Abstract—Nowadays, many enterprises have considered
cloud computing as a seminal technology, and have exploited
various types of service models to respond to different customer
needs. Patent analysis is an essential ability of survival and
development for high technology enterprises. It takes a huge
number of patents to support the generation of a business
service model of cloud computing. Patent engineers usually fail
to collect and analyze patents efficiently due to their large
number of professional glossaries and unknown patent
classification. This study uses patents in lawsuit as partial
important components of pearl patents and proposes a
compound retrieval strategy to completely collect the patents of
cloud computing. By using text mining as a tool for data
processing and keywords extraction, we adopt the technique for
order preference by similarity to ideal solution (TOPSIS) to
pick out features with high degree of distinguishability for
classification. These results establish an important foundation
for developing a patent classification system in the future.
Index Terms—Cloud computing, text mining, Feature
selection, TOPSIS.
J. Y. Huang is with the Department of Information Management, National
Chin-Yi University of Technology, No.57, Sec. 2, Zhongshan Rd., Taiping
Dist., Taichung City 41170, Taiwan (e-mail: jygiant@ncut.edu.tw).
[PDF]
Cite: Jia-Yen Huang, " Feature Selection for Cloud Computing Patents Classification," International Journal of Social Science and Humanity vol. 6, no. 7, pp. 541-546, 2016.