English learning behavior intelligent prediction system based on big data driving

Abstract

The invention discloses an English learning behavior intelligent prediction system based on big data driving, and particularly relates to the technical field of data analysis, which comprises a data acquisition module, a learning behavior analysis module, a personalized learning path prediction module and an optimization and iteration module, the data acquisition module is used for acquiring learning behavior data of students from a learning platform, cleaning and preprocessing the learning behavior data and storing the learning behavior data in a database, and the learning behavior analysis module is used for analyzing learning habits, learning effects and behavior modes of the students based on the acquired learning behavior data and establishing personalized learning models of the students. The personalized learning path prediction module is used for intelligently recommending an optimal learning path according to historical data and learning states of students and dynamically adjusting learning contents and sequences, and the optimization and iteration module is used for transmitting feedback data to the personalized learning path prediction module to carry out dynamic adjustment and outputting the optimal learning path according to the feedback data. And regularly updating and optimizing the personalized learning model.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and more specifically, to an intelligent prediction system for English learning behavior driven by big data. Background Art

[0002] In the current era of rapid development of information technology, the application of big data is changing all fields, and the education industry is no exception. English, as a globally common language, has increasingly become the focus of people's learning. Especially in China, English learning occupies an important position in primary, secondary and university education. However, there are some problems in the traditional English education model, such as insufficient personalized teaching, inability to effectively track the learning progress, and difficulty in accurately evaluating the learning effect.

[0003] Existing English learning systems still have many limitations. Many systems rely on preset teaching models, lack flexibility, and are difficult to meet the diverse needs of different students. The intelligent prediction system for English learning behavior based on big data can achieve accurate prediction of students' needs through in-depth mining of students' learning behaviors, and provide dynamically adjusted learning plans for students. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide an intelligent prediction system for English learning behavior driven by big data to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solution: An intelligent prediction system for English learning behavior driven by big data, including a data collection module, a learning behavior analysis module, a personalized learning path prediction module, and an optimization and iteration module; The data collection module collects students' learning behavior data from the learning platform, cleans and preprocesses the collected data, and stores it in the database; The learning behavior analysis module analyzes students' learning habits, learning effects, and behavior patterns based on the collected learning behavior data, and establishes a personalized learning model for students; The personalized learning path prediction module intelligently recommends the best learning path according to students' historical data and real-time learning status, and dynamically adjusts the learning content and order; The optimization and iteration module continuously tracks students' learning status, transmits the feedback data to the personalized learning path prediction module for dynamic adjustment, and regularly updates and optimizes the personalized learning model according to the feedback data.

[0006] In a preferred embodiment, the data collection module collects students' learning behavior data from the learning platform, cleans and preprocesses the collected data, and stores it in the database. The specific steps are as follows: Step A1. Establish a data connection: Collect students' learning behavior data from multi-dimensional platforms such as the learning platform, online classroom system, learning management system, and student accounts, including learning duration, interaction records, homework grades, and exam results; Step A2. Data processing and storage: Perform deduplication, missing value filling, outlier detection, and format standardization cleaning and preprocessing operations on the collected raw data to ensure data accuracy and consistency, and store it in the database.

[0007] In a preferred embodiment, the learning behavior analysis module analyzes students' learning habits, learning effects, and behavior patterns based on the collected learning behavior data, and establishes a personalized learning model for students. The specific steps are as follows: Step B1. Behavior pattern analysis: Extract the preprocessed learning behavior data from the database, and use data mining techniques to analyze students' learning habits, participation behaviors, and homework submission situations to identify students' learning patterns. Further, it includes the following steps: Step B101. Feature extraction: Extract learning duration features, homework submission situations, and participation behavior features from the preprocessed data. The learning duration feature is the mean of students' daily learning durations, and the participation behavior feature is the number of times students watch course videos. Merge the extracted feature data into a dataset , where each is a student's behavior feature vector, including learning duration, homework submission situation, and video viewing times features; Step B102. Cluster analysis: Use a clustering algorithm to group students' behavior features, identify different learning patterns, and set the number of clusters , indicating that students are divided into "active participation type" and "low participation type" categories, and initialize K cluster centers , calculate the Euclidean distance from each sample to each cluster center, and perform iterations until the clustering result converges. After completing pattern recognition and classification, map each student's behavior pattern to a different color, plot each student's learning duration and participation behavior features in a two-dimensional space, and mark different learning patterns with different colors according to the clustering result. The active participation type is marked in red, and the low participation type is marked in blue; Step B2. Build a personalized learning model: According to the analysis results, establish a personalized learning model, and predict students' learning effects through a regression model. The mathematical expression is , where is the learning effect of the i-th student, is the feature of the student, are the parameters of the model, is the error term. By using the training data set, the model parameters are optimized to predict the learning effect of the student.

[0008] In a preferred embodiment, the personalized learning path prediction module intelligently recommends the best learning path based on the historical data and real-time learning status of the student, and dynamically adjusts the learning content and order. The specific steps are as follows: Step C1, historical data analysis: Extract the learning duration, chapter completion degree, learning progress, and test scores from the student's historical learning data, and represent them as a vector , where represents the learning duration of the student on knowledge point j, represents the chapter completion degree of knowledge point j, represents the learning progress of the student, represents the test score of the student on knowledge point j. By aggregating the student's learning data, personalized learning features such as strengths, weaknesses, and learning progress are extracted. The strength means that the student spends a short time on learning knowledge point j and has a high test score; the weakness means that the student spends a long time on learning knowledge point j and has a low test score; Step C2, dynamically adjust the learning content and order: Use machine learning algorithms to intelligently recommend the best learning path according to the student's historical data and real-time learning status, and dynamically adjust the learning content and order in the learning path according to the real-time learning status and the student's progress to maximize the learning effect and improve the learning efficiency. It further includes the following steps: Step C201, based on the current learning status of the student, adjust the recommended content, introduce new learning materials and modify the learning order to maximize the learning effect. Represent the current learning status as . By evaluating the current learning status, adjust the recommended content and order. The specific formula is , where represents the adjusted recommended content, is the learning effect of the i-th student; Step C202, after adjusting the recommended content, retrain the regression model with the newly collected data to better adapt to the personalized needs of the student. The specific formula is: , where and are the updated and pre-updated model parameters respectively, X and y are the input features and target output respectively, is the learning rate, is a loss function that optimizes the model by minimizing the loss.

[0009] In a preferred embodiment, the optimization and iteration module continuously tracks the learning status of students, transmits the feedback data to the personalized learning path prediction module for dynamic adjustment, and regularly updates and optimizes the personalized learning model according to the feedback data. The specific steps are as follows: Step D1: Collect the feedback data of students during the learning process, including exam scores, homework completion, and error records, and transmit the feedback data to the personalized learning path prediction module for analysis. Combine the feedback data with the learning effect to analyze and evaluate the learning effectiveness of students to determine the effectiveness of the current learning path. Step D2: According to the latest learning effect evaluation, retrain the personalized learning model using the feedback data of students, and dynamically adjust the learning path with the updated learning model.

[0010] The beneficial effects of the present invention are as follows: Collect the learning behavior data of students from the learning platform, clean and preprocess the collected data, store it in the database, analyze the learning habits, learning effects, and behavior patterns of students based on the collected learning behavior data, establish a personalized learning model for students, intelligently recommend the best learning path according to the historical data and learning status of students, dynamically adjust the learning content and order, continuously track the learning status of students, transmit the feedback data to the personalized learning path prediction module for dynamic adjustment, and regularly update and optimize the personalized learning model according to the feedback data. Through data collection, behavior analysis, personalized learning path prediction, and optimization and iteration, the present invention can provide personalized and accurate learning paths for students, improving the learning efficiency and effect of students. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is the system flow chart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts shall fall within the protection scope of the present application.

[0013] In the description of the present application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the described features. In the description of the present application, "a plurality of" means two or more unless otherwise specifically defined.

[0014] In the description of the present application, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present application is not necessarily construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed in the present application.

[0015] Embodiment 1 This embodiment provides an intelligent prediction system for English learning behavior driven by big data as shown in Figure 1 Figure, which specifically includes a data acquisition module, a learning behavior analysis module, a personalized learning path prediction module, and an optimization and iteration module; The data acquisition module collects the learning behavior data of students from the learning platform, cleans and preprocesses the collected data, and stores it in the database; The learning behavior analysis module analyzes the learning habits, learning effects, and behavior patterns of students based on the collected learning behavior data, and establishes a personalized learning model for students; The personalized learning path prediction module intelligently recommends the best learning path according to the historical data and real-time learning status of students, and dynamically adjusts the learning content and order; The optimization and iteration module continuously tracks the learning status of students, transmits the feedback data to the personalized learning path prediction module for dynamic adjustment, and regularly updates and optimizes the personalized learning model according to the feedback data.

[0016] In this embodiment, it is specifically necessary to explain the data acquisition module. The data acquisition module collects the learning behavior data of students from the learning platform, cleans and preprocesses the collected data, and stores it in the database. The specific steps are as follows: Step A1. Establish a data connection: Collect students' learning behavior data from multi-dimensional platforms such as learning platforms, online classroom systems, learning management systems, and student accounts, including learning duration, interaction records, homework scores, and exam results. Step A2. Data processing and storage: Perform deduplication, missing value filling, outlier detection, and format standardization cleaning and preprocessing operations on the collected raw data to ensure data accuracy and consistency, and store it in a database.

[0017] In this embodiment, specifically, the learning behavior analysis module is based on the collected learning behavior data to analyze students' learning habits, learning effects, and behavior patterns, and establish a personalized learning model for students. The specific steps are as follows: Step B1. Behavior pattern analysis: Extract the preprocessed learning behavior data from the database, and use data mining techniques to analyze students' learning habits, participation behaviors, and homework submission situations to identify students' learning patterns. It further includes the following steps: Step B101. Feature extraction: Extract learning duration features, homework submission situations, and participation behavior features from the preprocessed data. The learning duration feature is the mean of the daily learning duration of students, and the participation behavior feature is the number of times students watch course videos. Combine the extracted feature data into a data set , where each is the behavior feature vector of students, including learning duration, homework submission situation, and video viewing times features; Step B102. Cluster analysis: Use a clustering algorithm to group students' behavior features to identify different learning patterns, set the number of clusters , indicating that students are divided into "active participation type" and "low participation type" categories, initialize K cluster centers , calculate the Euclidean distance from each sample to each cluster center, and perform iteration until the clustering result converges. After completing pattern recognition and classification, map the behavior patterns of each student to different colors, plot the learning duration and participation behavior features of each student in a two-dimensional space, and mark different learning patterns with different colors according to the clustering result. The active participation type is marked in red, and the low participation type is marked in blue; Step B2. Build a personalized learning model: According to the analysis results, establish a personalized learning model, and predict students' learning effects through a regression model. The mathematical expression is , where is the learning effect of the i-th student, is the feature of the student, is the parameter of the model, is the error term. Through the training data set, optimize the model parameters , predict the learning effect of students.

[0018] In this embodiment, specifically, the personalized learning path prediction module is described. The personalized learning path prediction module intelligently recommends the best learning path based on the historical data and real-time learning status of students, dynamically adjusts the learning content and order, increases students' learning participation, and improves the activity and user satisfaction of the platform. The specific steps are as follows: Step C1, historical data analysis: Extract the learning duration, chapter completion rate, learning progress, and test scores from the historical learning data of students, and represent them as a vector , where represents the learning duration of the student on knowledge point j, represents the chapter completion rate of knowledge point j, represents the learning progress of the student, represents the test score of the student on knowledge point j. By aggregating the learning data of students, personalized learning characteristics are extracted as strengths, weaknesses, and learning progress. The strength indicates that the student's learning duration on knowledge point j is short and the test score is high; the weakness indicates that the student's learning duration on knowledge point j is long and the test score is low; Step C2, dynamically adjust the learning content and order: Use machine learning algorithms to intelligently recommend the best learning path based on the historical data and real-time learning status of students. According to the real-time learning status and the progress of students, dynamically adjust the learning content and order in the learning path to maximize the learning effect and improve learning efficiency. By intelligently recommending learning content and paths, improve the pertinence and effectiveness of learning. It further includes the following steps: Step C201, based on the current learning status of the student, adjust the recommended content, introduce new learning materials and modify the learning order to maximize the learning effect. Represent the current learning status as , by evaluating the current learning status, adjust the recommended content and order. The specific formula is , where represents the adjusted recommended content, is the learning effect of the i-th student; Step C202, after adjusting the recommended content, retrain the regression model using the newly collected data to better adapt to the personalized needs of students. The specific formula is: , where and are the updated and pre-updated model parameters respectively. X and y are the input features and target outputs respectively, is the learning rate, is the loss function, which optimizes the model by minimizing the loss.

[0019] In this embodiment, it is specifically necessary to explain the optimization and iteration module. The optimization and iteration module continuously tracks the learning status of students, transmits the feedback data to the personalized learning path prediction module for dynamic adjustment, and regularly updates and optimizes the personalized learning model according to the feedback data. By tracking the learning effect, it can timely discover the learning bottlenecks of students and make adjustments to help students make continuous progress on an efficient path. The specific steps are as follows: Step D1: Collect the feedback data of students during the learning process, including exam scores, homework completion status, and error records, and transmit the feedback data to the personalized learning path prediction module for analysis. Combine the feedback data with the learning effect to analyze and evaluate the learning effectiveness of students to determine the effectiveness of the current learning path. Step D2: According to the latest learning effect evaluation, use the feedback data of students to retrain the personalized learning model, and dynamically adjust the learning path with the updated learning model.

[0020] It should be noted that in the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0021] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0022] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded computers, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0023] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means embodying the functionality specified in the flowchart(s) Figure 1 or flowcharts and / or block(s) Figure 1 or blocks.

[0024] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functionality specified in the flowchart(s) Figure 1 or flowcharts and / or block(s) Figure 1 or blocks.

[0025] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0026] It is obvious that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent prediction system for English learning behavior driven by big data, characterized in that: It includes a data collection module, a learning behavior analysis module, a personalized learning path prediction module, and an optimization and iteration module; The data collection module collects students' learning behavior data from the learning platform, cleans and preprocesses the collected data, and stores it in the database; The learning behavior analysis module analyzes students' learning habits, learning effects, and behavior patterns based on the collected learning behavior data, and establishes a personalized learning model for students; The personalized learning path prediction module intelligently recommends the best learning path according to students' historical data and real-time learning status, and dynamically adjusts the learning content and order; The optimization and iteration module transmits the feedback data to the personalized learning path prediction module for dynamic adjustment, and regularly updates and optimizes the personalized learning model according to the feedback data.

2. The intelligent prediction system for English learning behavior driven by big data according to claim 1, wherein: The data collection module collects students' learning behavior data from the learning platform, cleans and preprocesses the collected data, and stores it in the database. The specific steps are as follows: Step A1, establish a data connection: Collect students' learning behavior data from multi-dimensional platforms such as the learning platform, online classroom system, learning management system, and student accounts, including learning duration, interaction records, homework grades, and exam results; Step A2, data processing and storage: Perform deduplication, missing value filling, outlier detection, and format standardization cleaning and preprocessing operations on the collected raw data, and store it in the database.

3. The intelligent prediction system for English learning behavior driven by big data according to claim 1, characterized in that: The learning behavior analysis module analyzes students' learning habits, learning effects, and behavior patterns based on the collected learning behavior data, and establishes a personalized learning model for students. The specific steps are as follows: Step B1, behavior pattern analysis: Extract the preprocessed learning behavior data from the database, and use data mining techniques to analyze students' learning habits, participation behaviors, and homework submission situations to identify students' learning patterns; Step B2: Construct a personalized learning model: Based on the analysis results, establish a personalized learning model, and predict the learning effect of students through a regression model. The mathematical expression is , where is the learning effect of the \(i\)-th student, are the characteristics of the student, are the parameters of the model, is the error term. Through the training data set, optimize the model parameters to predict the learning effect of students.

4. The intelligent prediction system for English learning behavior driven by big data according to claim 3, characterized in that: In the behavior pattern analysis of Step B1, extract the preprocessed learning behavior data from the database, and use data mining techniques to analyze students' learning habits, participation behaviors, and homework submission situations to identify students' learning patterns. It further includes the following steps: Step B101, Feature Extraction: Extract the learning duration feature, homework submission status, and participation behavior feature from the preprocessed data. The learning duration feature is the average daily learning duration of students, and the participation behavior feature is the number of times students watch course videos. Merge the extracted feature data into a dataset , where each is the behavior feature vector of students, including features such as learning duration, homework submission status, and video viewing times; Step B102, Cluster Analysis: Use a clustering algorithm to group the behavioral characteristics of students, identify different learning patterns, and set the number of clusters , indicating that students are divided into "active participation type" and "low participation type" categories, and initialize K cluster centers , calculate the Euclidean distance from each sample to each cluster center, and perform iteration until the clustering result converges. After completing pattern recognition and classification, map the behavioral patterns of each student to different colors, and plot the learning duration and participation behavioral characteristics of each student in a two-dimensional space. According to the clustering results, use different colors to mark different learning patterns, with the active participation type marked in red and the low participation type marked in blue.

5. The intelligent prediction system for English learning behavior driven by big data according to claim 1, characterized in that: The personalized learning path prediction module intelligently recommends the best learning path according to students' historical data and real-time learning status, and dynamically adjusts the learning content and order. The specific steps are as follows: Step C1. Historical data analysis: Extract the learning duration, chapter completion rate, learning progress, and test scores from the student's historical learning data, and represent them as a vector , where represents the learning duration of the student on knowledge point j, represents the chapter completion rate of knowledge point j, represents the student's learning progress, represents the test score of the student on knowledge point j. By aggregating the student's learning data, extract personalized learning characteristics as strengths, weaknesses, and learning progress; Step C2, dynamically adjust the learning content and order: Use machine learning algorithms to intelligently recommend the best learning path according to students' historical data and real-time learning status, and dynamically adjust the learning content and order in the learning path according to the real-time learning status and students' progress to maximize the learning effect and improve learning efficiency.

6. The intelligent prediction system for English learning behavior driven by big data according to claim 1, wherein: In the dynamically adjusting the learning content and order of Step C2, use machine learning algorithms to intelligently recommend the best learning path according to students' historical data and real-time learning status, and dynamically adjust the learning content and order in the learning path according to the real-time learning status and students' progress to maximize the learning effect and improve learning efficiency. It further includes the following steps: Step C201: Based on the current learning state of the student, adjust the recommended content, introduce new learning materials and modify the learning sequence to maximize the learning effect. Represent the current learning state as , by evaluating the current learning state, adjust the recommended content and sequence. The specific formula is , where represents the adjusted recommended content, is the learning effect of the i-th student; Step C202: After adjusting the recommended content, retrain the regression model using the newly collected data to better adapt to the personalized needs of students. The specific formula is: , where and are the model parameters after and before the update respectively, X and y are the input features and the target output respectively, is the learning rate, is the loss function, and the model is optimized by minimizing the loss.

7. The intelligent prediction system for English learning behavior driven by big data according to claim 1, wherein: The optimization and iteration module continuously tracks the learning status of students, transmits the feedback data to the personalized learning path prediction module for dynamic adjustment, and regularly updates and optimizes the personalized learning model according to the feedback data. The specific steps are as follows: Step D1: Collect the feedback data of students during the learning process, including exam scores, homework completion status, and error records, transmit the feedback data to the personalized learning path prediction module for analysis, combine the feedback data with the learning effect, and analyze and evaluate the learning effectiveness of students to determine the effectiveness of the current learning path; Step D2: According to the latest learning effect evaluation, retrain the personalized learning model using the feedback data of students, and dynamically adjust the learning path with the updated learning model.

Images