest points from the average data; the potential demand prediction results include the demand trend of key learning, the predicted demand for key learning content, and the prediction of changes in learning frequency; the matching content selection includes a personalized recommended article list, a video tutorial collection, exercises, and simulation test selections; the personalized English learning path includes the chapter learning order, topic coverage, and a scheduled learning cycle; the dynamic adjustment results of the learning path include textbook content update information, a learning rhythm adjustment plan, and a learning goal update record; the personalized learning adaptability assessment results include an analysis of changes in English learning progress, an evaluation of efficiency optimization, and the degree of knowledge mastery.

[0014] As a further embodiment of the present invention, the steps of collecting raw data on learners' English homework completion speed and answer accuracy, calculating average completion time and accuracy using statistical analysis methods, identifying deviations between learning ability and points of interest, and obtaining learning ability assessment results are as follows:

[0015] S101: Collect raw data on learners' English homework completion speed and answer accuracy, filter data records, and perform data processing, including removing outliers and filling in missing data, to generate a processed data set;

[0016] S102: Using the processed data set, calculate the average time to complete the homework and the average accuracy rate of each learner, and compare the average and standard deviation to obtain a learning efficiency analysis result;

[0017] S103: Based on the learning efficiency analysis results, identify the learner's ability deviations and interests during the learning process, and obtain a learning ability assessment result by comparing performance differences between learners.

[0018] As a further solution of the present invention, the steps of analyzing the learning ability assessment results, using big data to identify the time series trend of English learning performance, predicting the demand for English learning content, and outputting the potential demand prediction results are specifically as follows:

[0019] S201: using the learning ability assessment results, performing data aggregation, integrating English learning scores in different time periods, and sorting the data in chronological order using time tags to obtain a time series data set;

[0020] S202: Utilizing the time series data set, performing trend analysis, using a sliding window technique to calculate the moving average and rate of change of the learning performance, identifying patterns and regularities of the English learning performance through the changing trends, and obtaining a time series trend analysis result;

[0021] S203: Based on the time series trend analysis results, perform demand forecasting to evaluate the potential demand for English learning content in the future time period, and generate potential demand forecast results by identifying content demand in the English performance optimization range and the English performance decline range.

[0022] As a further solution of the present invention, based on the potential demand prediction results, English teaching resources corresponding to the learner's interests are screened, and personalized English learning materials matching the learner are analyzed and recommended based on the text fit, to obtain a matching content selection, specifically the following steps:

[0023] S301: Using the potential demand prediction result, performing resource screening, accessing English teaching resource data, performing keyword extraction and tag matching, screening English teaching resources related to the learner's interests, and obtaining a teaching resource screening record;

[0024] S302: Based on the teaching resource screening record, calculating the fit value between the teaching resources and the learner's needs, evaluating the matching degree between the teaching resources and the learner's needs, and generating a personalized matching result;

[0025] S303: Recommending the most personalized teaching materials to the learner based on the personalized matching results, providing the learner with a customized learning experience, and outputting a selection of matching content.

[0026] As a further solution of the present invention, the formula for calculating the fit value between the teaching resources and learner needs is as follows:

[0027]

[0028] Among them, AB is the fitting value between teaching resources and learners’ needs, a i represents the characteristic value of the teaching resource in the i-th dimension, b i represents the eigenvalue of learner preference in the i-th dimension, P represents the update frequency of teaching resources, Q represents the average frequency of learners changing teaching materials, α and β are adjustment coefficients, R represents the user rating of teaching resources, S represents the highest rating of available teaching resources, and n is the number of dimensions.

[0029] As a further solution of the present invention, the steps of utilizing the matching content selection, combining the learner's personalized English learning needs, optimizing the order and content of English teaching materials, analyzing the degree of matching between the English teaching materials and the learning needs, and obtaining a personalized English learning path are as follows:

[0030] S401: Analyzing the learner's learning style and progress using the matching content selection, adjusting the order and emphasis of the English teaching material content, optimizing the structure and presentation of the English teaching material, and obtaining an optimized teaching material sequence;

[0031] S402: Based on the optimized teaching material sequence, matching the English teaching material content with the learner's needs, analyzing the coverage and adaptability of the English teaching content, evaluating the consistency between the teaching material content and the personalized needs, and generating a matching analysis result;

[0032] S403: Based on the matching analysis results, a path design is performed, and the consistency between the differentiated learning stages and the learner's needs is evaluated in combination with the learner's learning goals and preferences, and a personalized English learning path is output.

[0033] As a further solution of the present invention, according to the personalized English learning path, the learner's real-time English learning data is collected, the English teaching material content and learning pace are adjusted, and the path is optimized by comparing the English learning data with the preset goals to obtain the dynamic adjustment results of the learning path. The specific steps are:

[0034] S501: Using the personalized English learning path, monitor the learner's learning activities and performance in real time, collect English learning data, including homework completion time and test scores, and generate a real-time learning data set;

[0035] S502: Using the real-time learning data set, perform content and pace adjustments. Based on the learning effects and learner feedback displayed by the data, adjust the learning pace, verify that the teaching material updates correspond to learners' needs in real time, and obtain adjusted teaching material content.

[0036] S503: Based on the adjusted teaching material content, compare the student's real-time learning data with the preset learning goals, calculate the deviation value between the real-time mastery level and the expected goal, make necessary course adjustments, and output the dynamic adjustment results of the learning path.

[0037] As a further solution of the present invention, the formula for calculating the deviation between the real-time mastery level and the expected target is as follows:

[0038]

[0039] Among them, SA is the deviation value between the real-time mastery level and the expected target, represents the student's real-time learning data, t represents the preset learning target, w1 represents the deviation weight, f represents the student's learning preference, c represents the course difficulty coefficient, w2 represents the course weight adjustment coefficient, and μ represents the normalization constant.

[0040] As a further solution of the present invention, the steps of utilizing the dynamic adjustment results of the learning path to evaluate the personalized English learning effect, monitor the learner's progress changes, compare the learning data before and after the learning path adjustment, and obtain the personalized learning adaptability evaluation results are as follows:

[0041] S601: Using the learning path dynamic adjustment result, perform learning effect evaluation, monitor the learner's performance and progress in the adjusted learning path, collect key performance indicators, including homework submission rate and test scores, and obtain a learner progress dataset;

[0042] S602: Using the learner progress dataset, perform data comparative analysis to compare learning data before and after the learning path adjustment, including learning speed, accuracy, and engagement, analyze the impact of the learning path adjustment, and obtain comparative analysis results;

[0043] S603: Based on the comparative analysis results and referring to the learner's performance optimization, the personalized adaptability of the teaching material content and learning rhythm is evaluated, and a personalized learning adaptability evaluation result is output.

[0044] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0045] By collecting and analyzing data on learners' completion speed and accuracy of English assignments, and accurately assessing their learning abilities and interests, this big data-driven assessment approach provides in-depth insights into learners' actual performance, enabling more precise recommendations for teaching resources and improving their learning experience and outcomes. By identifying time-series trends in learning performance and predicting learning content needs, it not only captures learners' progress but also foresees future needs, enabling educational resources to be prepared in advance and proactively matching teaching content. By optimizing the sequence and content of teaching materials to ensure a close match with personalized learning needs, it significantly improves the efficiency of educational resource utilization and maximizes learning outcomes. Dynamically adjusting learning paths and assessing learning adaptability not only optimizes the learning process but also enhances the flexible application of course content, achieving a more personalized learning experience and higher learning achievement. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0047] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0048] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0049] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0050] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0051] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0052] Figure 7 This is a detailed flow chart of S6 of the present invention. DETAILED DESCRIPTION

[0053] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0054] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0055] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0056] See also Figure 1 The embodiment of the present invention provides a method for personalized English learning recommendation based on big data. The processing flow of the method may include the following steps:

[0057] S1: Collect raw data on learners' English homework completion speed and answer accuracy, use statistical analysis methods to calculate the average completion time and accuracy, and compare the learner's data with the group average to identify deviations in learning ability and interest points, and obtain learning ability assessment results;

[0058] S2: Analyze learning ability assessment results and use big data to identify time series trends in English learning performance, predict learners' demand for English learning content in the future, and output potential demand prediction results;

[0059] S3: Based on the potential demand prediction results, screen English teaching resources that match the learner's interests. Analyze and recommend personalized English learning materials that match the learner based on the text fit, and obtain a selection of matching content.

[0060] S4: Utilize the matching content selection and combine it with the learner's personalized English learning needs to optimize the order and content of the English teaching materials, analyze the degree of match between the English teaching materials and the learner's English learning needs, and obtain a personalized English learning path;

[0061] S5: Based on the personalized English learning path, we collect learners' real-time English learning data, adjust the English teaching materials and learning pace, and optimize the path by comparing the English learning data with the preset goals, thus obtaining the dynamic adjustment results of the learning path.

[0062] S6: Use the results of dynamic adjustment of learning paths to evaluate the effectiveness of personalized English learning, identify key learning nodes, monitor changes in learners' progress, compare learning data before and after learning path adjustment, calculate changes in learning effects and efficiency, and obtain personalized learning adaptability evaluation results.

[0063] The learning ability assessment results include the average homework completion time, homework accuracy, and deviation of interest points from the average data. The potential demand prediction results include the demand trend of key learning, the predicted demand for key learning content, and the prediction of changes in learning frequency. The matching content selection includes a personalized recommended article list, a video tutorial collection, exercises, and simulation test selections. The personalized English learning path includes the chapter learning order, topic coverage, and the scheduled learning cycle. The dynamic adjustment results of the learning path include textbook content update information, learning rhythm adjustment plan, and learning goal update records. The personalized learning adaptability assessment results include analysis of changes in English learning progress, evaluation of efficiency optimization, and knowledge mastery.

[0064] See also Figure 2, collect the original data of learners' English homework completion speed and answer accuracy, use statistical analysis methods to calculate the average completion time and accuracy, identify the deviations between learning ability and interest points, and obtain the learning ability assessment results in the following steps:

[0065] S101: Collect raw data on learners' English homework completion speed and answer accuracy, filter data records, and perform data processing, including removing outliers and filling in missing data. The execution process for generating the processed data set is as follows;

[0066] Collecting raw data on learners' English homework completion speed and answer accuracy requires meticulous recording of time and accuracy. Data recorders or learning management devices automatically capture the specific time each learner submits their homework and the answers to each question. During the data screening stage, advanced data screening techniques are used to eliminate data records that do not meet analysis requirements, such as records with incorrect timestamps, inconsistent formats, or empty answer fields. The data processing process includes removing obvious outliers caused by device errors or user errors, such as abnormally short or long homework completion times, or zero or 100% answer accuracy. To ensure the completeness and accuracy of the data, statistical methods are used to fill in missing data points, such as using the average completion time and accuracy of learners of the same type to fill in the gaps, ensuring the consistency and reliability of the data set and generating the processed data set.

[0067] S102: Using the processed data set, calculate the average time to complete the homework and the average accuracy rate of each learner, and compare the average and standard deviation to obtain the learning efficiency analysis results. The execution process is as follows;

[0068] Calculate the average time to complete each learner's homework and the average accuracy rate of answering questions according to the formula:

[0069]

[0070] and

[0071]

[0072] Calculate the average performance of all learners, where T avg is the average time to complete the job, R avg is the average correct rate of answering questions, B o represents the completion time of the oth learner, N represents the total number of learners, D o represents the correct answer rate of the oth learner;

[0073] Referring to a specific example, there are five learners, and the time to complete the assignment is 20, 30, 25, 40 and 15 minutes respectively;

[0074] The accuracy rates were 0.90, 0.80, 0.85, 0.95, and 0.75 respectively;

[0075] Substitute into the formula for calculation:

[0076]

[0077] The results reflect the learners' overall learning efficiency and outcomes.

[0078] S103: Based on the learning efficiency analysis results, identify the learner's ability deviations and interests in the learning process, and compare the performance differences between learners to obtain the learning ability assessment results. The execution process is as follows;

[0079] By identifying learners' ability gaps and areas of interest throughout the learning process and comparing performance differences in assignment completion time and accuracy across learners, we can reveal each learner's strengths and weaknesses. Leveraging this data, educators can create personalized learning plans for each learner, focusing on interests and areas for improvement, thereby enhancing the relevance and effectiveness of instruction. This analysis also helps uncover learners' underutilized potential or topics of particular interest, providing a scientific basis for future course design and teaching methods. By adjusting instructional content, difficulty, and teaching methods, and increasing classroom interaction and incentives, teachers can effectively enhance student motivation and overall learning efficiency, ultimately generating learning ability assessments.

[0080] See also Figure 3 , analyze the learning ability assessment results, use big data to identify the time series trend of English learning performance, predict the demand for English learning content, and output the potential demand prediction results. The specific steps are:

[0081] S201: Using the learning ability assessment results, perform data aggregation, integrate English learning scores in different time periods, and use time tags to sort the data in chronological order to obtain a time series dataset. The execution process is as follows;

[0082] By integrating and analyzing the results of students' learning ability assessments over different time periods, we reveal changing trends in their English learning abilities. Furthermore, based on individual student differences, we collect and integrate English learning performance data from different time periods. Using time-stamping technology, we sort the collected data into time series to ensure the accuracy and completeness of the data. Data from different time points are arranged chronologically to form a clear time series line, facilitating subsequent trend analysis and data mining. This process also includes data preprocessing, such as missing value handling and outlier detection, to improve the accuracy and reliability of data analysis. This entire data aggregation and integration process not only provides a comprehensive perspective on students' learning progress but also provides data support for developing personalized teaching strategies, resulting in a time series dataset.

[0083] S202: Utilize the time series data set to perform trend analysis. Use the sliding window technique to calculate the moving average and rate of change of the learning performance. Identify the patterns and regularities of the English learning performance through the trend of change. The execution process for obtaining the time series trend analysis results is as follows;

[0084] Analyze the trend of academic performance by calculating the moving average and rate of change of academic performance according to the formula:

[0085]

[0086] and

[0087] Δx t =x t -x t-1 ;

[0088] Calculate the moving average and rate of change of learning performance, where MA(t) represents the moving average at time t, Z represents the size of the sliding window, and x q Represents the score at the time point, Δx t represents the rate of change of performance at time t, x t and x t-1 are the scores at time t and t-1 respectively;

[0089] Referring to the fluctuation of English learning scores at different times, the sliding window size is set to 5, and the score sequence of a student [76, 81, 79, 84, 77] is calculated. The moving average is calculated using the formula:

[0090]

[0091] Calculate the rate of change of grades:

[0092] Δx4=84-79=5;

[0093] The results show that academic performance improved from the third to the fourth time point. In this way, students' learning trends and cyclical fluctuations can be grasped more accurately, providing teachers with strong data support for adjusting teaching content.

[0094] S203: Based on the time series trend analysis results, perform demand forecasting to evaluate the potential demand for English learning content in the future time period. By identifying the content demand in the English performance improvement range and the decline range, the execution process of generating the potential demand forecast results is as follows;

[0095] By analyzing time series data of academic performance and identifying upward and downward trends in performance, we can assess the potential demand for English learning content in future time periods. Through in-depth analysis of content demand during optimization and decline periods, we can develop corresponding teaching strategies and resource allocation plans. For example, during the optimization period of rising performance, we can increase the challenge for students by introducing more difficult learning materials. During the decline period, we need to analyze the reasons for the decline, including improper learning methods, inappropriate learning materials, or insufficient student motivation. Based on this, we can adjust teaching content, increase tutoring and feedback, and help students overcome learning difficulties. This demand forecasting method not only allows educators to better understand students' learning status but also predict and prepare for future increases in educational resource demand, ensuring educational quality and student learning outcomes, and generating potential demand forecasts.

[0096] See also Figure 4 Based on the potential demand prediction results, we screen English teaching resources that match learners' interests, analyze and recommend personalized English learning materials that match learners based on the text fit, and obtain the matching content selection in the following steps:

[0097] S301: Using the potential demand prediction results, perform resource screening, access English teaching resource data, perform keyword extraction and tag matching, screen English teaching resources related to learners' interests, and obtain the teaching resource screening record. The execution process is as follows:

[0098] We access a database of English teaching resources, extract keywords, and perform tag matching. This process leverages advanced text analysis and data mining techniques to automatically identify and extract key content relevant to learning needs. We then screen teaching resources, focusing on materials highly relevant to learners' interests and predicted needs, such as videos, lesson plans, and interactive exercises. This process considers not only the educational quality of the resources but also their currency and user reviews to ensure the effectiveness and popularity of the selected materials. This screening mechanism directly impacts learners' learning motivation and efficiency, providing more targeted learning support and resulting in a record of selected teaching resources.

[0099] S302: Based on the teaching resource screening records, the fitting value between the teaching resources and the learner's needs is calculated, the matching degree between the teaching resources and the learner's needs is evaluated, and the execution process of generating personalized matching results is as follows;

[0100] The formula for calculating the fit between teaching resources and learner needs is as follows:

[0101]

[0102] Among them, AB is the fitting value between teaching resources and learners’ needs, a i represents the characteristic value of the teaching resource in the i-th dimension, b i represents the eigenvalue of learner preference in the i-th dimension, P represents the update frequency of teaching resources, Q represents the average frequency of learners changing teaching materials, α and β are adjustment coefficients, R represents the user rating of teaching resources, S represents the highest rating of available teaching resources, and n is the number of dimensions;

[0103] Parameter meaning and setting value:

[0104] a i and b i is the characteristic value of resources and learners in the i-th dimension, obtained by analyzing the existing data, for example, a i Represents the text complexity of the resource, b i Indicates learners’ preference for complex texts;

[0105] P and Q are the resource update frequency and the average frequency of learners changing textbooks, respectively, which are obtained from user log data;

[0106] α and β are adjustment coefficients that reflect the update frequency and the importance of resource scoring. The appropriate coefficient values are determined based on historical data analysis, and α is set to 0.1 and β is set to 0.05;

[0107] R and S represent the user rating of the resource and the highest rating of available teaching resources, respectively, which are directly obtained from the database;

[0108] Assume that the characteristic vectors of a teaching resource and a learner are [2, 3, 4] and [1, 5, 2], the update frequency P = 2, the average frequency of learners changing teaching materials Q = 3, the resource score R = 85, and the highest score S = 100;

[0109] Then calculate the eigenvector multiplication and normalization:

[0110] 2·1+3·5+4·2=25;

[0111]

[0112]

[0113] Calculate the frequency difference adjustment:

[0114] 0.1·|2-3|=0.1;

[0115] Calculate the score scale adjustment:

[0116]

[0117] Substitute the parameters into the formula for calculation:

[0118] AB=0.843+0.1+0.0425=0.9855;

[0119] The results show that the teaching resources are highly matched with learners' preferences, indicating that the resources can well meet learners' learning needs. The high fit value reveals that choosing this teaching material will lead to more effective learning results.

[0120] S303: Based on the personalized matching results, the learning materials that best meet the learner's personalized needs are recommended to provide the learner with a customized learning experience. The execution process of outputting the matching content selection is as follows;

[0121] Customized learning recommendations are made to determine the most appropriate learning content based on the learner's learning history, performance trends, and predicted potential needs. This recommendation mechanism not only considers the learner's current learning level, but also their learning preferences and projected future development direction. The customized learning experience provided is achieved through carefully selected video tutorials, practical exercises, and interactive simulation tests, aiming to enhance learners' learning interest and effectiveness. This includes both foundational knowledge consolidation materials and more challenging advancement materials, ensuring that every learner can achieve self-improvement through appropriate challenges and output a matching content selection.

[0122] See also Figure 5 , using matching content selections, combined with learners' personalized English learning needs, optimizing the order and content of English teaching materials, analyzing the degree of match between English teaching materials and learning needs, and obtaining personalized English learning paths. The specific steps are:

[0123] S401: Using the matching content selection, analyzing the learner's learning style and progress, adjusting the order and focus of the English textbook content, and optimizing the structure and presentation of the English textbook, the execution process of obtaining the optimized textbook sequence is as follows;

[0124] We analyze learners' learning styles and progress, using advanced data analysis tools and learning management devices to adjust the sequence and emphasis of English textbook content. Based on learners' specific feedback and learning outcomes, we optimize the textbook structure and presentation. For example, we prioritize areas where learners are weaker, reinforcing practice, while simplifying well-developed content. We also incorporate multimedia and interactive elements to enhance the textbook's appeal and effectiveness, making it more tailored to learners' cognitive styles and learning paces. This approach aims to improve learning efficiency and learner satisfaction, resulting in an optimized textbook sequence.

[0125] S402: Based on the optimized textbook sequence, the English textbook content is matched with the learner's needs, the coverage and adaptability of the English teaching content are analyzed, and the consistency between the textbook content and the personalized needs is evaluated. The execution process of generating the matching analysis results is as follows;

[0126] A detailed match analysis between English textbook content and learner needs involves an in-depth review and evaluation of textbook content, analyzing its coverage and adaptability. By comparing learners' individual needs with the knowledge points provided in the textbook, the consistency between the textbook content and learners' needs is assessed to determine whether the textbook fully meets learners' learning objectives. This analysis helps educators understand the strengths and weaknesses of the textbook and further adjust teaching strategies and textbook content to ensure a high degree of alignment with learners' needs. It is a key basis for educators and learners to jointly participate in the textbook optimization process, ensuring the effectiveness and applicability of teaching content and generating matching analysis results.

[0127] S403: Based on the matching analysis results, a path design is performed. The consistency between the differentiated learning stages and the learner's needs is evaluated based on the learner's learning goals and preferences. The execution process for outputting a personalized English learning path is as follows;

[0128] Executing pathway design involves evaluating the design of differentiated learning stages based on learners' learning goals and personal preferences. By analyzing learners' feedback and progress, we precisely adjust the learning pathway to match the learning needs of each stage, ensuring effective learning support at all stages, from entry-level to advanced. Focusing not only on learners' current needs but also anticipating potential future needs, we ensure a more rational and effective learning pathway overall. This provides learners with a clear blueprint for learning development, helping them learn at their own pace and interests, achieving optimal learning outcomes, and ultimately delivering a personalized English learning pathway.

[0129] See also Figure 6Based on the personalized English learning path, we collect learners' real-time English learning data, adjust the English teaching materials and learning pace, and optimize the path by comparing the English learning data with the preset goals. The specific steps to obtain the dynamic adjustment results of the learning path are as follows:

[0130] S501: Using a personalized English learning path, real-time monitoring of learners' learning activities and performance is performed, and English learning data, including homework completion time and test scores, is collected. The execution process for generating a real-time learning dataset is as follows;

[0131] Real-time monitoring of learners' learning activities and performance, including meticulous recording of completion times and test scores, is automated through learning management devices, ensuring immediate data collection and analysis. The collected English learning data includes detailed records of every learner's learning activity, such as study time, assignment submission times, and scores. This data not only reflects learners' learning progress but also reveals predicted areas of learning difficulties or strengths. This allows educators to quickly respond to learners' needs, adjusting teaching methods or providing additional support to optimize learning outcomes and improve learning satisfaction, generating real-time learning datasets.

[0132] S502: Using real-time learning data sets, content and pacing adjustments are performed. Based on the learning outcomes and learner feedback displayed by the data, the learning pacing is adjusted to verify that the teaching material updates are aligned with learner needs in real time. The execution process for obtaining the adjusted teaching material content is as follows;

[0133] Adjustments to content and pacing are implemented based on data-driven learning outcomes and direct feedback from learners. Adjustments to textbook content and pacing aim to improve the adaptability and effectiveness of instruction, ensuring that the content reflects learners' needs and learning status in real time. If data indicates poor performance in a specific area, the textbook will be adjusted to increase the intensity and depth of instruction in that area, while also slowing down the pace to allow learners to fully absorb and understand the material. This flexible adjustment strategy ensures that instructional content remains synchronized with learners' actual performance and feedback, enhancing the personalization of instruction and the effectiveness of learning. It also ensures that textbook content better aligns with learners' current needs, effectively supporting their learning progress, and ultimately resulting in adjusted textbook content.

[0134] S503: Based on the adjusted teaching material content, the student's real-time learning data is compared with the preset learning objectives, the deviation between the real-time mastery level and the expected goal is calculated, and necessary course adjustments are made. The execution process of outputting the dynamic adjustment results of the learning path is as follows;

[0135] The formula for calculating the deviation between the real-time mastery level and the expected target is as follows:

[0136]

[0137] Among them, SA is the deviation value between the real-time mastery level and the expected goal, d represents the student's real-time learning data, t represents the preset learning goal, w1 represents the deviation weight, f represents the student's learning preference, c represents the course difficulty coefficient, w2 represents the course weight adjustment coefficient, and μ represents the normalization constant.

[0138] Parameter meaning and setting value:

[0139] d is the student's real-time learning data, such as a test score of 68, which reflects the student's current level of mastery of a certain course;

[0140] t is the preset learning goal. For example, if the full score of the test is 100, it indicates the expected level of student mastery.

[0141] w1 is the bias weight, which is set to 0.5 based on past statistical data analysis and is used to enhance the impact of target bias in the calculation;

[0142] f is the learning preference, which is set to 0.7 and quantifies the degree to which students prefer a certain type of course based on the analysis of students’ historical data;

[0143] c is the course difficulty coefficient, which is set to 2 and quantifies the complexity of the course content based on the course difficulty rating of the education department;

[0144] w2 is the course weight adjustment coefficient, which is set to 1.5 to balance the impact of different course difficulties on the learning path;

[0145] u is the normalization constant, which is set to 10 to ensure the comparability and consistency of the calculation results;

[0146] Substitute the parameters into the formula for calculation:

[0147]

[0148] The results show that there is a large deviation between students' real-time mastery and the expected goals, and after considering the course difficulty and personal preferences, the priority of the learning path needs to be adjusted. This result is used to guide teachers to make corresponding course adjustments to better meet students' learning needs.

[0149] See also Figure 7 , using the results of dynamic adjustment of learning paths, evaluating the effectiveness of personalized English learning, monitoring learners' progress changes, and comparing learning data before and after learning path adjustment to obtain personalized learning adaptability evaluation results are as follows:

[0150] S601: Using the results of the dynamic adjustment of the learning path, perform learning effect evaluation, monitor the learner's performance and progress in the adjusted learning path, collect key performance indicators, including homework submission rate and test scores, and obtain the learner progress dataset. The execution process is as follows;

[0151] Perform learning effectiveness assessments, which include monitoring learners' performance and progress within the adjusted learning paths and collecting key performance indicators such as assignment submission rates and test scores. This data is automatically recorded by the learning management device, providing educators with a comprehensive perspective on and analysis of learners' performance on the new learning paths, including activity, learning speed, and content mastery. This detailed monitoring helps educators understand each learner's specific needs and promptly adjust teaching strategies and resource allocation to ensure optimal use of educational resources, maximize learning outcomes, and generate a dataset of learner progress.

[0152] S602: Using the learner progress dataset, perform data comparative analysis to compare learning data before and after the learning path adjustment, including learning speed, accuracy, and engagement, and analyze the impact of the learning path adjustment. The execution process for obtaining the comparative analysis results is as follows;

[0153] Comparative data analysis using learner progress datasets focuses on changes in learner learning data before and after learning path adjustments, including metrics such as learning speed, accuracy, and engagement. This comparative analysis allows educators to clearly identify the specific impact of learning path adjustments, identifying which adjustments are effective and which require further optimization. This analysis helps reveal the actual effects of learning path adjustments on learner behavior and learning outcomes, providing data support for further educational decision-making. Data analysis tools play a key role in this process, using advanced statistical methods and data visualization techniques to clearly demonstrate the differences before and after learning path adjustments, resulting in comparative analysis results.

[0154] S603: Based on the comparative analysis results and referring to the learner's performance optimization, the personalized adaptability of the teaching material content and learning pace is evaluated, and the execution process of outputting the personalized learning adaptability evaluation results is as follows;

[0155] Conducting personalized learning adaptability assessments involves evaluating the degree of personalized adaptability of teaching material content and learning pace. By comprehensively considering learners' performance optimization, educators can assess whether the current teaching material content and learning pace are highly aligned with learners' individual needs. This assessment process takes into account learners' feedback, academic performance, and behavioral data to ensure that adjustments to teaching materials and teaching strategies precisely meet learners' needs. This provides educators with key insights to further optimize the allocation of educational resources and teaching methods, ensuring that each learner can learn at a pace and style that suits them, improving learning efficiency and satisfaction, and outputting personalized learning adaptability assessment results.

[0156] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A personalized English learning recommendation method based on big data, characterized by: The following steps are involved: S1: Collect the original data of learners' English homework completion speed and answer accuracy, use statistical analysis methods to calculate the average completion time and accuracy, identify the deviations between learning ability and interest points, and obtain learning ability assessment results; S2: Analyze the learning ability assessment results, use big data to identify the time series trend of English learning performance, predict the demand for English learning content, and output potential demand prediction results; S3: Based on the potential demand prediction results, screen English teaching resources that match the learner's interests, analyze and recommend personalized English learning materials that match the learner based on text fit, and obtain a matching content selection; S4: Utilizing the matching content selection and combining it with the learner's personalized English learning needs, optimizing the order and content of the English teaching materials, analyzing the degree of matching between the English teaching materials and the learning needs, and obtaining a personalized English learning path; S5: Based on the personalized English learning path, collect the learner's real-time English learning data, adjust the English teaching material content and learning pace, and optimize the path by comparing the English learning data with the preset goals to obtain a dynamic adjustment result of the learning path; S6: Using the dynamic adjustment results of the learning path, evaluate the personalized English learning effect, monitor the learner's progress changes, compare the learning data before and after the learning path adjustment, and obtain the personalized learning adaptability evaluation results.

2. The method for personalized English learning recommendation based on big data according to claim 1, characterized in that: The learning ability assessment results include the average homework completion time, homework accuracy, and deviation of interest points from the average data; the potential demand prediction results include the demand trend of key learning, the predicted demand for key learning content, and the prediction of changes in learning frequency; the matching content selection includes a personalized recommended article list, a video tutorial collection, exercises, and simulation test selections; the personalized English learning path includes the chapter learning order, topic coverage, and a scheduled learning cycle; the dynamic adjustment results of the learning path include textbook content update information, a learning rhythm adjustment plan, and a learning goal update record; the personalized learning adaptability assessment results include an analysis of changes in English learning progress, an assessment of efficiency optimization, and the degree of knowledge mastery.

3. The method for personalized English learning recommendation based on big data according to claim 1, characterized in that: The steps for collecting raw data on learners' English homework completion speed and answer accuracy, using statistical analysis methods to calculate average completion time and accuracy, and identifying deviations in learning ability and interest points to obtain learning ability assessment results are as follows: S101: Collect raw data on learners' English homework completion speed and answer accuracy, filter data records, and perform data processing, including removing outliers and filling in missing data, to generate a processed data set; S102: Using the processed data set, calculate the average time to complete the homework and the average accuracy rate of each learner, and compare the average and standard deviation to obtain a learning efficiency analysis result; S103: Based on the learning efficiency analysis results, identify the learner's ability deviations and interests during the learning process, and obtain a learning ability assessment result by comparing performance differences between learners.

4. The method for personalized English learning recommendation based on big data according to claim 1, characterized in that: The steps of analyzing the learning ability assessment results, using big data to identify the time series trend of English learning performance, predicting the demand for English learning content, and outputting the potential demand prediction results are as follows: S201: using the learning ability assessment results, performing data aggregation, integrating English learning scores in different time periods, and sorting the data in chronological order using time tags to obtain a time series data set; S202: Utilizing the time series data set, performing trend analysis, using a sliding window technique to calculate the moving average and rate of change of the learning performance, identifying patterns and regularities of the English learning performance through the changing trends, and obtaining a time series trend analysis result; S203: Based on the time series trend analysis results, perform demand forecasting to evaluate the potential demand for English learning content in the future time period, and generate potential demand forecast results by identifying content demand in the English performance optimization range and the English performance decline range.

5. The method for personalized English learning recommendation based on big data according to claim 1, characterized in that: Based on the potential demand prediction results, the steps of screening English teaching resources corresponding to the learner's interests, analyzing and recommending personalized English learning materials matching the learner based on the text fit, and obtaining a matching content selection are as follows: S301: Using the potential demand prediction result, performing resource screening, accessing English teaching resource data, performing keyword extraction and tag matching, screening English teaching resources related to the learner's interests, and obtaining a teaching resource screening record; S302: Based on the teaching resource screening record, calculating the fit value between the teaching resources and the learner's needs, evaluating the matching degree between the teaching resources and the learner's needs, and generating a personalized matching result; S303: Recommending the most personalized teaching materials to the learner based on the personalized matching results, providing the learner with a customized learning experience, and outputting a selection of matching content.

6. The method for personalized English learning recommendation based on big data according to claim 5, characterized in that: The formula for calculating the fit value between the teaching resources and learner needs is as follows: Among them, AB is the fitting value between teaching resources and learners’ needs, a i represents the characteristic value of the teaching resource in the i-th dimension, b i represents the eigenvalue of learner preference in the i-th dimension, P represents the update frequency of teaching resources, Q represents the average frequency of learners changing teaching materials, α and β are adjustment coefficients, R represents the user rating of teaching resources, S represents the highest rating of available teaching resources, and n is the number of dimensions.

7. The method for personalized English learning recommendation based on big data according to claim 1, characterized in that: The steps for optimizing the order and content of English teaching materials by using the matching content selection and combining it with the learner's personalized English learning needs, analyzing the degree of matching between the English teaching materials and the learning needs, and obtaining a personalized English learning path are as follows: S401: Analyzing the learner's learning style and progress using the matching content selection, adjusting the order and emphasis of the English teaching material content, optimizing the structure and presentation of the English teaching material, and obtaining an optimized teaching material sequence; S402: Based on the optimized teaching material sequence, matching the English teaching material content with the learner's needs, analyzing the coverage and adaptability of the English teaching content, evaluating the consistency between the teaching material content and the personalized needs, and generating a matching analysis result; S403: Based on the matching analysis results, a path design is performed, and the consistency between the differentiated learning stages and the learner's needs is evaluated in combination with the learner's learning goals and preferences, and a personalized English learning path is output.

8. The method for personalized English learning recommendation based on big data according to claim 1, characterized in that: According to the personalized English learning path, the learner's real-time English learning data is collected, the English teaching material content and learning pace are adjusted, and the path is optimized by comparing the English learning data with the preset goals. The specific steps for obtaining the dynamic adjustment result of the learning path are as follows: S501: Using the personalized English learning path, monitor the learner's learning activities and performance in real time, collect English learning data, including homework completion time and test scores, and generate a real-time learning data set; S502: Using the real-time learning data set, perform content and pace adjustments. Based on the learning effects and learner feedback displayed by the data, adjust the learning pace, verify that the teaching material updates correspond to learners' needs in real time, and obtain adjusted teaching material content. S503: Based on the adjusted teaching material content, compare the student's real-time learning data with the preset learning goals, calculate the deviation value between the real-time mastery level and the expected goal, make necessary course adjustments, and output the dynamic adjustment results of the learning path.

9. The method for personalized English learning recommendation based on big data according to claim 8, characterized in that: The formula for calculating the deviation between the real-time mastery level and the expected target is as follows: Among them, SA is the deviation value between the real-time mastery level and the expected goal, d represents the student's real-time learning data, t represents the preset learning goal, w1 represents the deviation weight, f represents the student's learning preference, c represents the course difficulty coefficient, w2 represents the course weight adjustment coefficient, and μ represents the normalization constant.

10. The method for personalized English learning recommendation based on big data according to claim 1, characterized in that: The steps for utilizing the dynamic adjustment results of the learning path to evaluate the personalized English learning effect, monitor the learner's progress changes, compare the learning data before and after the learning path adjustment, and obtain the personalized learning adaptability evaluation results are as follows: S601: Using the learning path dynamic adjustment result, perform learning effect evaluation, monitor the learner's performance and progress in the adjusted learning path, collect key performance indicators, including homework submission rate and test scores, and obtain a learner progress dataset; S602: Using the learner progress dataset, perform data comparative analysis to compare learning data before and after the learning path adjustment, including learning speed, accuracy, and engagement, analyze the impact of the learning path adjustment, and obtain comparative analysis results; S603: Based on the comparative analysis results and referring to the learner's performance optimization, the personalized adaptability of the teaching material content and learning rhythm is evaluated, and a personalized learning adaptability evaluation result is output.

Images