摘要
信息检索的目标在于帮助用户准确而高效地检索得到相关信息。传统的方法不能精确识别用户要求的信息。将粗糙集理论应用于信息检索,利用能处理不精确和不完备信息方面的优势,把用户查询与数据库中对象间相关程度划分为若干等级标准,并定义相关贴近度函数,提出了一种扩充和优化用户查询的新方法,并给出其算法实现。新方法隐含了布尔逻辑,可实现索引词加权,具备将检索命中文档排序的能力,帮助用户实现对检索信息的准确定位。最后通过仿真实例验证了改进方法的可行性和有效性。
The target of information retrieval is to help users find desired information effectively and efficiently.This paper applys rough set to information retrieval,takes the advantages of rough set theory to deal with vague or uncertain data set,divides the user queries and the inter-related degree of data objects into some levels,and defines the similarity function,proposes and designs a new method to expand and optimize the user query.Its advantages include the implicit inclusion of Boolean logic,term weighting,and the ability to rank retrieved documents.Finally,this paper designs the retrieval algorithm based on rough set,and prove its validity and feasibility by using an instance.
出处
《计算机仿真》
CSCD
北大核心
2010年第10期361-365,共5页
Computer Simulation
基金
河南省国际合作项目(084300510050)
关键词
粗糙集
信息检索
匹配等级
贴近度
Rough set
Information retrieval
Matching level
Similarity
