基于深度学习的智能语音问答系统  

Intelligent Voice Question Question and Answer System Based on Deep Learning

作　　者：张凯亮 陈云 ZHANG Kailiang;CHEN Yun(School of Information Engineering,Xuzhou University of Technology,Xuzhou Jiangsu 221018,China)

机构地区：[1]徐州工程学院信息工程学院,江苏徐州221018

出　　处：《信息与电脑》2022年第7期104-107,共4页Information & Computer

摘　　要：针对传统智能问答系统存在的问题,笔者基于深度学习算法建立一个智能语音问答系统。首先,利用基于神经网络的词向量表示法建立对话生成模型,引入循环神经网络(Recurrent Neural Network,RNN)解决序列之间的映射问题;其次,选用引入Attention注意力机制的Seq2seq神经网络模型进行试验,通过构建的模型将输入转换成计算机能理解的二进制编码;最后,进行系统测试。测试结果表明,该问答系统的鲁棒性较好,可提供日常健康方面的智能问答,终端用户体验良好。Aiming at the problems existing in the traditional intelligent question answering system, the author establishes an intelligent voice question answering system based on Deep Learning algorithm. Firstly, the word vector representation based on neural network is used to establish the dialogue generation model, and the RNN is introduced to solve the mapping problem between sequences;Secondly, the Seq2seq neural network model with Attention mechanism is selected for experiment, and the input is transformed into binary code that can be understood by computer through the constructed model;Finally, the system is tested. The test results show that the Q & a system has good robustness, can provide intelligent Q & A in daily health, and has a good enduser experience.

关 键 词：Seq2seq 深度学习 智能语音 

分 类 号：TN912.3[电子电信—通信与信息系统]