Method for constructing intelligent learning environment

Abstract

The present invention discloses a method for constructing an intelligent learning environment. The method adopts a learner model-driven construction method, pays full attention to individual differences of learners, improves learning effects, designs intelligent and personalized learning scenarios according to learner models and teaching needs, enhances the adaptability of the learning environment, and realizes the integration and scheduling of learning resources by building a learning resource library, thereby improving the efficiency of learning resource utilization. The method solves the problems that the existing intelligent learning environment construction methods lack sufficient attention to individual differences of learners, resulting in poor learning effects, failure to effectively combine learning scenarios and teaching needs, resulting in poor adaptability of the learning environment, scattered learning resources, and lack of effective integration and scheduling mechanisms.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and in particular to a method for constructing an intelligent learning environment. Background Art

[0002] With the rapid development of information technology, the field of education is undergoing a profound transformation. As a new type of educational technology, intelligent learning environment provides learners with personalized, intelligent and efficient learning experience by integrating technologies such as the Internet of Things, cloud computing, big data and artificial intelligence.

[0003] However, existing methods for building intelligent learning environments often have the following problems:

[0004] 1. Lack of sufficient attention to individual differences among learners, resulting in poor learning outcomes;

[0005] 2. Failure to effectively combine learning scenarios and teaching needs, resulting in poor adaptability of the learning environment;

[0006] 3. Learning resources are scattered and lack effective integration and scheduling mechanisms. Summary of the invention

[0007] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0008] In view of the problems existing in the above-mentioned existing intelligent learning environment construction method, the present invention is proposed.

[0009] Therefore, the technical problem solved by the present invention is to solve the problem that the existing intelligent learning environment construction method lacks sufficient attention to the individual differences of learners, resulting in poor learning effects, failure to effectively combine learning scenarios and teaching needs, resulting in poor adaptability of the learning environment, scattered learning resources, and lack of effective integration and scheduling mechanisms.

[0010] To solve the above technical problems, the present invention provides the following technical solutions: a method for constructing an intelligent learning environment, comprising the following steps: S1: Collecting learner data: Collecting the learner data through the learner's learning behavior, learning achievements and interest category information; S2: Establishing a learner model: Using a machine learning algorithm, analyzing and processing the collected learner data, constructing the learner model, and obtaining the learner's learning simulation parameters under the current subject; S3: Selecting an intelligent learning scenario: Obtaining the learning simulation parameters under the current subject, and determining whether the learner likes the current subject based on the size of the learning simulation parameters; S4: Integrating learning resources: By building a learning resource library, the integration and scheduling of various learning resources are realized to meet the learners' learning needs in different scenarios; S5: Constructing an intelligent learning environment: Integrating the learner model, the adjustment mechanism of the intelligent learning scenario and the learning resource library to construct an intelligent learning environment.

[0011] As a preferred scheme of the intelligent learning environment construction method described in the present invention, wherein: the learning behavior in the learner data is specifically: the number of times the learner learns in a single time period; the learning outcomes in the learner data are specifically: the learning progress of the subject selected by the learner at the current time point; the interest and hobby categories in the learner data are specifically: the learning subject categories selected by the learner.

[0012] As a preferred solution of the intelligent learning environment construction method of the present invention, wherein: constructing the learner model and obtaining the learning simulation parameters under the current subject of the learner is specifically: H1: obtaining the interest category in the learner data; H2: constructing the learner model and obtaining the learning simulation parameters under the current subject;

[0013] The learner model constructed is specifically:

[0014]

[0015] Among them, δ is the learning simulation parameter; n is the number of times in the single time period learning process, times; α1 is the progress of the first learning in the single time period learning process, %; α n is the progress of the nth learning in a single time period, %; 1.205, 0.64 and -1 are adjustment constants; dn is the integral operation.

[0016] As a preferred scheme of the intelligent learning environment construction method described in the present invention, when the learning simulation parameters under the current subject are not lower than the set threshold, it is defined that the learner likes the learning of the current subject, and the current learning scene is also selected in the next stage; when the learning simulation parameters under the current subject are lower than the set threshold, it is defined that the learner does not like the learning of the current subject, and a different category of learning scenes is selected in the next stage.

[0017] As a preferred solution of the intelligent learning environment construction method described in the present invention, the set threshold is specifically 1.976.

[0018] As a preferred solution of the intelligent learning environment construction method described in the present invention, when building the learning resource library, various types of learning resources are classified and labeled to achieve integration and selection of learning resources.

[0019] As a preferred solution of the intelligent learning environment construction method described in the present invention, when constructing the learner model, a decision tree and a neural network machine learning algorithm are used.

[0020] The present invention provides a method for constructing an intelligent learning environment, which has the following beneficial effects: the present invention adopts a learner model-driven construction method, pays full attention to individual differences of learners, improves learning effects, designs intelligent and personalized learning scenarios according to learner models and teaching needs, enhances the adaptability of the learning environment, and realizes the integration and scheduling of learning resources by building a learning resource library, thereby improving the efficiency of learning resource utilization. This solves the problem that the existing intelligent learning environment construction methods lack sufficient attention to individual differences of learners, resulting in poor learning effects, failure to effectively combine learning scenarios and teaching needs, resulting in poor adaptability of the learning environment, scattered learning resources, and lack of effective integration and scheduling mechanisms. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0022] Figure 1 This is an overall method flow chart of the intelligent learning environment construction method provided by the present invention.

[0023] Figure 2 A flow chart of the method for constructing a learner model and obtaining learning simulation parameters for the learner's current subject provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0025] Existing methods for building intelligent learning environments often have the following problems:

[0026] 1. Lack of sufficient attention to individual differences among learners, resulting in poor learning outcomes;

[0027] 2. Failure to effectively combine learning scenarios and teaching needs, resulting in poor adaptability of the learning environment;

[0028] 3. Learning resources are scattered and lack effective integration and scheduling mechanisms.

[0029] Therefore, please refer to Figure 1 The present invention provides a method for constructing an intelligent learning environment, comprising the following steps:

[0030] S1: Collect learner data: Collect learner data through learners’ learning behaviors, learning outcomes, and interest category information;

[0031] S2: Building a learner model: Using machine learning algorithms, analyze and process the collected learner data, build a learner model, and obtain the learning simulation parameters of the learner's current subject;

[0032] S3: Selecting an intelligent learning scenario: obtaining a learning simulation parameter under the current subject, and determining whether the learner is satisfied with the learning of the current subject based on the size of the learning simulation parameter;

[0033] S4: Integrate learning resources: By building a learning resource library, various learning resources can be integrated and scheduled to meet learners' learning needs in different scenarios;

[0034] S5: Build an intelligent learning environment: Integrate the learner model, the adjustment mechanism of the intelligent learning scenario and the learning resource library to build an intelligent learning environment.

[0035] Specifically, the learning behaviors in the learner data are: the number of times the learner has learned in a single time period;

[0036] It should be noted that in actual operation, the single time period can be preferentially selected as one week, the number of learning times within the one-week time period is obtained, and the progress of each learning is simultaneously counted.

[0037] The learning outcomes in the learner data are specifically: the learning progress of the subject selected by the learner at the current time point;

[0038] It should be noted that the overall learning progress is defined as unit 1.

[0039] The interest and hobby categories in the learner data are specifically: the categories of learning subjects selected by the learner.

[0040] For further information, see Figure 2 , build a learner model, and obtain the learning simulation parameters of the learner's current subject:

[0041] H1: Obtain the interest and hobby categories in learner data;

[0042] H2: Build a learner model and obtain the learning simulation parameters under the current subject;

[0043] Among them, the learner model constructed is specifically:

[0044]

[0045] Among them, δ is the learning simulation parameter; n is the number of times in the single time period learning process, times; α1 is the progress of the first learning in the single time period learning process, %; α n is the progress of the nth learning in a single time period, %; 1.205, 0.64 and -1 are adjustment constants; dn is the integral operation.

[0046] Specifically, when the learning simulation parameters under the current subject are not lower than the set threshold, it is defined that the learner likes to learn the current subject, and the current learning scenario is also selected in the next stage; when the learning simulation parameters under the current subject are lower than the set threshold, it is defined that the learner does not like to learn the current subject, and a different category of learning scenario is selected in the next stage.

[0047] Furthermore, the threshold is set to be 1.976.

[0048] Furthermore, when building a learning resource library, various types of learning resources should be classified and labeled to achieve the integration and selection of learning resources.

[0049] It should be noted that: in the specific construction process, in addition to the mature application of existing technologies, the learning resource library can also be optimized and constructed. The specific implementation steps are as follows:

[0050] 1. Resource classification system design

[0051] Clarify resource types: According to the nature and purpose of learning resources, resources can be divided into types such as documents, videos, audios, interactive learning tools, online courses, simulation tests, etc.

[0052] Design classification dimensions: Classify according to dimensions such as subject, grade, knowledge point, teaching objectives, and resource format.

[0053] 2. Resource labeling

[0054] Tagging system design: Design a tagging system that includes general tags (such as difficulty level, resource type) and custom tags (such as subject-specific terms, teaching strategies).

[0055] Tag assignment rules: Develop a set of rules to guide resource administrators on how to assign appropriate tags to each resource, ensuring the accuracy and consistency of tags.

[0056] 3. Resource Flow

[0057] Resource collection: Collect various learning resources through crawler technology, partners’ provision, teachers’ uploads, etc.

[0058] Resource review: Conduct content review on the collected resources to ensure their quality and applicability.

[0059] Metadata management: Create metadata records for each resource, including resource title, description, author, publication date, copyright information, etc.

[0060] Resource classification and labeling: Classify and label resources according to the classification system and labeling system.

[0061] Resource storage: Store processed resources in the resource library to ensure the accessibility and security of resources.

[0062] IV. Resource Selection Mechanism

[0063] Intelligent recommendation algorithm: Develop an intelligent recommendation algorithm to recommend appropriate resources based on learners' historical behavior, preferences, and learning progress.

[0064] Search and filter functions: Provides a search box and filter options, allowing users to filter and find resources based on keywords, resource type, difficulty, and other conditions.

[0065] User evaluation and feedback: Allow users to evaluate and provide feedback on the resources they have used, which will serve as a basis for resource selection and optimization.

[0066] V. Specific implementation steps

[0067] Establish the goals and requirements for building the resource library, and develop a plan for building the resource library.

[0068] Build a resource library management platform, including functions such as resource uploading, editing, reviewing, and publishing.

[0069] Design and implement resource classification and labeling systems, and formulate relevant rules and standards.

[0070] Develop resource integration tools to realize automated resource collection and classification and labeling processing.

[0071] Write intelligent recommendation and search algorithms and integrate them into the resource library management platform.

[0072] Test the resource library to ensure the stability, security and usability of the system.

[0073] Provide user training and technical support to ensure that teachers and students can use the resource library effectively.

[0074] Through the above steps, the method of the present invention can effectively build a structured and intelligent learning resource library to provide learners with convenient and personalized resource selection and usage experience.

[0075] Furthermore, when building the learner model, decision tree and neural network machine learning algorithms are used for construction.

[0076] It should be noted that in the specific construction process, in addition to the mature application of existing technologies, you can also refer to the following specific implementation steps:

[0077] 1. Data Preparation

[0078] Data collection: According to the methods described above, learners’ learning behavior data, learning outcomes data, and interest and hobby information are collected.

[0079] Data preprocessing: clean data, handle missing values, standardize or normalize data, and ensure data quality.

[0080] 2. Feature Engineering

[0081] Feature selection: Analyze the data to identify the features that are important for building the learner model.

[0082] Feature extraction: Use statistical methods or deep learning techniques to extract features from raw data that are helpful for model building.

[0083] 3. Learner Model Construction

[0084] Decision tree model: a. Select an appropriate decision tree algorithm, such as classification and regression tree (CART), ID3 or C4.5 algorithm. b. Use the collected learner data to train the decision tree model. c. Prune the model to avoid overfitting and improve the generalization ability of the model. d. Evaluate model performance, such as accuracy, recall, F1 score, etc.

[0085] Neural network model: a. Design the neural network structure, determine the number of layers, number of neurons, activation function, etc. b. Use the learner's data to train the neural network, and use algorithms such as gradient descent and back propagation to optimize the network weights. c. Validate the network through the validation set and adjust the network parameters to obtain the best performance. d. Use the test set to evaluate the accuracy and generalization ability of the neural network model.

[0086] IV. Model Evaluation and Optimization

[0087] Cross-validation: The cross-validation method is used to evaluate the stability and reliability of the model.

[0088] Performance indicators: According to the model type, select appropriate performance indicators for evaluation, such as accuracy, recall rate, F1 score for classification models, mean square error (MSE), coefficient of determination (R 2 )wait.

[0089] Model tuning: Based on the evaluation results, adjust the model parameters or structure to improve model performance.

[0090] 5. Model deployment and application

[0091] Deploy the model: Deploy the trained learner model to the learning environment so that it can serve learners in real applications.

[0092] Real-time updates: Models are updated regularly to reflect changes in learner behavior and preferences.

[0093] User feedback: Collect user feedback on the model to further optimize model performance.

[0094] 6. Specific implementation steps

[0095] Determine the purpose and requirements of building a learner model and select an appropriate machine learning algorithm.

[0096] Prepare the data set, perform data cleaning and preprocessing.

[0097] Perform feature engineering to select and extract key features.

[0098] The learner models are constructed using decision tree algorithm and neural network algorithm respectively.

[0099] Train, validate, and test the model to evaluate model performance.

[0100] Adjust model parameters based on the evaluation results to optimize model performance.

[0101] Deploy the optimized model into the learning environment for real-time learning and prediction.

[0102] Through the above steps, the method of the present invention can construct an accurate and effective learner model, thereby providing support for personalized learning.

[0103] In order to verify the technical effect of the present invention, the following simulation verification test is now provided:

[0104] 1. Goal Setting

[0105] Verify the actual effect of the intelligent learning environment construction method on improving learning outcomes and resource utilization efficiency.

[0106] 2. Preparation

[0107] Collect learner data: including learning behavior, learning outcomes, and interest category information.

[0108] Building learner models: using decision tree and neural network algorithms.

[0109] Build a learning resource library: classify and label various learning resources.

[0110] 3. Implementation phase

[0111] Integrate learning resources: Integrate and schedule resources through the learning resource library.

[0112] Build an intelligent learning environment: combine learner models, intelligent learning scenario adjustment mechanisms and learning resource libraries.

[0113] Perform real-time learning and prediction: Deploy optimized models into learning environments.

[0114] 4. Data Collection

[0115] Collect learning data before and after the experiment, including learners' learning behavior, learning outcomes, and learning satisfaction.

[0116] 5. Data Analysis

[0117] The collected data were analyzed and the changes before and after the experiment were compared to evaluate the effectiveness of the intelligent learning environment construction method.

[0118] Data certification form:

[0119]

[0120] Data analysis results:

[0121] After the experiment, the learners’ learning behaviors increased by an average of 56%.

[0122] Learning outcomes progress improved by an average of 31%.

[0123] Learner satisfaction ratings increased by approximately 40% on average.

[0124] The present invention adopts a learner model-driven construction method, pays full attention to individual differences of learners, improves learning effects, designs intelligent and personalized learning scenarios according to learner models and teaching needs, enhances the adaptability of the learning environment, and realizes the integration and scheduling of learning resources by building a learning resource library, thereby improving the efficiency of learning resource utilization. It solves the problems that the existing intelligent learning environment construction methods lack sufficient attention to individual differences of learners, resulting in poor learning effects, failure to effectively combine learning scenarios and teaching needs, resulting in poor adaptability of the learning environment, scattered learning resources, and lack of effective integration and scheduling mechanisms.

[0125] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing an intelligent learning environment, characterized in that: The steps include: S1: Collect learner data: collect learner data through learner's learning behavior, learning achievements and interest category information; S2: Building a learner model: using a machine learning algorithm to analyze and process the collected learner data, building the learner model, and obtaining the learning simulation parameters of the learner under the current subject; S3: Selecting an intelligent learning scenario: obtaining the learning simulation parameters under the current subject, and determining whether the learner likes the learning of the current subject based on the magnitude of the learning simulation parameters; S4: Integrate learning resources: By building a learning resource library, various learning resources can be integrated and scheduled to meet learners' learning needs in different scenarios; S5: Constructing an intelligent learning environment: Integrate the learner model, the adjustment mechanism of the intelligent learning scenario and the learning resource library to construct an intelligent learning environment.

2. The method for constructing an intelligent learning environment according to claim 1, characterized in that: The learning behavior in the learner data specifically includes: the number of times the learner learns in a single time period; The learning outcomes in the learner data specifically include: the learning progress of the subject selected by the learner at the current time point; The interest and hobby categories in the learner data are specifically: the learning subject categories selected by the learner.

3. The method for constructing an intelligent learning environment according to claim 2, characterized in that: Constructing the learner model and obtaining the learning simulation parameters of the learner's current subject are specifically: H1: Obtain the interest and hobby categories in the learner data; H2: Construct the learner model and obtain the learning simulation parameters under the current subject; The learner model constructed is specifically: Among them, δ is the learning simulation parameter; n is the number of times in the single time period learning process, times; α1 is the progress of the first learning in the single time period learning process, %; α n is the progress of the nth learning in a single time period, %; 1.205, 0.64 and -1 are adjustment constants; dn is the integral operation.

4. The method for constructing an intelligent learning environment according to claim 3, characterized in that: When the learning simulation parameters under the current subject are not lower than the set threshold, it is defined that the learner likes learning the current subject, and the current learning scene will be selected in the next stage; when the learning simulation parameters under the current subject are lower than the set threshold, it is defined that the learner does not like learning the current subject, and a different category of learning scene will be selected in the next stage.

5. The method for constructing an intelligent learning environment according to claim 4, characterized in that: The set threshold is specifically 1.

976.

6. The method for constructing an intelligent learning environment according to claim 5, characterized in that: When building the learning resource library, various types of learning resources are classified and labeled to achieve integration and selection of learning resources.

7. The method for constructing an intelligent learning environment according to claim 6, characterized in that: When constructing the learner model, a decision tree and a neural network machine learning algorithm are used.

Images