In this paper we study the personalized book recommender system in a child-robot interactive environment. Firstly, we propose a novel text search algorithm using an inverse filtering mechanism that improves the efficiency. Secondly, we propose a user interest prediction method based on the Bayesian network and a novel feedback mechanism. According to children's fuzzy language input, the proposed method gives the predicted interests. Thirdly, the domain specific synonym association is proposed based on word vectorization, in order to improve the understanding of user intention. Experimental results show that the proposed recommender system has an improved performance and it can operate on embedded consumer devices with limited computational resources.

翻译：本文研究了儿童与机器人交互环境中的个性化图书推荐系统。首先，我们提出一种基于逆滤波机制的新型文本搜索算法，有效提升了搜索效率。其次，提出基于贝叶斯网络和新型反馈机制的用户兴趣预测方法，能够根据儿童模糊的语言输入给出预测兴趣。第三，基于词向量化技术提出领域特定同义词关联方法，以增强对用户意图的理解。实验结果表明，所提出的推荐系统性能得到提升，且能够在计算资源有限的嵌入式消费设备上运行。