To accelerate searching an enjoyable holiday resort from massive-scale tourism spots on social media, the TR-DNNMF tourism spots recommendation system combining neural network and matrix decomposition is developed in this work. The model is built upon the architecture of the neural collaborative filtering model. It leverages the generalized matrix decomposition model coupled with the multi-layer neural network model as the pre-training model for training. Subsequently, it integrates the two models to anticipate user’s rating of tourism spots and further recommends the suitable tourism spots. Our model combines the linearity of matrix factorization and the nonlinearity of deep neural network to uncover the potential features of user-scenic spots. This makes the model exhibit high scalability and strong fitting ability. Experiments are conducted based on the domestic tourist attractions from user interaction data. Features that is non-descriptive to the model are discarded to reduce the time and memory consumption. Conclusively, our designed system can offer satisfactory prediction, as evidenced by the competitive accuracies on six experimental data sets.

为了加快在社交媒体上从大规模旅游景点中搜索令人愉快的度假胜地，本文开发了结合神经网络和矩阵分解的 TR-DNNMF 旅游景点推荐系统。该模型建立在神经协同过滤模型的架构之上。它利用广义矩阵分解模型加上多层神经网络模型作为预训练模型进行训练。随后，将两种模型相结合，预测用户对旅游景点的评价，进一步推荐合适的旅游景点。我们的模型结合了矩阵分解的线性和深度神经网络的非线性来揭示用户场景的潜在特征。这使得该模型具有很高的可扩展性和很强的拟合能力。基于用户交互数据中的国内旅游景点进行实验。对模型非描述性的特征被丢弃以减少时间和内存消耗。总而言之，我们设计的系统可以提供令人满意的预测，六个实验数据集的竞争准确性证明了这一点。