一种智能化跨学科教育资源整合及推荐系统

• Format: Patent
• Language: Chinese
• Published: 20.12.2024
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

本发明属于学习推荐技术领域，具体是指一种智能化跨学科教育资源整合及推荐系统，包括资源整合模块、资源推荐模块和反馈信息模块；采用聚合过滤方法将涉及同一知识点的搜索结果进行聚合和过滤，能够提取学科教育资源的关键内容；通过图同构网络将学科教育资源表示为图结构，提取图同构网络中每个节点和边的邻域特征，并通过图卷积层和扰动对抗函数进行聚合和转换，能够深入挖掘知识点的潜在特征和关系，为推荐的教育资源提供准确有效的依据；收集学生的学习进展和反馈信息，对图卷积层和扰动对抗函数进行优化，提高了推荐列表的及时性和适应性。 The invention belongs to the technical field of learning recommendation, and particularly relates to an intelligent interdisciplinary education resource integration and recommendation system which comprises a resource integration module, a resource recommendation module and a feedback information module. Searching results related to the same knowledge point are aggregated and filtered by adopting an aggregation filtering method, and key contents of subject education resources can be extracted; according to the method, subject education resources are expressed as a graph structure through a graph isomorphic network, neighborhood features of each node and edge in the graph isomorphic network are extracted, aggregation and conversion are carried out through a gra