• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.147-170
• /
• 2022

Although the number of patent which is one of the core outputs of technological innovation continues to increase, the number of low-value patents also hugely increased. Therefore, efficient evaluation of patents has become important. Estimation of patent lifespan which represents private value of a patent, has been studied for a long time, but in most cases it relied on a linear model. Even if machine learning methods were used, interpretation or explanation of the relationship between explanatory variables and patent lifespan was insufficient. In this study, patent lifespan (number of renewals) is predicted based on the idea that patent lifespan represents the value of the patent. For the research, 4,033,414 patents applied between 1996 and 2017 and finally granted were collected from USPTO (US Patent and Trademark Office). To predict the patent lifespan, we use variables that can reflect the characteristics of the patent, the patent owner's characteristics, and the inventor's characteristics. We build four different models (Ridge Regression, Random Forest, Feed Forward Neural Network, Gradient Boosting Models) and perform hyperparameter tuning through 5-fold Cross Validation. Then, the performance of the generated models are evaluated, and the relative importance of predictors is also presented. In addition, based on the Gradient Boosting Model which have excellent performance, Accumulated Local Effects Plot is presented to visualize the relationship between predictors and patent lifespan. Finally, we apply Kernal SHAP (SHapley Additive exPlanations) to present the evaluation reason of individual patents, and discuss applicability to the patent evaluation system. This study has academic significance in that it cumulatively contributes to the existing patent life estimation research and supplements the limitations of existing patent life estimation studies based on linearity. It is academically meaningful that this study contributes cumulatively to the existing studies which estimate patent lifespan, and that it supplements the limitations of linear models. Also, it is practically meaningful to suggest a method for deriving the evaluation basis for individual patent value and examine the applicability to patent evaluation systems.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.11
• /
• pp.2724-2730
• /
• 2015

Internet of Things (IoT) is possibly the most widely discussed technological concept in today's technology circles. This technology is expected to dramatically change not only how we work but also how we live. The concept of IoT basically means a web of connected devices which can be controlled over a data network. With cost of technology required to control these devices going down and increasing internet connectivity through smartphones, IoT is expected to be an all pervasive technology in the next 10 years. In this paper, we study the technological landscape of this fast growing technology domain from an Intellectual Property (Patents) perspective. We find that the patent distribution in this domain is very fragmented with the top patent applicants in the field holding around 5% of the total patents. Especially, the US geography has seen the maximum patent filings and is closely followed by the big Asian markets of Japan and Korea.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.185-199
• /
• 2018

The purpose of this study is to derive the core technologies of VR using patent analysis and to explore the direction of social and public interest in VR using news analysis. In Study 1, we derived keywords using the frequency of words in patent texts, and we compared by company, year, and technical classification. Netminer, a network analysis program, was used to analyze the IPC codes of patents. In Study 2, we analyzed news articles using T-LAB program. TF-IDF was used as a keyword selection method and chi-square and association index algorithms were used to extract the words most relevant to VR. Through this study, we confirmed that VR is a fusion technology including optics, head mounted display (HMD), data analysis, electric and electronic technology, and found that optical technology is the central technology among the technologies currently being developed. In addition, through news articles, we found that the society and the public are interested in the formation and growth of VR suppliers and markets, and VR should be developed on the basis of user experience.

• Journal of Technology Innovation
• /
• v.22 no.4
• /
• pp.117-143
• /
• 2014

Tracing an evolutionary technological trajectory in the macroscopic viewpoint is useful for technology policy, but not for corporate technology and intellectual property strategy. Tackling this issue, recent bibliometric studies using patents and papers have made efforts to identify more specific and detailed technological trajectory. However, these studies cannot go beyond simple description of the past trajectory. Also, identification of technology fusion and evolution relies on experts judgments. We suggest a way of identifying microscopic evolutionary technological trajectories by combining patent citation network analysis with dynamic technology tree. Also, using new indicators of generality, diversity and novelty, we can detect key technologies that can be a starting point of next generation technology and derivative technology. HVDC(High Voltage DC transmission) system technology is exemplified.

• Asian Journal of Innovation and Policy
• /
• v.8 no.1
• /
• pp.73-96
• /
• 2019

This study suggests a new approach for identifying core robot tech-nologies based on technological cross-impact. Specifically, the approach applies data mining techniques and multi-criteria decision-making methods to the co-classification information of registered patents on the robots. First, a cross-impact matrix is constructed with the confidence values by applying association rule mining (ARM) to the co-classification information of patents. Analytic network process (ANP) is applied to the co-classification frequency matrix for deriving weights of each robot technology. Then, a technique for order performance by similarity to ideal solution (TOPSIS) is employed to the derived cross-impact matrix and weights for identifying core robot technologies from the overall cross-impact perspective. It is expected that the proposed approach could help robot technology managers to formulate strategy and policy for technology planning of robot area.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.193-201
• /
• 2018

In this paper, we extracted relevant patent data and conducted statistical analysis to understand the technical development trend related to Wireless Power Transfer (WPT) for Light Rail Transit (LRT). Recently, with the development of WPT technologies, the Light Rail Transit (LRT) industry is concentrating on applying WPT to the power supply system of trains because of their advantages compared wired counterpart, such as low maintenance cost and high stability. This technology is divided into three areas: wireless feeding and collecting technology, high-frequency power converter technology and orbital and infrastructure technology. From each specific area, key words in patent document were extracted by TF-IDF method and analyzed by social network. In the keyword network, core word of each specific technology were extracted according to their degree centrality. Then, the multi-word phrases were also built to represent the concept of core technologies. Finally, based on the analysis results, the development strategies for each specifics technical area of WPT in LRT filed will be provided.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.10 no.1
• /
• pp.143-151
• /
• 2015

Technology convergence, recently accelerated in various technical fields, can be achieved by discovering a new technology while exchanging the knowledge among the different technologies and utilizing such knowledge into the existing fields of technology. In particular, technology convergence actively occurs in knowledge-intensive ICT. However, limited research is available on the routes of ICT technical knowledge diffusion because of insufficient data. Therefore, this study built a database on the citations of patent data applied from 2006 to 2013 in Korea and their cited patents. We drew a patent citation network, a technology citation network and an applicant citation network, after which we analyzed the routes of technical knowledge diffusion. Results showed that ICT played a leading role in knowledge citation among technologies and that such diffusion took a shorter time in technology citation when it occurred more frequently and when the citation occurred between ICTs. In addition, most of the ICT showed a strong citation relationship with the other ICTs or such technologies in the field of physics or electricity, whereas electric elements (H01) showed various citation relationships with technologies other than ICT. Furthermore, we found a strong technology diffusion relationship between domestic corporations and domestic natural persons. National organizations often cited the patents of other applicants, whereas the patents of domestic corporations were actively cited between domestic corporations or by other applicants. Thus, this study is expected to be useful in measuring the performance of technologies, including the diffusion to other technologies. As well as in considering the routes of technical knowledge diffusion in Korea.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.10 no.1
• /
• pp.86-93
• /
• 2007

The objective of this paper is to examine the structure of technology spillover from UAV(unmanned air vehicle) technology to other industries by applying patents analysis. The network analysis on patent data of USPTO(United Stated Patents and Trademark Office) from 1981 to 2000 was adopted to investigate the characteristic change of the technology spillover The results show that the influence of the UAV technology to other industries has grown over the twenty years period. For the weapon system development, this study provides a research basis to estimate the technology spillover effects on industries. Searching a structural niche from the inter-industrial knowledge flow structure might be a useful technique to find core technologies which generate large technology spillover on the other industries.

• Journal of Technology Innovation
• /
• v.26 no.3
• /
• pp.1-36
• /
• 2018

In the era of the 4th Industrial Revolution, it is important for companies to understand the changing environment by converging various technologies and to respond to the changing business environment. In this study, we conducted a social network analysis on 10 firms in the automotive industry, which have recently been accelerating their competition for technology development, by extracting convergence patents co-classified in two or more of the US registered patents in the last 6 years. As a result, it has been confirmed that the number of technology related to the convergence of the automotive field is greatly increasing, and the convergence between the technologies is becoming stronger. In addition, Volkswagen, Ford and Hyundai showed significant changes in technology convergence. They were analyzed as having a change in strategy in eco-friendly automotive technologies. This study suggests various ways for companies to utilize the results of network analysis more meaningfully.

• The Journal of Engineering Geology
• /
• v.23 no.2
• /
• pp.127-136
• /
• 2013

We analyzed the patent trends for whole drilling bits to reveal the main R&D directions, focusing on patents applied for and registered in Korea, the USA, Japan, and Europe. The technology was classified into two groups as a primary classification step (reaming systems and fixed systems), and into seven groups as a secondary classification step (sliding, odex, horizontal pivot, vertical pivot, concentric, eccentric, and etc.). A total of 33,614 patents were retrieved and 870 patents were selected for final effective analysis by data deduplication and filtering. A portfolio analysis using the correlation between the number of patents and the applicants for each patents revealed a sliding system as the key technology with greatest growth potential. From an analysis of the barriers to patents being granted, we emphasize the need to avoid similar topics existing patents or patent applications and to develop differential technology.