Text content analysis using semantic similarity and keyword extraction for automatic file name generation

Tremendous growth in internet technology has created a new platform which helps the users to download and store huge quantity of information. This situation has created a problem for the users, if they are searching for particular information or content from these files, it is very difficult for them to get and this process has become tedious and time consuming one. The main aim of this paper is to develop a new tool which provides the appropriate, meaningful and accurate file names automatically, after verifying and analysing the content. There are three important steps are carried out in this research work; in the first step, classification is performed based on file names, to find whether the file name is meaningful or meaningless. To do this task, the file names are compared using a proposed character numeric other (CNO) algorithm. During the second step, it classifies only the meaningless filenames by using the proposed search techniques. In the third step, it performs the keyword extraction and title extraction. In this step, there are two new algorithms keyword extraction (KWE) algorithm and automatic file name generator (AFNG) algorithms are proposed to generate the new file names automatically, from this, most appropriate file name is selected by the users.