Design And Implementation Of System Based On Multi-Knowledge Extraction

Rough set theory has been used as a data analysis tool in many fields. Multi-knowledge extraction based on rough sets had attracted widespread interest. It needs to develop system based on multi-knowledge extraction, to improve the transparency of the complex theory of multi-knowledge, to find the hidden knowledge from data-driven systems.Based on the research of domestic and foreign related knowledge extraction systems, this paper designs a multi-knowledge extraction system, and implements the mini system. System can provide a series of functions such as data preprocessing, attribute reduction and rule obtaining to users. Compared with other knowledge extraction systems, users can get multiple reductions, not single reduction in other systems. Firstly, According to the process and methods of software development, this paper plans the whole flow of the system and determines the algorithms which are adopted in the stage of data preprocessing and data process. Then, this paper analyzes the functional requirement of the system, meantime descries the data flow diagram and organization chart of system. Also, this paper analyzes the modules of login, rights management, data preprocessing, attribute reduction and rule obtaining, and completes the detailed design and database design for our system. Finally, based on the design of the multi-knowledge extraction system, this paper completes the implementation and system test. According to the different needs of system, this paper implements different functions by flexible ways to solve the transparency of the complex theory of multi-knowledge, which has provided more complete functions for users to obtain multi-knowledge from data effectively.