基于相似学习者发现的资源推荐系统

为了解决给规模大、分布广的远程学习者提供个性化的学习资源推荐的这一难点问题,提出了一种新颖的基于多代理的远程协作学习资源推荐机制,引入学习状态评估向量对复杂的学习行为进行建模,并基于组代理之间的交互来发现具有相似学习状态的学习者,同时构建了一个供社区学习者共享的即时交互和学习资源推荐平台,为社区学习者的学习资源共享提供了有针对性的推荐.实验证明,具有较高的相似学生发现准确率和社区构建效率,同时通过社区学生的资源推荐和共享,提高了学习者的学习效率和成绩.

Resource recommendation system based on similar learners exploitation

A novel E-learning resource collaborative recommendation mechanism based on multi-agent was proposed to solve the big challenge to provide personalized learning resource to large-scale and distributed E-learners.A learning status evaluation vector was introduced to model the E-learners' behaviors, and help to find and reorganize the learners' share of similar learning status into smaller communities based on the interaction between group agents.Furthermore a collaborative communication and learning resource recommendation platform was developed to enable the learner to share personalized recommended resources.Experimental results showed that this algorithm has higher discovery accuracy of similar E-learner and construction efficiency of community.Based on the learning resource recommendation and sharing among E-learners in the common community,this system is proved to enhance the learning effect and scores.