Identification of promising inventions considering the quality of knowledge accumulation: a machine learning approach
- PDF / 752,821 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 59 Downloads / 178 Views
Identification of promising inventions considering the quality of knowledge accumulation: a machine learning approach Uijun Kwon1 · Youngjung Geum1 Received: 15 November 2018 / Accepted: 3 September 2020 © Akadémiai Kiadó, Budapest, Hungary 2020
Abstract The identification of promising inventions is an important task in technology planning practice. Although several studies have been carried out using patent-based machine learning techniques, none of these have used the quality of knowledge accumulation as an input for identifying promising inventions, and have simply considered the number of backward citations as the link with previous knowledge. The current study therefore aims to fill this research gap by predicting promising inventions with patent-based machine learning, using the quality of knowledge accumulation as an important input variable. Eight criteria and 17 patent indicators are used as input variables, and patent forward citations are employed as the output variable. Six machine learning techniques are tested on 363,620 G06F patents filed between January 1990 and December 2009, and the results show that the quality of knowledge accumulation is the most important variable in predicting emerging inventions. Keywords Promising technology · Technology forecasting · Patent analysis · Machine learning · Patent indicator
Introduction Technology has formed a central part of modern innovation, and this is especially true in the current commercial arena, where many technology-intensive products based on artificial intelligence are designed, developed and launched onto the market. It is evident that new innovative ideas are primarily recognised based on technological advances and improvements; in the literature, these are referred to as technology-push innovations (Chau and Tam 2000; Uriona-Maldonado et al. 2010). For this reason, the existing literature has been almost unanimous in support of the value of technology planning. This is critically important, since planning innovation generally begins under conditions of extreme uncertainty; this is known as a fuzzy front end (Brem and Voigt 2009), and needs to be dealt with using a well-planned and integrative planning method. * Youngjung Geum [email protected] 1
Department of Industrial and Information Systems Engineering, Seoul National University of Science and Technology, Seoul, South Korea
13
Vol.:(0123456789)
Scientometrics
When planning technological innovation, the most important step involves an understanding of technology trends and identification of promising technological inventions. This is especially important in view of the rapid changes in technological development trends and the limited resources of each firm. Since the time and resources available for new product development are not endless, it is critically important to understand promising technologies within the industry. This task is known as technology forecasting, and has been widely discussed, both in theory and in practice (Daim et al. 2006). As Porter et al. (1991) have
Data Loading...
