Wonchul Seo

Analyzing interdisciplinarity of technology fusion using knowledge flows of patents

Despite the importance of identifying industry-wide impact of technology fusion, there are few studies to analyze interdisciplinary trends of technology convergence from an industry-wide perspective. This paper, therefore, presents a procedural method to analyze trends of industry-wide technology fusion by measuring knowledge flows of patents. The method constructs a technological knowledge flow matrix that represents knowledge flows among technology classes, and then extends it to an industry-wide knowledge flow matrix by exploiting the concordance between technology classes and industrial sectors. By computing assessment indicators of technology fusion regarding industrial sectors of a specific technology area, the method outputs a visual map that shows trends of industrial technology fusion. The presented method is illustrated using patents related to the new and renewable energy-based railway technology. We expect that the method will be incorporated into the R&D planning processes to assist R&D planners to initiate new R&D projects with a proper direction. Under these directions, the R&D projects can create new inventions by converging prominent technologies beyond industrial boundaries. Further, the method has the potential to become a basis of systematic support systems for technology experts to conduct knowledge-intensive technology planning activities.

Identifying product opportunities using collaborative filtering-based patent analysis

We propose a recommendation approach for product opportunity exploration.The approach identifies application products based on a firms existing product portfolio.The approach is built on patent text mining and collaborative filtering.The approach contributes to systematic product opportunity discovery across domains. One practical and low-risk approach to product planning for technology-based firms is to identify application products based on their existing product portfolios. Previous studies, however, have tended to neglect the current product development capabilities of target firms and to apply the technical data of specific fields to their methods, thereby failing to quantify a way of identifying various product opportunities. As a remedy, this paper proposes a new multi-step approach to product recommendation. The steps include (1) generating assigneeproduct portfolio vectors using text mining on a large-scale sample of patents, (2) recommending untapped products for a target firm by using latent Dirichlet allocation and collaborative filtering, (3) producing a visual map based on the promise and domain heterogeneity of the recommended products. To validate the practicability, we applied our approach to a Korean high-tech manufacturer by using all of the patents registered in the United States Patent and Trademark Office database during the period of time from 2009 to 2013. This study contributes to the systematic discovery of new product opportunities across various domains using the existing product portfolios of firms, and could become the basis for a future product opportunity analysis system.

Development of a Data and Model-Interconnected Holonic Architecture for Intelligent Decision-Making on Cyber-Physical Production Systems

In manufacturing industries, the intelligence, autonomy and interconnectivity of manufacturing objects, and the adaptiveness in dynamic changes have been recognized as desirable objectives; however, they were hard to implement. Recently, the convergence of the advances in information and communication technology is making it possible to implement those objectives, called Smart Manufacturing (SM). Of these SM technologies, Cyber-Physical Production Systems (CPPS) will be considerably one of the most-advanced technologies because CPPS envisions dynamic and autonomous capabilities through mirroring physical and their cyber manufacturing objects in real-time. These capabilities match with the aim of Holonic Manufacturing Systems (HMS) in terms of autonomy and cooperation, thereby making HMS re-highlighted as a control architecture of CPPS. This paper presents the development of a data and model-interconnected holonic control architecture that especially considers the synchronization with a big data infrastructure and a data analytics environment. The present work aims at providing : 1) a predictive process-planning mechanism with the connection of manufacturing data and decision-making models, and 2) a systems integration environment for opening the information about intelligent manufacturing objects. The goals of the present work are to increase intelligence and interconnection, which are the major performances pursued by CPPS.