数字式图书馆海量文献数据查询优化仿真  

Digital Library Mass Document Data Query Optimization Simulation

作　　者：谢燕[1] XIE Yan(Baoji University of Arts and Sciences,Shanxi Baoji 721013,China)

机构地区：[1]宝鸡文理学院

出　　处：《计算机仿真》2019年第6期426-429,共4页Computer Simulation

摘　　要：探究有效的海量文献数据查询优化方法,能够提高数据查询的运行速度,加快响应时间,增强查全率,在使用过程中具有重要的现实意义。为了解决查询海量数据时存在响应时间较长、运行速度较慢、准确率较低等问题,提出基于改进遗传算法的数据查询优化方法,利用稀疏表示哈希算法构建海量文献数据模型,获取抽象空间中文献和文本信息的特征表示,计算二者隐藏在语义空间的相关近似值,得到海量文献数据目标函数。运用梯度将目标函数转换成新的适应度函数,利用函数值变化机率优化适应度函数,将十进制实数编码加入遗传算法中,根据概率选取染色体具有最小函数值时,由该值获取最优查询结果。仿真结果证明,所提方法在保证较短的平均响应时间和平均查询速度的基础上,提高查询的平均准确率和查全率。The effective optimization method of massive literature data query can improve the speed of data query,accelerate response time and enhance recall rate.Therefore,this method has practical significance.In order to solve the problem about the long response time,slow running speed and low accuracy in querying massive data,this paper puts forward a method to optimize data query based on improved genetic algorithm.Firstly,the sparse representation hashing algorithm was used to construct the model of massive literature data and obtain characteristic representation of literature and text information in abstract space.Secondly,the correlation approximate values of the two hidden in the semantic space were calculated and the objective function of massive literature data was obtained.Moreover,the gradient was used to transform objective function into new fitness function.Meanwhile,the change probability of function was used to optimize the fitness function.Then,decimal real-number coding was added into the genetic algorithm.According to the probability,when the chosen chromosome had the minimum function value,the optimal query result could be obtained.Simulation results show that the proposed method can improve the average accuracy rate and recall rate of query based on the short average response time and average query speed.

关 键 词：文献数据 查询优化 查询速度 平均准确率 查全率 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]