为解决传统推荐存在精准性差的问题，构建了一个融合K-最近邻算法（K-nearest neighbor，KNN）、图神经网络（graph neural network，GNN）和深度宽度（Wide&Deep）网络的推荐模型。融入KNN分类方法对数据进行噪声过滤，以提高数据质量；利用GNN提取用户会话图的节点嵌入表示，基于注意力机制加权用户全局特征以捕获用户短期兴趣；调用Wide&Deep以解决稀疏数据时的模型过度泛化问题。为了验证模型的有效性，分别在MovieLens-1M、Bing-News、Book-Crossing数据集与6种传统推荐方法进行对比实验，结果表明所提模型的各项评价指标更佳。为了进一步验证该模型在实际应用领域中的可行性，面向农业领域搭建了农业一体管理App化肥推荐系统，得到推荐结果的准确率为0.721，曲线下面积为0.784，满足了预期的应用需求。
In order to solve the problem of poor accuracy in traditional recommendation, a multi-layer K-nearest neighbor (KNN) network recommend model KNN-GWD, in combination of graph neural network (GNN) and wide & deep network was constructed. In the model, the KNN classification method is for data noise filtering to improve data quality. GNN is used to extract the node embedding representation of user's conversation graphs, and capture user's short-term interest by weighting user's global characteristics based on attention mechanism. Wide&Deep is used to solve the problem of model overgeneralization in the case of sparse data. In order to verify the effectiveness of the model, comparative experiments were carried out on MovieLens-1M, Bing-News and Book-Crossing data sets with this model and six other traditional recommendation methods. Experimental results show that the evaluation indicators of this model are better. In order to further verify the feasibility of the proposed model in the actual application field, an agricultural integrated management App fertilizer recommendation system was built with the accuracy of recommended results of 0.721 and the area under curve of 0.784, which met the expected application requirements.
[1] Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[J]. ArXiv Preprint ArXiv:1310.4546, 2013. (2013-10-16)[2021-06-15]. https://arxiv.org/abs/1310.4546vl.
[2] Grbovic M, Djuric N, Radosavljevic V, et al. Scalable semantic matching of queries to ads in sponsored search advertising[C]//Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2016:375-384.
[3] Grbovic M, Radosavljevic V, Djuric N, et al. E-commerce in your inbox:product recommendations at scale[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015:1809-1818.
[4] Covington P, Adams J, Sargin E. Deep neural networks for Youtube recommendations[C]//Proceedings of the 10th ACM Conference on Recommender Systems, 2016:191-198.
[5] Wu S, Tang Y Y, Zhu Y Q, et al. Session-based recommendation with graph neural networks[C]//Proceedings of AAAI Conference on Artificial Intelligence, 2019, 33(1):346-353.
[6] Guo H F, Tang R M, Ye Y M, et al. DeepFM:a factorization-machine based neural network for CTR prediction[J]. ArXiv Preprint ArXiv:1703.04247, 2017. (2017-05-13)[2021-06-15]. https://arxiv.org/abs/1703.04247.
[7] Cheng H, Koc L, Harmsen J, et al. Wide&deep learning for recommender systems[C]//Conference on Recommender Systems, 2016:7-10.
[8] Wang R X, Fu B, Fu G, et al. Deep & cross network for ad click predictions[M]//Proceedings of the ADKDD'17, 2017:1-7.
[9] Liu B, Tang R M, Chen Y Z, et al. Feature generation by convolutional neural network for click-through rate prediction[C]//The World Wide Web Conference, 2019:1119-1129.
[10] Liu Y D, Ge K K, Zhang X, et al. Real-time attention based look-alike model for recommender system[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019:2765-2773.
[11] Huang T W, Zhang Z Q, Zhang J L. FiBiNET:combining feature importance and bilinear feature interaction for click-through rate prediction[C]//Proceedings of the 13th ACM Conference on Recommender Systems, 2019:169-177.
[12] Tang H Y, Liu J N, Zhao M, et al. Progressive layered extraction (PLE):a novel multi-task learning (MTL) model for personalized recommendations[C]//Proceedings of the 14th ACM Conference on Recommender Systems, 2020:269-278.
[13] Chen Q W, Zhao H, Li W, et al. Behavior sequence transformer for E-commerce recommendation in Alibaba[C]//Proceedings of the 1st International Workshop on Deep Learning Practice for High-Dimensional Sparse Data, 2019:1-4.
[14] 陆凯, 徐华. 基于最近邻距离权重的ML-KNN算法[J]. 计算机应用研究, 2020, 37(4):982-985. Lu K, Xu H. ML-KNN algorithm based on nearest neighbor distance weight[J]. Application Research of Computers, 2020, 37(4):982-985. (in Chinese)
