【摘要】 针对医疗数据多样性导致推荐过程存在干扰,易产生较大推荐歧义,且使用简单学习过程无法区分数据,导致推荐结果不佳的问题,提出面向医疗系统的多样性数据深层神经网络推荐算法.首先,设计了医疗推荐系统框架,对多样性医疗数据进行预处理.然后,引入设计的深层神经网络模型,并对该模型进行训练.最后,将预处理完成的医疗数据输入深层神经网络模型进行深度处理,输出推荐函数,完成数据推荐,解决学习中的歧义性.试验结果表明,所提算法的数据预处理效果较好,改进后的深层神经网络模型能够产生更多的激活函数,且所提算法的数据推荐准确率高达89%,精度较高,优于其他模型,利用所提算法改进后的医疗系统学习性能较好,能够为医疗领域的信息化发展提供参考依据.更多还原

【Abstract】 In view of the problem that the recommendation process is disturbed by the diversity of medical data, it is easy to produce a large recommendation ambiguity, and the data cannot be distinguished by using the simple learning process, which results in poor recommendation results, a deep neural network recommendation algorithm for diversity data for medical system is presented. First of all, the framework of the medical recommendation system is designed to preprocess the diversity medical data. And then, the designed deep neural network model is introduced and trained. Finally, the preprocessed medical data is input into the deep neural network model for advanced processing, the recommendation function is output, the data recommendation is completed, and the ambiguity in learning is solved. The experimental results show that the data preprocessing effect of the proposed algorithm is good, and the improved deep neural network model can produce more activation functions, the data recommendation accuracy of the proposed algorithm is as high as 89%, the precision is high, which is superior to other models, indicating that the improved medical system has better learning performance and can provide a reference for the development of information technology in the medical field.更多还原