Information-Centric Networking (ICN) uses content name to replace traditional IP address where data becomes independent from location, application, storage, and means of transportation. Due to the complex structure and variable length of content names, designing efficient content name lookup algorithms becomes a new challenge. In this paper, we propose an efficient name lookup structure for ICN, called Learned Bloom-Filter Lookup, which combines Recurrent Neural Networks (RNN) with standard Bloom filter to improve lookup efficiency. In our scheme, RNN trains the element set and non-element set, which are used to obtain the pre-filtering of names. Moreover, we look up the contents by using the backup Bloom filter to reduce the false negatives generated by the learned model. In addition, we evaluate the performance of the proposed algorithm using experimental simulations. Compared with the Bloom-Hash and NameFilter methods, the results show that our method can reduce the false positive rate and improve the accuracy of the search. Furthermore, the memory required by our method is less than the Bloom-Hash and NameFilter methods.

以信息为中心的网络（ICN）使用内容名称来代替传统的IP地址，因为数据变得不受位置，应用程序，存储和运输方式的约束。由于内容名称的复杂结构和可变长度，设计有效的内容名称查找算法成为新的挑战。在本文中，我们为ICN提出了一种有效的名称查找结构，称为“学习型布隆过滤器查找”，该结构将递归神经网络（RNN）与标准布隆过滤器相结合以提高查找效率。在我们的方案中，RNN训练元素集和非元素集，用于获得名称的预过滤。此外，我们通过使用备用布隆过滤器来查找内容，以减少由学习模型生成的误报。此外，我们使用实验仿真来评估所提出算法的性能。与Bloom-Hash和NameFilter方法相比，结果表明我们的方法可以减少误报率并提高搜索的准确性。此外，我们的方法所需的内存少于Bloom-Hash和NameFilter方法。