Abstract—Technology changes with the times. It is difficult to predict, as technology develops under the influence of several factors. We analyze the technology by carrying out the patent from a time series perspective. The study consists of two phases. In the first phase, time series models detect the trend, cycle, and seasonality of the technology. Next phase performs to predict the importance of term. In order to confirm the practical applicability of the proposed method, 2,268 industrial robot patents were collected and tested. As a result, it was found that technologies beyond the dual control based on carbon materials among industrial robots will continue to develop.
 

Index Terms—robot, patent analysis, time series, predictive modeling

Cite: Juhyun Lee, Junseok Lee, Jiho Kang, Sangsung Park, and Dongsik Jang, "Prediction of Robot Technology Using Multi-phase Model," Journal of Advances in Information Technology, Vol. 11, No. 3, pp. 181-185, August 2020. doi: 10.12720/jait.11.3.181-185

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.