Measuring Similarity System and Method of Android Application Using Text Mining

摘要

The present invention relates to a technique of extracting a busmark from a Dalvik Executable of an Android application and measuring similarity between applications using TF-IDF. The feature extracting unit extracts a bus mark, extracts a contrast term from the original application file, and counts the number of times the contrast term is included in the bus mark of the original application file and the bus mark of the contrast application file. And a similarity calculator for projecting onto a vector space to calculate the similarity between the original application file and the control application file.