数字化图书档案海量数据快速提取仿真研究
|
摘要
对数字化图书档案海量数据进行快速提取能够提高图书档案数据的利用效率。针对当前数字化图书档案海量数据提取方法存在的提取速度慢,且数据提取质量较差的问题,提出一种基于BP神经网络的数字化图书档案海量数据快速提取方法,利用范围型海量数据属性的值域特征,将数字化图书档案数据的分布样本划分为多个子区间,实现数据分类,并通过构建神经元模型,根据隐含层和输出层的数据输出,确定输出的误差项,调整BP神经网络各层权重,构建基于BP神经网络的数字化图书档案海量数据快速提取模型,实现数字化图书档案海量数据快速提取。实验结果表明,所提方法对数字化图书档案海量数据提取的速度较快,且提取的效率较高,用户对提取结果的满意度较高。
At present, the rapid extraction of massive data in digital book archives can increase the utilization efficiency of data, but the extraction speed is slow and data extraction quality is low. Therefore, this article focuses on a method for rapidly extracting massive data in digital book archives based on BP neural network. Firstly, the domain features range-type massive data attributes were used to divide the distribution sample of digital book archive data into many subintervals and thus to realize the data classification. Meanwhile, the neuron model was built. According to the data output at the hidden layer and the output layer, the term of output error was determined and the weight of each layer in BP neural network was adjusted. Finally, the model of rapid extraction for massive data in digital book archives based on BP neural network was built. Thus, we achieved the rapid extraction for massive data in digital book archives. Simulation results verify that the proposed method can fast extract massive data in digital book archives. Meanwhile, the extraction efficiency is high and the degree of satisfaction for the extraction results is high.
At present, the rapid extraction of massive data in digital book archives can increase the utilization efficiency of data, but the extraction speed is slow and data extraction quality is low. Therefore, this article focuses on a method for rapidly extracting massive data in digital book archives based on BP neural network. Firstly, the domain features range-type massive data attributes were used to divide the distribution sample of digital book archive data into many subintervals and thus to realize the data classification. Meanwhile, the neuron model was built. According to the data output at the hidden layer and the output layer, the term of output error was determined and the weight of each layer in BP neural network was adjusted. Finally, the model of rapid extraction for massive data in digital book archives based on BP neural network was built. Thus, we achieved the rapid extraction for massive data in digital book archives. Simulation results verify that the proposed method can fast extract massive data in digital book archives. Meanwhile, the extraction efficiency is high and the degree of satisfaction for the extraction results is high.
引文
[1] 朱龙元,杨智翔. 基于三维激光扫描的滑坡信息提取方法研究[J]. 人民长江, 2016,47(17):53-55.
[2] 梁涵卿,等. 输电线路不对称短路故障关键暂态信息获取方法[J]. 电网技术, 2017,41(8):2702-2708.
[3] 韩文霆,等. 基于无人机遥感技术的玉米种植信息提取方法研究[J]. 农业机械学报, 2017,48(1):139-147.
[4] 刘杰,刘文吉,刘灿波. 船舶轴系设计规范中曲线类图形的反向数据获取方法[J]. 船海工程, 2017,46(4):140-143.
[5] 孔宪光,等. 面向复杂工业大数据的实时特征提取方法[J]. 西安电子科技大学学报(自然科学版), 2016,43(5):70-74.
[6] 樊延平,郭齐胜,柏杰. 面向过程的装备需求论证信息资源获取方法[J]. 计算机工程与设计, 2016,37(4):1085-1090.
[7] 王升翔,等. 基于分层树模型的中文网页主题时间提取方法[J]. 计算机应用, 2017,37(s1):270-272.
[8] 佟瑞鹏,等. 基于深度学习的施工安全泛场景数据获取方法[J]. 中国安全科学学报, 2017,27(5):1-6.
[9] 刘尚懿. 动态摄像机图像传输信息优化提取仿真研究[J]. 计算机仿真, 2017,34(10): 213-216.
[10] 苑广辉,等. 黄土高原复杂地形上高质量湍流通量数据获取方法[J]. 地球物理学报, 2016,59(6):1971-1982.
[2] 梁涵卿,等. 输电线路不对称短路故障关键暂态信息获取方法[J]. 电网技术, 2017,41(8):2702-2708.
[3] 韩文霆,等. 基于无人机遥感技术的玉米种植信息提取方法研究[J]. 农业机械学报, 2017,48(1):139-147.
[4] 刘杰,刘文吉,刘灿波. 船舶轴系设计规范中曲线类图形的反向数据获取方法[J]. 船海工程, 2017,46(4):140-143.
[5] 孔宪光,等. 面向复杂工业大数据的实时特征提取方法[J]. 西安电子科技大学学报(自然科学版), 2016,43(5):70-74.
[6] 樊延平,郭齐胜,柏杰. 面向过程的装备需求论证信息资源获取方法[J]. 计算机工程与设计, 2016,37(4):1085-1090.
[7] 王升翔,等. 基于分层树模型的中文网页主题时间提取方法[J]. 计算机应用, 2017,37(s1):270-272.
[8] 佟瑞鹏,等. 基于深度学习的施工安全泛场景数据获取方法[J]. 中国安全科学学报, 2017,27(5):1-6.
[9] 刘尚懿. 动态摄像机图像传输信息优化提取仿真研究[J]. 计算机仿真, 2017,34(10): 213-216.
[10] 苑广辉,等. 黄土高原复杂地形上高质量湍流通量数据获取方法[J]. 地球物理学报, 2016,59(6):1971-1982.