摘要
提出了一种并行模式下挖掘大量声音档案数据的模型.该模型通过将串行模型与解析映射和聚合算子相结合,实现了并行分布式分析方法.仿真结果表明,随着进程池数量增加,系统运行效率逐渐提高.
A model of mining a large number of voice file data in parallel mode is proposed.By combining the serial model with analytic mapping and aggregation operator,the parallel distributed analysis method is realized.The simulation results show that with the increase of the number of process pools,the efficiency of the system is gradually improved.
作者
鲜娅静
XIAN Ya-jing(Xi′an Medical University,Xi′an 710021,China)
出处
《云南师范大学学报（自然科学版）》
2022年第1期42-45,共4页
Journal of Yunnan Normal University:Natural Sciences Edition
基金
陕西省教育厅专项基金资助项目(17DL0079)。
关键词
声音档案
数据挖掘
分布式
并行计算
Voice archives
Data mining
Distributed
Parallel computing
