With the advent of the big data era, edge cloud computing has developed rapidly. In this era of popular digital music, various technologies have brought great convenience to online music education. But vast databases of digital music prevent educators from making specific-purpose choices. Music recommendation will be a potential development direction for online music education. In this paper, we propose a deep learning model based on multi-source information fusion for music recommendation under the scenario of edge-cloud computing. First, we use the music latent factor vector obtained by the Weighted Matrix Factorization (WMF) algorithm as the ground truth. Second, we build a neural network model to fuse multiple sources of music information, including music spectrum extracted from extra music information to predict the latent spatial features of music. Finally, we predict the user’s preference for music through the inner product of the user vector and the music vector for recommendation. Experimental results on public datasets and real music data collected by edge devices demonstrate the effectiveness of the proposed method in music recommendation.

中文翻译：

---

面向边缘云计算的神经网络驱动的大规模在线音乐教育机制

随着大数据时代的到来，边缘云计算快速发展。在这个数字音乐盛行的时代，各种技术给在线音乐教育带来了极大的便利。但庞大的数字音乐数据库使教育工作者无法做出特定目的的选择。音乐推荐将是在线音乐教育潜在的发展方向。本文提出了一种基于多源信息融合的边缘云计算场景下的音乐推荐深度学习模型。首先，我们使用加权矩阵分解（WMF）算法获得的音乐潜在因子向量作为基本事实。其次，我们构建了一个神经网络模型来融合多个音乐信息源，包括从额外音乐信息中提取的音乐频谱，以预测音乐的潜在空间特征。最后，我们通过用户向量和推荐音乐向量的内积来预测用户对音乐的偏好。在公共数据集和边缘设备收集的真实音乐数据上的实验结果证明了该方法在音乐推荐方面的有效性。