Educational resource security sharing system and method based on big data

Abstract

The invention belongs to the technical field of education systems, and discloses an education resource security sharing system and method based on big data, and the system comprises a data collection module, a learning behavior analysis module, a personalized path generation module, a resource optimization distribution module, a policy analysis module, a security management module, and an interaction interface module. According to the invention, through deep learning and data mining technologies, learning behaviors and feedback of students are effectively collected and analyzed, a student data set is generated, and a solid foundation is provided for learning mode analysis and behavior mode recognition; a personalized learning path with high fitness is designed for students, the learning efficiency and experience are improved, a resource optimization allocation module effectively predicts resource demands, optimizes allocation and improves the resource use efficiency through association rule learning and sequence pattern mining, and a policy analysis module applies a time sequence and a regression analysis technology to improve the resource utilization efficiency. And a scientific basis is provided for making educational policies.

Description

Technical Field

[0001] The present invention belongs to the technical field of educational systems. Specifically, it relates to a secure educational resource sharing system and method based on big data. Background Art

[0002] The field of educational technology is a broad area that encompasses the use of technological means to enhance the educational process and outcomes. In this field, technology is used to support and improve teaching and learning activities, including online learning platforms, deep learning models, intelligent teaching software, and educational games. In recent years, with the rapid development of technology, the field of educational technology has begun to place more emphasis on personalized learning, data-driven teaching strategies, and the application of augmented and virtual reality in education. The core goal of this field is to improve the accessibility, effectiveness, and attractiveness of education while using data analysis to optimize the learning process and the management of educational resources.

[0003] Among them, the secure educational resource sharing system based on big data is a system that combines big data analysis and network security technology to optimize the sharing of educational resources. The purpose of this system is to improve the quality of education and the utilization efficiency of resources by sharing educational resources efficiently and securely. It aims to allow educational institutions and learners to better access and use various educational resources, such as e-textbooks, online courses, and multimedia teaching materials. In addition, the system also endeavors to improve the learning experience and teaching outcomes through personalized recommendations and resource optimization. To achieve these goals, the system usually uses big data technology to analyze and process a large amount of education-related data, such as students' learning behaviors, grades, and feedback. Through these analyses, the system can provide customized learning materials and courses, as well as optimize the allocation of educational resources. To ensure the security of the sharing process, the system will also implement advanced network security measures, such as data encryption, security authentication, and access control, to ensure the security and privacy protection of educational resources during the sharing process.

[0004] Traditional educational systems have obvious deficiencies in comparison. These systems usually lack effective analytical capabilities and are difficult to understand and respond to the personalized learning needs of students, resulting in a lack of personalization and adaptability in the design of learning paths. Traditional systems often lack precision in resource allocation and cannot fully predict and meet the learning resource needs of different students, leading to low utilization efficiency of educational resources. In terms of policy analysis, there is a lack of effective analysis tools, making educational policies often deviate from the actual learning situation and have poor effects. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art and to propose a secure educational resource sharing system and method based on big data.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: An educational resource security sharing system based on big data includes a data collection module, a learning behavior analysis module, a personalized path generation module, a resource optimization allocation module, a policy analysis module, a security management module, and an interactive interface module; The data collection module, based on a deep learning model, uses data mining techniques to collect students' behavior and feedback information, and performs data cleaning and integration to generate a student dataset; The learning behavior analysis module, based on the student dataset, uses clustering algorithms and predictive modeling techniques to analyze learning patterns and identify behavior patterns, generating a student learning behavior analysis report; The personalized path generation module, based on the student learning behavior analysis report, uses collaborative filtering and content recommendation algorithms to design personalized learning paths and perform fitness evaluation, generating personalized learning paths; The resource optimization allocation module, based on the personalized learning path, uses association rule learning and sequence pattern mining techniques to predict resource requirements and formulate resource allocation strategies, generating an optimized resource allocation plan; The policy analysis module, based on the optimized resource allocation plan, uses time series analysis and regression analysis techniques to predict the impact of education policies and evaluate policy effects, generating a policy analysis report; The security management module, based on the policy analysis report, uses data encryption technology and access control strategies to conduct security audits of data and perform risk assessments, generating a security management report; The interactive interface module, based on the security management report, uses user experience design principles to design and optimize the interface and collect feedback information, generating a user interface; The student dataset includes students' online learning behaviors, exam scores, interaction feedback, and personal interests. The student learning behavior analysis report includes learning efficiency, preferred subjects, active periods, and learning difficulties. The policy analysis report includes the impact of policy changes on learning effects, improvements in resource utilization, and feedback from teachers and students. The security management report specifically refers to the security status of data transmission and storage, access permission management, and security event records.

[0007] The following is a further optimization of the above technical solution by the present invention: The data collection module includes a behavior log sub-module, a score record sub-module, an interaction data sub-module, and a feedback information sub-module; The behavior log sub-module, based on a deep learning model, uses data crawling techniques to collect students' online learning behavior logs and formats the data to generate formatted behavior logs; The achievement record sub-module summarizes and analyzes students' achievement records based on formatted behavior logs using statistical analysis methods, and generates a comprehensive achievement analysis report; The interaction data sub-module analyzes students' interaction data on the online platform based on the comprehensive achievement analysis report using interaction analysis techniques, and generates an interaction data analysis report; The feedback information sub-module analyzes students' feedback information based on the interaction data analysis report using text mining techniques, and generates a comprehensive analysis of students' feedback.

[0008] Further optimization: The learning behavior analysis module includes a clustering analysis sub-module, a learning preference prediction sub-module, a behavior pattern recognition sub-module, and an achievement analysis sub-module; The clustering analysis sub-module divides students' learning behaviors into groups using the K-means clustering algorithm based on the comprehensive analysis of students' feedback, and generates learning behavior groups; The learning preference prediction sub-module predicts students' learning preferences using the decision tree algorithm based on the learning behavior groups, and generates a learning preference prediction report; The behavior pattern recognition sub-module identifies students' behavior patterns using sequence pattern mining techniques based on the learning preference prediction report, and generates a behavior pattern recognition report; The achievement analysis sub-module analyzes the relationship between students' achievements and behavior patterns using regression analysis techniques based on the behavior pattern recognition report, and generates a report on students' learning behavior analysis.

[0009] Further optimization: The personalized path generation module includes a collaborative filtering sub-module, a content recommendation sub-module, a path design sub-module, and a fitness evaluation sub-module; The collaborative filtering sub-module analyzes the similarity between students using the collaborative filtering algorithm based on the report on students' learning behavior analysis, makes personalized resource recommendations, and generates a preliminary list of personalized resource recommendations; The content recommendation sub-module generates an optimized list of personalized resource recommendations using the content-based recommendation algorithm based on the preliminary list of personalized resource recommendations; The path design sub-module designs the learning route and progress using the path planning algorithm based on the optimized list of personalized resource recommendations, and generates a personalized learning path plan; The fitness evaluation sub-module examines the practicality and effectiveness of the path using the multi-armed bandit algorithm based on the personalized learning path plan, and generates the final personalized learning path.

[0010] Further optimization: The resource optimization allocation module includes a resource demand prediction sub-module, a resource allocation strategy sub-module, and a resource usage efficiency analysis sub-module; The resource demand prediction sub-module predicts the resource demand in the future time period based on the final personalized learning path, using time series analysis, and generates a resource demand prediction report; The resource allocation strategy sub-module generates a resource allocation strategy report based on the resource demand prediction report, using association rule learning; The resource usage efficiency analysis sub-module analyzes the efficiency and trend of resource usage based on the resource allocation strategy report, using sequential pattern mining, and generates an optimized resource allocation plan.

[0011] Further optimization: The policy analysis module includes a policy impact prediction sub-module, a policy effect evaluation sub-module, and a data integration sub-module; The policy impact prediction sub-module conducts a trend analysis of educational policy changes based on the optimized resource allocation plan, using time series analysis, and generates an educational policy impact prediction report; The policy effect evaluation sub-module generates a policy effect evaluation report based on the educational policy impact prediction report, using regression analysis; The data integration sub-module generates a comprehensive policy analysis report based on the policy effect evaluation report, using data warehouse and data summarization technologies.

[0012] Further optimization: The security management module includes a data encryption sub-module, an access control sub-module, and a security monitoring sub-module; The data encryption sub-module generates encrypted data based on the comprehensive policy analysis report, using encryption algorithms, including symmetric and asymmetric encryption algorithms; The access control sub-module establishes access control rules based on the encrypted data, using access control policies; The security monitoring sub-module generates a security management report based on the access control rules, using an intrusion detection system and abnormal behavior analysis technologies based on network behavior analysis and anomaly detection algorithms.

[0013] Further optimization: The interaction interface module includes an interface design sub-module, a user experience optimization sub-module, and a feedback collection sub-module; The interface design sub-module conducts interface layout planning and prototype design based on the security management report, using information architecture design and interaction design principles, and generates a preliminary interface design; The user experience optimization sub-module conducts user experience evaluation and interface adjustment based on the preliminary interface design, using usability testing and interface review methods, and generates an optimized interface design; The feedback collection sub-module collects and analyzes user experience data based on the optimized interface design, using a user feedback mechanism and data analysis tools, and generates a user interaction interface; The information architecture design specifically defines the organization and hierarchical structure of the interface content. The interaction design principles include the usability principle, user feedback, and interface consistency. The data analysis tools include web analytics services and sentiment analysis techniques, which are used to quantify and analyze user behavior and feedback.

[0014] The present invention also provides a method for secure sharing of educational resources based on big data. The method for secure sharing of educational resources based on big data is executed based on the above-mentioned system for secure sharing of educational resources based on big data, and includes the following steps: S1: Based on a deep learning model, using data mining techniques, real-time collect the online learning behaviors, exam scores, interaction feedback, and personal interests of students, perform data cleaning and integration, and generate a student dataset. S2: Based on the student dataset, using machine learning algorithms, analyze the learning patterns and identify behavior patterns, and generate a student learning behavior analysis report. S3: Based on the student learning behavior analysis report, using a recommendation system algorithm, generate a personalized learning path. S4: Based on the personalized learning path, using a resource optimization algorithm, predict resource requirements and formulate an allocation strategy, and generate an optimized resource allocation plan. S5: Based on the optimized resource allocation plan, using statistical analysis methods, analyze the impact of educational policies, and generate a policy analysis report. S6: Based on the policy analysis report, using data security techniques, perform data security auditing and risk assessment, and generate a security management report.

[0015] The following is a further optimization of the above technical solution by the present invention: The data mining techniques include decision trees, association rule analysis, and principal component analysis. The machine learning algorithms include K-means clustering, support vector machines, and neural networks. The recommendation system algorithms include collaborative filtering and content-based recommendation. The resource optimization algorithms include association rule learning and sequential pattern mining. The statistical analysis methods include time series analysis and regression analysis. The data security techniques include AES encryption and role-based access control.

[0016] The present invention adopts the above technical solution and has the following beneficial effects: In the present invention, through deep learning and data mining techniques, the system efficiently collects and analyzes students' learning behaviors and feedback information, thereby generating a more accurate student dataset; these datasets provide a solid foundation for learning behavior analysis, making the analysis of learning patterns more precise and helping to identify students' behavior patterns; the personalized path generation module uses advanced collaborative filtering and content recommendation algorithms to design a more suitable personalized learning path for students, which not only improves learning efficiency but also enhances students' learning experience; the application of the resource optimization allocation module can effectively predict resource requirements and optimize resource allocation through association rule learning and sequence pattern mining techniques, thereby improving the utilization efficiency of educational resources; the policy analysis module uses time series analysis and regression analysis techniques to provide a scientific basis for the formulation and adjustment of educational policies.

[0017] The present invention will be further described below in conjunction with the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is the system flowchart of the embodiment of the present invention; Figure 2 is the schematic diagram of the system framework in the embodiment of the present invention; Figure 3 is the flowchart of the data acquisition module in the embodiment of the present invention; Figure 4 is the flowchart of the learning behavior analysis module in the embodiment of the present invention; Figure 5 is the flowchart of the personalized path generation module in the embodiment of the present invention; Figure 6 is the flowchart of the resource optimization allocation module in the embodiment of the present invention; Figure 7 is the flowchart of the policy analysis module in the embodiment of the present invention; Figure 8 is the flowchart of the security management module in the embodiment of the present invention; Figure 9 is the flowchart of the interaction interface module in the embodiment of the present invention; Figure 10 is the schematic diagram of the method steps in the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Please refer to Figures 1 to 2 , the present invention provides a technical solution: an educational resource security sharing system based on big data includes a data acquisition module, a learning behavior analysis module, a personalized path generation module, a resource optimization allocation module, a policy analysis module, a security management module, and an interaction interface module; The data collection module is based on a deep learning model and uses data mining techniques to collect students' behavior and feedback information, and then conducts data cleaning and integration to generate a student dataset; The learning behavior analysis module is based on the student dataset and uses clustering algorithms and predictive modeling techniques to analyze learning patterns and identify behavior patterns, generating a student learning behavior analysis report; The personalized path generation module is based on the student learning behavior analysis report and uses collaborative filtering and content recommendation algorithms to design personalized learning paths and conduct fitness evaluations, generating personalized learning paths; The resource optimization allocation module is based on the personalized learning path and uses association rule learning and sequential pattern mining techniques to predict resource requirements and formulate resource allocation strategies, generating an optimized resource allocation plan; The policy analysis module is based on the optimized resource allocation plan and uses time series analysis and regression analysis techniques to predict the impact of education policies and evaluate policy effects, generating a policy analysis report; The security management module is based on the policy analysis report and uses data encryption technology and access control strategies to conduct security audits of data and perform risk assessments, generating a security management report; The interactive interface module is based on the security management report and uses user experience design principles to design and optimize the interface and collect feedback information, generating a user interaction interface; The student dataset includes students' online learning behaviors, exam scores, interaction feedback, and personal interests. The student learning behavior analysis report includes learning efficiency, preferred subjects, active periods, and learning difficulties. The policy analysis report includes the impact of policy changes on learning effects, improvements in resource utilization, and feedback from teachers and students. The security management report specifically refers to the security status of data transmission and storage, access permission management, and security event records.

[0020] Through precise data collection and analysis, the system can personalizedly meet the needs of students and teachers, effectively reducing resource waste; the design of personalized learning paths not only enhances students' learning motivation but also specifically helps overcome learning difficulties, thereby improving learning effectiveness; the application of the policy analysis module provides data support for the formulation and adjustment of education policies, making policies more in line with actual needs and effects; the security management module ensures data security and privacy protection, increasing users' trust in the system; the user-friendly interactive interface improves user participation and satisfaction.

[0021] Please refer to Figure 3 , the data collection module includes a behavior log sub-module, a score record sub-module, an interaction data sub-module, and a feedback information sub-module; The behavior log sub-module, based on a deep learning model, uses data crawling technology to collect students' online learning behavior logs, formats the data, and generates formatted behavior logs. The performance record sub-module, based on the formatted behavior logs, uses statistical analysis methods to summarize and analyze students' performance records and generate a comprehensive performance analysis report. The interaction data sub-module, based on the comprehensive performance analysis report, uses interaction analysis technology to analyze students' interaction data on the online platform and generate an interaction data analysis report. The feedback information sub-module, based on the interaction data analysis report, uses text mining technology to analyze students' feedback information and generate a comprehensive analysis of students' feedback.

[0022] The behavior log sub-module collects students' behavior data on the online learning platform through data crawling technology, including behaviors such as clicks, browsing, and answering questions; uses a deep learning model to process and analyze these raw data to ensure data consistency and accuracy; generates formatted behavior logs, which include students' learning activities, timestamps, and other relevant information; the main task of this sub-module is to efficiently capture students' learning behaviors and provide a key data basis for subsequent analysis.

[0023] The performance record sub-module, based on the formatted behavior logs, uses statistical analysis methods to comprehensively analyze students' performance records; this includes integrating and statistically analyzing students' exam scores, assignment scores, and other assessment data; the result is the generation of a comprehensive performance analysis report, which reflects students' academic performance and progress; through this sub-module, educators can better understand students' academic achievements and weaknesses in order to provide targeted support.

[0024] The interaction data sub-module, based on the comprehensive performance analysis report, uses interaction analysis technology to deeply analyze students' interaction data on the online platform; this includes students' classroom participation, discussion activities, online quizzes, and other interaction behaviors; through these data, educators can more comprehensively understand students' learning behaviors and engagement levels, and thus better adjust teaching strategies to meet students' needs.

[0025] The feedback information sub-module uses text mining technology to automatically analyze the text information such as students' submitted assignments, forum posts, and feedback questionnaires; this sub-module not only conducts sentiment analysis but also extracts themes to gain insights into students' needs and emotional states; through this process, the system generates a comprehensive analysis of students' feedback, providing educators with more insights to help better understand students' feedback and needs.

[0026] Please refer to Figure 4 , the learning behavior analysis module includes a clustering analysis sub-module, a learning preference prediction sub-module, a behavior pattern recognition sub-module, and a performance analysis sub-module. Based on the comprehensive analysis of students' feedback, the clustering analysis sub-module uses the K-means clustering algorithm to group students' learning behaviors and generate learning behavior groups. Based on the learning behavior groups, the learning preference prediction sub-module uses the decision tree algorithm to predict students' learning preferences and generate a learning preference prediction report. Based on the learning preference prediction report, the behavior pattern recognition sub-module uses sequence pattern mining technology to identify students' behavior patterns and generate a behavior pattern recognition report. Based on the behavior pattern recognition report, the academic performance analysis sub-module uses regression analysis technology to analyze the relationship between students' academic performance and behavior patterns and generate a student learning behavior analysis report.

[0027] Based on the comprehensive analysis of students' feedback, the clustering analysis sub-module applies the K-means clustering algorithm to cluster students' learning behaviors into different learning behavior groups. This process helps classify students according to their learning behavior characteristics to better understand their learning habits and patterns. Finally, it generates learning behavior groups, providing basic data for subsequent analysis, which can be used for more refined personalized support and suggestions for students.

[0028] Based on the learning behavior groups, the learning preference prediction sub-module uses the decision tree algorithm to predict students' learning preferences, including subject preferences and learning method preferences, etc. The decision tree model relies on the information of the learning behavior groups to infer students' learning preferences, thereby generating a learning preference prediction report. This report provides important guidance for educators on how to personalize the design of learning paths to meet students' needs.

[0029] Based on the learning preference prediction report, the behavior pattern recognition sub-module uses sequence pattern mining technology to identify students' behavior patterns, including the sequence and frequency of learning behaviors. By analyzing the time series data of students' learning behaviors, it identifies typical behavior patterns during the learning process, such as when to access specific content or perform specific operations. The generated behavior pattern recognition report helps understand students' learning behavior habits and provides a basis for personalized support and suggestions.

[0030] Based on the behavior pattern recognition report, the academic performance analysis sub-module uses regression analysis technology to deeply analyze the correlation between students' academic performance and their learning behavior patterns. Regression analysis helps identify which learning behavior patterns have positive or negative effects on academic performance, thereby providing key insights for educators. Finally, it generates a student learning behavior analysis report, which can be used to more precisely formulate personalized teaching strategies and student support plans.

[0031] Please refer to Figure 5, the personalized path generation module includes a collaborative filtering sub-module, a content recommendation sub-module, a path design sub-module, and a fitness evaluation sub-module; The collaborative filtering sub-module, based on the student learning behavior analysis report, uses the collaborative filtering algorithm to analyze the similarity among students, make personalized resource recommendations, and generate a preliminary personalized resource recommendation list; The content recommendation sub-module, based on the preliminary personalized resource recommendation list, uses the content-based recommendation algorithm to generate an optimized personalized resource recommendation list; The path design sub-module, based on the optimized personalized resource recommendation list, uses the path planning algorithm to design the learning route and progress, and generate a personalized learning path plan; The fitness evaluation sub-module, based on the personalized learning path plan, uses the multi-armed bandit algorithm to examine the practicality and effectiveness of the path, and generate the final personalized learning path.

[0032] The collaborative filtering sub-module, based on the student learning behavior analysis report, uses the collaborative filtering algorithm to analyze the similarity of learning behaviors among students; by discovering the common interests and behavior patterns among students, it generates a preliminary personalized resource recommendation list.

[0033] The content recommendation sub-module, based on the preliminary personalized resource recommendation list, uses the content-based recommendation algorithm to optimize the recommendation list; this sub-module considers the specific content of the resources and the interests of the students to ensure that the recommendations are more in line with the needs of the students; finally, it generates an optimized personalized resource recommendation list.

[0034] The path design sub-module, based on the optimized personalized resource recommendation list, uses the path planning algorithm to design the learning route and progress; considering the learning goals of the students and the availability of resources, it helps to formulate a specific learning plan, including the order of resource use and the learning schedule; the generated personalized learning path plan helps students better organize their learning activities.

[0035] The fitness evaluation sub-module, based on the personalized learning path plan, uses the multi-armed bandit algorithm to evaluate the practicality and effectiveness of the path; by monitoring the feedback and progress of students during the learning process, it continuously adjusts the path to improve its fitness; finally, it generates the final personalized learning path to meet the academic needs and learning goals of the students.

[0036] Please refer to Figure 6 , the resource optimization and allocation module includes a resource demand prediction sub-module, a resource allocation strategy sub-module, and a resource usage efficiency analysis sub-module; The resource demand prediction sub-module, based on the final personalized learning path, uses time series analysis to predict the resource demand in the future time period and generate a resource demand prediction report; Based on the resource demand prediction report, the resource allocation strategy sub-module uses association rule learning to generate a resource allocation strategy report; Based on the resource allocation strategy report, the resource utilization efficiency analysis sub-module uses sequential pattern mining to analyze the efficiency and trend of resource utilization, and generates an optimized resource allocation plan.

[0037] Based on the final personalized learning path, the resource demand prediction sub-module uses time series analysis techniques to predict the resource demand in the future time period; this sub-module not only considers the current needs of students, but also takes into account the changes that occur during the learning process of students; the generated resource demand prediction report provides an accurate basis for resource allocation.

[0038] Based on the resource demand prediction report, the resource allocation strategy sub-module uses association rule learning techniques to generate a resource allocation strategy report; this sub-module provides a detailed plan for resource allocation by analyzing the correlation between resources and the needs of students; these plans consider the availability of resources and the priorities of students to ensure the reasonable allocation of resources.

[0039] Based on the resource allocation strategy report, the resource utilization efficiency analysis sub-module uses sequential pattern mining techniques to analyze the utilization efficiency and trend of resources; this sub-module helps to monitor the actual utilization of resources, identify possible waste or bottlenecks, and provide an optimized resource allocation plan; through continuous analysis and adjustment, the system can improve the utilization efficiency of educational resources to better support the learning needs of students.

[0040] Please refer to Figure 7 , the policy analysis module includes a policy impact prediction sub-module, a policy effect evaluation sub-module, and a data integration sub-module; Based on the optimized resource allocation plan, the policy impact prediction sub-module uses time series analysis to conduct a trend analysis of educational policy changes and generates an educational policy impact prediction report; Based on the educational policy impact prediction report, the policy effect evaluation sub-module uses regression analysis to generate a policy effect evaluation report; Based on the policy effect evaluation report, the data integration sub-module uses data warehouse and data summarization techniques to generate a comprehensive policy analysis report.

[0041] Based on the optimized resource allocation plan, the policy impact prediction sub-module uses time series analysis techniques to conduct a trend analysis of educational policy changes; this sub-module identifies the potential impacts of educational policies, including changes in resource allocation, student performance, and learning experience; the generated educational policy impact prediction report provides policy decision-makers with expectations of future policy changes.

[0042] The policy effect evaluation sub-module generates a policy effect evaluation report based on the education policy impact prediction report, using regression analysis techniques; this sub-module evaluates the actual impact of the policy, including whether the resource allocation has achieved the expected goals, whether the students' performance has improved, and whether the educational experience has been enhanced; policy decision-makers formulate or adjust policies based on these evaluation results.

[0043] The data integration sub-module generates a comprehensive policy analysis report based on the policy effect evaluation report, using data warehouse and data summarization techniques; this sub-module integrates data and analysis results from various aspects to provide a comprehensive policy analysis report for policy decision-makers; this report includes not only the impact and effect of the policy but also considers the interrelationships of various variables to better understand the overall picture of policy implementation.

[0044] Please refer to Figure 8 , the security management module includes a data encryption sub-module, an access control sub-module, and a security monitoring sub-module; The data encryption sub-module generates encrypted data based on the comprehensive policy analysis report, using encryption algorithms, including symmetric and asymmetric encryption algorithms; The access control sub-module establishes access control rules based on the encrypted data, using access control policies; The security monitoring sub-module generates a security management report based on the access control rules, using intrusion detection systems and abnormal behavior analysis techniques based on network behavior analysis and anomaly detection algorithms.

[0045] The data encryption sub-module uses advanced encryption algorithms, including symmetric and asymmetric encryption algorithms, based on the comprehensive policy analysis report to protect the security of sensitive data; by encrypting the data, it ensures that even if a security vulnerability occurs during data transmission or storage, the confidentiality of the data can be guaranteed; the generated encrypted data can only be decrypted by authorized users or systems, protecting the confidentiality of the data.

[0046] The access control sub-module establishes access control rules based on the encrypted data, using strict access control policies; these rules ensure that only authorized users or systems can access the encrypted data; through access control, the scope of data access is restricted, reducing potential security threats; this helps to maintain the integrity of the data and protect the data from unauthorized access.

[0047] The security monitoring sub-module generates a security management report based on the access control rules, using intrusion detection systems with network behavior analysis and anomaly detection algorithms, as well as abnormal behavior analysis techniques; this sub-module monitors activities in the system, identifies potential security threats and abnormal behaviors; once an anomaly is detected, the system will generate an alarm and take necessary measures to address the threat, while generating a security management report to record all security events.

[0048] Please refer to Figure 9 , the interactive interface module includes an interface design sub-module, a user experience optimization sub-module, and a feedback collection sub-module; Based on the security management report, the interface design sub-module uses information architecture design and interaction design principles to plan the interface layout and create a prototype design to generate a preliminary interface design; Based on the preliminary interface design, the user experience optimization sub-module uses usability testing and interface review methods to evaluate the user experience and make interface adjustments to generate an optimized interface design; Based on the optimized interface design, the feedback collection sub-module uses a user feedback mechanism and data analysis tools to collect user experience data, analyze and process it, and generate a user interface; The information architecture design specifically defines the organization and hierarchical structure of the interface content. The interaction design principles include usability principles, user feedback, and interface consistency. The data analysis tools include web analytics services and sentiment analysis techniques, which are used to quantify and analyze user behavior and feedback.

[0049] Based on the security management report, the interface design sub-module uses information architecture design and interaction design principles; defines the organizational structure and hierarchical layout of the interface content to ensure the orderly presentation of information; plans the interface layout according to user needs and usability principles, and creates a prototype design to form a preliminary interface design.

[0050] Based on the preliminary interface design, the user experience optimization sub-module uses methods such as usability testing and interface review to evaluate the user experience; collects feedback and suggestions from real users by involving them; makes adjustments and improvements to the interface according to the feedback to generate an optimized interface design; this process helps to ensure that the user interface meets user expectations and improves user satisfaction.

[0051] Based on the optimized interface design, the feedback collection sub-module uses a user feedback mechanism and data analysis tools; mainly collects user experience data through user feedback forms, surveys, or other feedback channels; then, uses data analysis tools such as web analytics services and sentiment analysis techniques to quantify and analyze the collected data; this helps system administrators understand user behavior and feedback, and further improve the interface and functions of the system.

[0052] Please refer to Figure 10 , a method for secure sharing of educational resources based on big data. The method for secure sharing of educational resources based on big data is executed based on the above-mentioned system for secure sharing of educational resources based on big data, and includes the following steps: S1: Based on a deep learning model, using data mining techniques, collect students' online learning behaviors, exam scores, interaction feedback, and personal interests in real-time, perform data cleaning and integration, and generate a student dataset; S2: Based on the student dataset, use machine learning algorithms to analyze the learning patterns and identify behavior patterns, and generate a student learning behavior analysis report; S3: Based on the student learning behavior analysis report, use recommendation system algorithms to generate personalized learning paths; S4: Based on the personalized learning paths, use resource optimization algorithms to predict resource requirements and formulate allocation strategies, and generate an optimized resource allocation plan; S5: Based on the optimized resource allocation plan, use statistical analysis methods to analyze the impact of education policies and generate a policy analysis report; S6: Based on the policy analysis report, use data security techniques to conduct data security audits and risk assessments, and generate a security management report.

[0053] Data mining techniques include decision trees, association rule analysis, and principal component analysis. Machine learning algorithms include K-means clustering, support vector machines, and neural networks. Recommendation system algorithms include collaborative filtering and content-based recommendation. Resource optimization algorithms include association rule learning and sequential pattern mining. Statistical analysis methods include time series analysis and regression analysis. Data security techniques include AES encryption and role-based access control.

[0054] This method realizes the comprehensive collection and integration of student data, improves data quality and accuracy, and provides a solid foundation for personalized education; this helps schools better understand students, identify learning problems in advance, and provides strong support for personalized support and education; through learning behavior analysis, educators can better understand students' learning styles and trends, thus better formulating teaching strategies and providing targeted support, improving the quality of education; the generation of personalized learning paths enables students to obtain resources suitable for their learning styles and interests, improving learning efficiency and learning experience, and stimulating learning motivation; resource optimization algorithms ensure the efficient use of educational resources, reduce costs, and make education more sustainable; the policy analysis report helps decision-makers better understand the impact of education policies, provides a scientific basis for policy formulation and adjustment, thus improving the education system and the quality of education; the application of data security techniques ensures the privacy and security of student data, enhancing the compliance and credibility of data management.

[0055] The above are only the preferred embodiments of the present invention, and do not impose other forms of limitation on the present invention. Any person skilled in the relevant art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An educational resource secure sharing system based on big data, characterized in that: The system includes a data collection module, a learning behavior analysis module, a personalized path generation module, a resource optimization allocation module, a policy analysis module, a security management module, and an interactive interface module; Based on a deep learning model, the data collection module uses data mining techniques to collect students' behavior and feedback information, and performs data cleaning and integration to generate a student dataset; Based on the student dataset, the learning behavior analysis module uses clustering algorithms and predictive modeling techniques to analyze learning patterns and identify behavior patterns, generating a student learning behavior analysis report; Based on the student learning behavior analysis report, the personalized path generation module uses collaborative filtering and content recommendation algorithms to design personalized learning paths and conduct fitness evaluations, generating personalized learning paths; Based on the personalized learning path, the resource optimization allocation module uses association rule learning and sequence pattern mining techniques to predict resource requirements and formulate resource allocation strategies, generating an optimized resource allocation plan; Based on the optimized resource allocation plan, the policy analysis module uses time series analysis and regression analysis techniques to predict the impact of education policies and evaluate policy effects, generating a policy analysis report; Based on the policy analysis report, the security management module uses data encryption techniques and access control policies to conduct security audits of data and perform risk assessments, generating a security management report; Based on the security management report, the interactive interface module uses user experience design principles to design and optimize the interface and collect feedback information, generating a user interaction interface; The student dataset includes students' online learning behavior, exam scores, interaction feedback, and personal interests. The student learning behavior analysis report includes learning efficiency, preferred subjects, active periods, and learning difficulties. The policy analysis report includes the impact of policy changes on learning effects, improvements in resource utilization, and feedback from teachers and students. The security management report specifically refers to the security status of data transmission and storage, access permission management, and security event records.

2. The education resource security sharing system based on big data according to claim 1, wherein: The data collection module includes a behavior log sub-module, a grade record sub-module, an interaction data sub-module, and a feedback information sub-module; Based on a deep learning model, the behavior log sub-module uses data crawling techniques to collect students' online learning behavior logs and formats the data to generate formatted behavior logs; Based on the formatted behavior logs, the grade record sub-module uses statistical analysis methods to summarize and analyze students' grade records, generating a comprehensive grade analysis report; Based on the comprehensive grade analysis report, the interaction data sub-module uses interaction analysis techniques to analyze students' interaction data on the online platform, generating an interaction data analysis report; Based on the interaction data analysis report, the feedback information sub-module uses text mining techniques to analyze students' feedback information, generating a comprehensive analysis of students' feedback.

3. The education resource security sharing system based on big data according to claim 2, wherein: The learning behavior analysis module includes a clustering analysis sub-module, a learning preference prediction sub-module, a behavior pattern recognition sub-module, and a grade analysis sub-module; The clustering analysis sub-module conducts a comprehensive analysis based on students' feedback, uses the K-means clustering algorithm to group students' learning behaviors, and generates learning behavior groups. The learning preference prediction sub-module, based on the learning behavior groups, uses the decision tree algorithm to predict students' learning preferences and generates a learning preference prediction report. The behavior pattern recognition sub-module, based on the learning preference prediction report, uses sequence pattern mining technology to identify students' behavior patterns and generates a behavior pattern recognition report. The performance analysis sub-module, based on the behavior pattern recognition report, uses regression analysis technology to analyze the relationship between students' performance and behavior patterns and generates a student learning behavior analysis report.

4. The education resource security sharing system based on big data according to claim 3, wherein: The personalized path generation module includes a collaborative filtering sub-module, a content recommendation sub-module, a path design sub-module, and a fitness evaluation sub-module. The collaborative filtering sub-module, based on the student learning behavior analysis report, uses the collaborative filtering algorithm to analyze the similarity between students, makes personalized resource recommendations, and generates a preliminary personalized resource recommendation list. The content recommendation sub-module, based on the preliminary personalized resource recommendation list, uses the content-based recommendation algorithm to generate an optimized personalized resource recommendation list. The path design sub-module, based on the optimized personalized resource recommendation list, uses the path planning algorithm to design the learning route and progress and generates a personalized learning path plan. The fitness evaluation sub-module, based on the personalized learning path plan, uses the multi-armed bandit algorithm to test the practicality and effectiveness of the path and generates the final personalized learning path.

5. The education resource security sharing system based on big data according to claim 4, characterized in that: The resource optimization allocation module includes a resource demand prediction sub-module, a resource allocation strategy sub-module, and a resource usage efficiency analysis sub-module. The resource demand prediction sub-module, based on the final personalized learning path, uses time series analysis to predict the resource demand in the future time period and generates a resource demand prediction report. The resource allocation strategy sub-module, based on the resource demand prediction report, uses association rule learning to generate a resource allocation strategy report. The resource usage efficiency analysis sub-module, based on the resource allocation strategy report, uses sequence pattern mining to analyze the efficiency and trend of resource usage and generates an optimized resource allocation plan.

6. The education resource secure sharing system based on big data according to claim 5, characterized in that: The policy analysis module includes a policy impact prediction sub-module, a policy effect evaluation sub-module, and a data integration sub-module. The policy impact prediction sub-module, based on the optimized resource allocation plan, uses time series analysis to conduct a trend analysis of changes in education policies and generates an education policy impact prediction report. The policy effect evaluation sub-module, based on the education policy impact prediction report, uses regression analysis to generate a policy effect evaluation report. The data integration sub-module, based on the policy effect evaluation report, uses data warehouse and data aggregation technologies to generate a comprehensive policy analysis report.

7. The education resource secure sharing system based on big data according to claim 6, characterized in that: The security management module includes a data encryption sub-module, an access control sub-module, and a security monitoring sub-module. The data encryption sub-module, based on the comprehensive policy analysis report, uses encryption algorithms, including symmetric and asymmetric encryption algorithms, to generate encrypted data. The access control sub-module, based on the encrypted data, uses access control policies to establish access control rules. The security monitoring sub-module generates a security management report based on access control rules, using an intrusion detection system and abnormal behavior analysis technology based on network behavior analysis and abnormal detection algorithms.

8. The education resource secure sharing system based on big data according to claim 7, characterized in that: The interaction interface module includes an interface design sub-module, a user experience optimization sub-module, and a feedback collection sub-module; Based on the security management report, the interface design sub-module uses information architecture design and interaction design principles to plan the interface layout and perform prototype design, generating a preliminary interface design; Based on the preliminary interface design, the user experience optimization sub-module uses usability testing and interface review methods to evaluate the user experience and perform interface adjustments, generating an optimized interface design; Based on the optimized interface design, the feedback collection sub-module uses a user feedback mechanism and data analysis tools to collect user experience data, analyze and process it, and generate a user interface; The information architecture design specifically defines the organization and hierarchical structure of interface content. The interaction design principles include usability principles, user feedback, and interface consistency. The data analysis tools include web analytics services and sentiment analysis techniques for quantifying and analyzing user behavior and feedback.

9. An educational resource security sharing method based on big data, characterized in that, The execution of the big data-based educational resource security sharing system according to any one of claims 1-8 includes the following steps: Based on a deep learning model, using data mining techniques, real-time collect students' online learning behaviors, exam scores, interaction feedback, and personal interests, perform data cleaning and integration, and generate a student dataset; Based on the student dataset, use machine learning algorithms to analyze the learning pattern and identify behavior patterns, generating a student learning behavior analysis report; Based on the student learning behavior analysis report, use a recommendation system algorithm to generate a personalized learning path; Based on the personalized learning path, use a resource optimization algorithm to predict resource requirements and formulate allocation strategies, generating an optimized resource allocation plan; Based on the optimized resource allocation plan, use statistical analysis methods to analyze the impact of education policies and generate a policy analysis report; Based on the policy analysis report, use data security techniques to perform data security audits and risk assessments, generating a security management report.

10. The method for secure sharing of educational resources based on big data according to claim 9, characterized in that: The data mining techniques include decision trees, association rule analysis, and principal component analysis. The machine learning algorithms include K-means clustering, support vector machines, and neural networks. The recommendation system algorithms include collaborative filtering and content-based recommendation. The resource optimization algorithms include association rule learning and sequential pattern mining. The statistical analysis methods include time series analysis and regression analysis. The data security techniques include AES encryption and role-based access control.

Images