• 지능정보연구
• /
• 제24권3호
• /
• pp.221-241
• /
• 2018

지식사회에 들어서며 새로운 형태의 자본으로서 정보의 중요성이 강조되고 있다. 그리고 기하급수적으로 생산되는 디지털 정보의 효율적 관리를 위해 정보 분류의 중요성도 증가하고 있다. 본 연구에서는 기업의 기술사업화 의사결정에 도움이 될 수 있는 맞춤형 정보를 자동으로 분류하여 제공하기 위하여, 기업의 사업 성격을 나타내는 한국표준산업분류(이하 'KSIC')를 기준으로 정보를 분류하는 방법을 제안하였다. 정보 혹은 문서의 분류 방법은 대체로 기계학습을 기반으로 연구되어 왔으나 KSIC를 기준으로 분류된 충분한 학습데이터가 없어, 본 연구에서는 문서간 유사도를 계산하는 방식을 적용하였다. 구체적으로 KSIC 각 코드별 설명문을 수집하고 벡터 공간 모델을 이용하여 분류 대상 문서와의 유사도를 계산하여 가장 적합한 KSIC 코드를 제시하는 방법과 모델을 제시하였다. 그리고 IPC 데이터를 수집한 후 KSIC를 기준으로 분류하고, 이를 특허청에서 제공하는 KSIC-IPC 연계표와 비교함으로써 본 방법론을 검증하였다. 검증 결과 TF-IDF 계산식의 일종인 LT 방식을 적용하였을 때 가장 높은 일치도를 보였는데, IPC 설명문에 대해 1순위 매칭 KSIC의 일치도는 53%, 5순위까지의 누적 일치도는 76%를 보였다. 이를 통해 보다 정량적이고 객관적으로 중소기업이 필요로 할 기술, 산업, 시장정보에 대한 KSIC 분류 작업이 가능하다는 점을 확인할 수 있었다. 또한 이종 분류체계 간 연계표를 작성함에 있어서도 본 연구에서 제공하는 방법과 결과물이 전문가의 정성적 판단에 도움이 될 기초 자료로 활용될 수 있을 것으로 판단된다.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2007년도 추계 종합학술대회 논문집
• /
• pp.103-106
• /
• 2007

지적재산권의 중요성이 커지면서 특허 검색을 이용하는 일반 사용자의 숫자가 늘어나고 있다. 일반적으로 한 두개의 키워드만을 사용하는 일반 사용자의 검색 패턴을 고려할 때, 대량의 특허 문서에서 원하는 검색 결과를 찾는 일은 쉽지 않은 일이다. 이에 모든 특허 문서에서 제공되는 국제 특허 분류(IPC) 정보를 사용해서 사용자의 검색 결과를 클리스터링하여 보여주어 사용자가 검색하고자 하는 검색범위를 손쉽게 제한 할 수 있도록 도와주어 원하는 결과를 좀 더 빠르게 찾을 수 있는 특허 검색 시스템을 소개하고자 한다.

• International Journal of Contents
• /
• 제13권2호
• /
• pp.66-74
• /
• 2017

Patent classification is becoming more critical as patent filings have been increasing over the years. Despite comprehensive studies in the area, there remain several issues in classifying patents on IPC hierarchical levels. Not only structural complexity but also shortage of patents in the lower level of the hierarchy causes the decline in classification performance. Therefore, we propose a new method of classification based on different criteria that are categories defined by the domain's experts mentioned in trend analysis reports, i.e. Patent Landscape Report (PLR). Several experiments were conducted with the purpose of identifying type of features and weighting methods that lead to the best classification performance using Support Vector Machine (SVM). Two types of features (noun and noun phrases) and five different weighting schemes (TF-idf, TF-rf, TF-icf, TF-icf-based, and TF-idcef-based) were experimented on.

• 정보관리연구
• /
• 제41권3호
• /
• pp.27-44
• /
• 2010

지금까지 특허분석에 관한 연구는 특허지도(Patent Map; PM)분석을 수행하여 기술동향을 분석하고 있으나, 주제에 대한 검색결과를 엑셀 등을 이용하여 그래프화하여 출원빈도에 대한 추이를 나타내는 것이 대부분이다. 이러한 분석은 특정주제에 대한 것으로 국가의 산업이나 국제적인 산업의 동향을 직접 비교 분석하기에는 미흡한 실정이다. 본 연구에서는 PM분석의 신뢰성을 높이기 위해 통계분석의 필요성을 제시하고, 1990년부터 2004년에 출원된(출원번호 기준) 한국특허 전체를 대상으로 연도별, 분류별(IPC Section 분류)로 각 국가(한국, 미국, 일본, 독일)의 출원빈도를 통계적으로 유의한 수준을 분석하였다. 또한 국가 및 기술 분류에 대한 출원빈도에 대해 포아송 회귀분석을 수행하고, 통계 적으로 유의한 수준에 따른 평가를 R&D에 활용할 수 있도록 하였다.

• 한국컴퓨터정보학회논문지
• /
• 제24권1호
• /
• pp.25-32
• /
• 2019

With the rapid development of artificial intelligence technology, the patenting activities related to the fields of AI is increasing worldwide. In particular, a share of patent filed in China has exploded in recent years and overtakes the numbers in the US. In the present study, we focus our attention on the patenting activity of China and the US. We analyzed 6,281 and 13,664 patent applications in the US and China respectively between 2008 and 2018, and belonging to the "G06F(Electric Digital Data Processing)", "G06N(Computer Systems Based on Specific Computational Models)", "H04L(Transmission of Digital Information)" and nine more relevant technological classes, as indicated by the International Patent Classification(IPC). Our analysis contributes to: first, the understanding of patent application trends from foreign countries filed in the US and China, 2) patent application status by applicants category such as companies, universities and individuals, 3) the development direction and forecasting vacant technology of AI according to main IPC code. Through the analysis of this paper, we can suggest some implications for patent research related to artificial intelligence in Korea. Plus, by analyzing the most recent patent data, we can provide important information for future artificial intelligence technology research.

• 대한예방한의학회지
• /
• 제18권2호
• /
• pp.147-154
• /
• 2014

Objective : The purpose of this study is to analyze for the patent application tendency in Korean Oriental Pediatric Medicine. Recently, many studies are published in Korean Oriental Pediatric Medicine. However, in the patent area, the research results are few. Method : For patent analysis, we searched the database kipris (http://www.kipris.or.kr) which managed in the Korean Intellectual Property Office by keywords about Korean Oriental Pediatrics. They are technically analysed by year and IPC, patent's contents, main applicant and organization. Results : 1. Patents by year have been on the rise 2 in 1997 to 32 in 2011. 2. Our findings are Section A61;182, A23;46 in IPC analysis 3. In classification of content, 'application-food' is 67 cases, 'application-functional cosmetic' is 18 cases, 'application-clothes' is 5 cases. 4. Korea Institute of Oriental Medicine have 14 patent cases, that is the most patent agency in possession. Main applicants are person > company > university > laboratory > state or local government. Conclusion : This study shows that it has high frequency of daily necessity in patent cases about oriental pediatrics. The results are more distributed 'applied' field than 'treatment' field. The patent information should be connected research achievement results in Korean Oriental Medicine.

• 한국지역사회생활과학회지
• /
• 제17권4호
• /
• pp.15-27
• /
• 2006

Most countries recognize traditional knowledge as an economical resource in recent years, and so are actively participating in WIPO discussions for making sure of their intellectual property rights. In this study, the definition of traditional knowledge was discussed for making clear its categories and relative subjects. A tool for Korean Traditional Knowledge Resource Classification(KTKRC) was developed for putting the data of the resources in order, and was indispensable for searching for and examining cultural artifacts within the system of international intellectual property rights. KTKRC covers comprehensively our various traditional knowledge resources and has a similar structure to IPC for international searching, examining, and information exchange. KTKRC consists of a section of traditional knowledge(A), and three subsections: production technology(A0), living technology(A2) and creative technology(A4). The subsections include 8 classes, 28 subclasses, 105 groups, and a great number of subgroups.

• 설비공학논문집
• /
• 제16권4호
• /
• pp.332-339
• /
• 2004

A technical analysis was conducted to predict the development trend for the highly efficient absorption type refrigeration system. The study was based on a submitted patent during January 1981 and December 2000 in Korea, Japan and America. The total number of extruded patents from the registered database was 24,822 and the filtering process makes the reduction of the data number to 3,510. Technical development of Japan for the absorption type refrigeration system is prominent compared to the other country due to approximately 75％ of the patents coming from Japan. When the patent is divided into two categories, the patent for component technology for the refrigeration system makes up 75％ and the refrigerating type technology 25％ of the patents. This shows technical development for the system component is advanced compared to the technology development for the system type. When the patents are classified by nationality of patent applicants, foreigners contribute up to 33％ of the patents in Korea. However, Japan's case shows the 99％ of the patents are invented by the Japanese. If the patents are classified to the International Patent Classification, most of the data for the absorption type refrigeration system belongs to IPC F25B.

• 한국산업융합학회 논문집
• /
• 제7권2호
• /
• pp.199-205
• /
• 2004

This paper describes the fault diagnosis method to order to construct CIM in complex system with hierarchical structure similar to human body structure. Complex system is divided into unit, item and component. For diagnosing this hierarchical complex system, it is necessary to implement a special neural network. Fault diagnosis system can forecast faults in a system and decide from the signal information of current machine state. Comparing with other diagnosis system for a single fault, the developed system deals with multiple fault diagnosis, comprising hierarchical neural network (HNN). HNN consists of four level neural network, i.e. first is fault symptom classification and second fault diagnosis for item, third is symptom classification and forth fault diagnosis for component. UNIX IPC is used for implementing HNN with multitasking and message transfer between processes in SUN workstation with X-Windows (Motif). We tested HNN at four units, seven items per unit, seven components per item in a complex system. Each one neural network represents a separate process in UNIX operating system, information exchanging and cooperating between each neural network was done by message queue.

• 한국정밀공학회지
• /
• 제14권11호
• /
• pp.135-146
• /
• 1997

This paper describes fault diagnosis method in complex system with hierachical structure similar to human body structure. Complex system is divided into unit, item and component. For diagnosing this hierarchical complex system, it is necessary to implement special neural network. Fault diagnosis system can forecast faults in a system and decide from current machine state signal information. Comparing with other diagnosis system for single fault, the developed system deals with multiple fault diagnosis comprising Hierarchical Neural Network(HNN). HNN consists of four level neural network, first level for item fault symptom classification, second level for item fault diagnosis, third level for component symptom classification, forth level for component fault diagnosis. UNIX IPC(Inter Process Communication) is used for implementing HNN wiht multitasking and message transfer between processes in SUN workstation with X-Windows(Motif). We tested HNN at four units, seven items per unit, seven components per item in a complex system. Each one neural newtork operate as a separate process in HNN. The message queue take charge of information exdhange and cooperation between each neural network.