基于改进Apriori的数字化图书信息模糊检索研究  

Research on Fuzzy Retrieval of Digital Library Information Based on Improved Association Rules

作　　者：耿洪旭[1] GENG Hong-xu(Hainan Provincial Library,Haikou 570203 China)

机构地区：[1]海南省图书馆,海南海口570203

出　　处：《自动化技术与应用》2024年第12期130-134,共5页Techniques of Automation and Applications

基　　金：海南省哲学社会科学项目(HNSK[YB]18-108)。

摘　　要：为了提高数字化图书馆中信息模糊检索的效率,基于改进Apriori算法,提出数字化图书信息模糊检索方法。首先采用矩阵向量和完全连接算法对关联规则中的Apriori算法进行优化,通过减少运算过程中的连接次数和构建事务项的向量矩阵来减少运算步骤。然后再将优化后的Apriori算法应用于模糊检索过程中,以提高检索的精度。实验结果表明,改进Apriori算法在模糊检索中可以达到99.1%的词组搜索覆盖率,并且稳定响应时间为3 ms,最终可以实现91.5%的检索精准度。采用研究提出的改进Apriori算法构建的数字化图书馆信息模糊检索功能具有较高的运算效率和检索准确率。In order to improve the efficiency of information fuzzy retrieval in digital libraries,this study first optimizes the Apriori algorithm in association rules using matrix vectors and fully connected algorithms.By reducing the number of connections in the operation process and constructing a vector matrix of transaction items,the calculation steps are reduced.Then,the optimized Apriori algorithm is applied to the fuzzy retrieval process to improve the accuracy of the retrieval.The experimental results show that the improved Apriori algorithm can achieve a phrase search coverage of 99.1%in fuzzy retrieval,with a stable response time of 3ms,and ultimately achieve a retrieval accuracy of 91.5%.In summary,the digital library information fuzzy retrieval function constructed using the improved Apriori algorithm proposed in the study has high computational efficiency and retrieval accuracy.

关 键 词：APRIORI算法 关联规则 数字化 模糊检索 完全连接 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]