Technology Forecasting Based on Topic Identification of Online Innovation Communities and S-Curve

Abstract

[Purpose/Significance] It is very important for enterprises, industries and countries to carry out technology prediction from a meso-perspective, so it is necessary to establish a set of suitable methods. [Method/Process] Applying text mining and detection of patent citation network, this study built subject clustering based on biggest fragmenting to detect innovation communities and with s-curve to forecast technology development of innovation communities. [Results/Conclusions] The empirical research on hybrid rice breeding innovation field shows that the proposed method not only enriches the theory and method of technology prediction, but also gives the relevant innovation institutions and national level strategic suggestions from the meso-perspective.