Patent Analysis for Organization based on Patent Evolution Model Yunji Jang Jangwon Gim Jinpyo Lee KISTI, UST KISTI KAIST Korea Institute of Science and Korea Institute of Science and Korea Advanced Institute Technology Information, KISTI Technology Information, KISTI of Science and Technology, University of Science and Daejeon, South Korea KISTI Technology, UST jangwon@kisti.re.kr Daejeon, South Korea Daejeon, South Korea jinpyo.lee@cs.kaist.ac.kr yunji@kisti.re.kr Do-Heon Jung Hanmin Jung KISTI KISTI Korea Institute of Science and Korea Institute of Science and Technology Information, KISTI Technology Information, KISTI Daejeon, South Korea Daejeon, South Korea heon@kisti.re.kr jhm@kisti.re.kr ABSTRACT With the rapid progress in science and technology in recent times, new research fields are being discovered and studied each day and 1. INTRODUCTION With the rapid progress in science and technology in recent times, numerous research findings are being published and presented. new research fields are being discovered and studied each day and Considering this, organizations from various countries have been numerous research findings are being published and presented. In investing considerable effort to bring about internal and external several countries including South Korea, USA, and Japan, changes in their organizations. In fact, at many organizations, policies for strengthening the protection of intellectual property studies are being carried out to derive meaningful results by are being implemented. Moreover, the number of patent analyzing research outcomes. Thus, in this paper we propose an applications for research results has also increased [1]. evolution model through analysis of the patent titles from one Considering this, organizations from various countries have been specific institution. First, we classified the keyword of title investing considerable effort to bring about internal and external according to properties of keyword and then defined the relation changes in their organizations. In other words, organizations case of patent. After, we suggest the evolution model of relation believe that they may not be able to survive in today’s competitive based on timeline and applied to the actual data. It can predict market without innovation, and therefore, much effort is being keyword of future patent by applying to actual data. invested in that direction [2]. In fact, at many organizations, studies are being carried out to derive meaningful results by analyzing research outcomes [3,4]. In general, among the research Categories and Subject Descriptors outcomes, patent data is a type of research outcome that can be H.4 [Information Systems Applications]: Data Mining used as an indicator for measuring the technological and I.6: [Simulation and Modeling]: Model Validation and Analysis innovative competency of an organization. Patents are not only essential from the standpoint of copyrighting and publishing of General Terms research and development, but also for aiding future research and Theory development plans [5]. Patent data consist of title, technology implementation details, Keywords technology category code, citation information, and owner Patent Data, Patent Analysis, Patent Keyword, Patent Evolution, information. Analyzing such patent information is very important Organization Patent because it can help in interpreting the changes in the technology, trends, level, and commercial value. Patent analysis includes various kinds of analysis such as frequency analysis, share Copyright © 2015 for the individual papers by the papers' analysis, time-series analysis, citation analysis, and rights analysis. authors.Copying permitted for private and academic purposes. Time-series analysis and two-dimensional analysis, in particular, This volume is published and copyrighted by its editors. are more common [6]. Published at Ceur-ws.org Proceedings of the Second International Workshop on Patent Mining and its Applications (IPAMIN). May 27–28, 2015, Beijing, China. 2.1. Title Refinement Table 1. Types of patent analysis The refining patent title stage is performed prior to the extraction Theme Details of meaningful keywords such as goal and approach. In this stage, Frequency Filed country, Inventor, Applicant, unnecessary words are removed from the patent title. On the basis Analysis Technology Classification .. of blank spaces, the patent title is divided. Considering the Filed country, Inventor, Applicant, statistical numbers of divided words, they are removed step by Share Analysis Technology analysis, Detailed technical step. classification .. Application rate analytics , National analysis, 2.2. Patent Representation Time Series Inventor analysis, Applicant analysis, To observe the keyword concept-based evolution process for a Analysis Technical analysis, New applications analysis, certain organization, the words from the refined titles are New inventor analysis .. classified into Approach, Goal Object, and Goal Predicate. Goal Inventor correlation map, Applicant represents keywords that indicate the purpose of the patent's Correlations correlation map, Technical correlation map .. invention. Since the title of a patent is the name of the invention, a Citation Citation relation analysis , Core patent goal keyword, which is the target technology, is always present. Analysis analysis .. Based on the type of Patent, Approach keywords are sometimes Rights Patent family map .. present, which are keywords that describe the core technology Analysis used to develop the goal technology. In this study, a dictionary was built for classifying keywords into Approach and Goal. The Several studies have attempted to analyze the characteristics of classified Approach and Goal keywords are tagged as object and companies based on the citation relationship of patents, for predicate through a prebuilt morpheme analyzer. When the example, the number of research projects that attempt to morpheme analysis is completed, a relation network is drawn to determine the technological strategy of a competing company map the relation types between Approach, Goal Object, and Goal through citation relationship has been on the rise [7-10]. Predicate. These studies analyze a company based on the information of the 2.3. Relation Type Definition patents the companies have applied for; however, to the best of our knowledge, no study has performed a time-series analysis of All types were defined for the types of relations for patent patent data yet. Therefore, in this paper, we propose a patent expressions between two or more patent titles. The relations evolution model based on time-series analysis. Furthermore, defined in this paper refer to cases in which one or more keywords unlike previous papers, in this paper, we only analyze the title, overlap among three keywords that are separated into Approach, among the many patent data, as a patent title can adequately serve Goal Object, and Goal Predicate. as representative information about a patent. 2. PATENT ANALYSIS MODEL In this study, we analyze the evolution process of a patent title in four stages. Figure 1 shows procedure of patent analysis. First, after removing the useless, meaningless words from a patent title, the remaining words, keywords, which represent the purpose of the patent and the patent's core technology, are extracted. Next, while drawing a relation network to map the relation type between the extracted keywords, the evolution of relation types is examined by applying time-series analysis. Figure 2. Patent relation types Figure 2 shows the relation types that can be derived on the basis of Approach, Goal Object, and Goal Predicate. A circle indicates an Approach, a triangle indicates a Goal Object, and a diamond indicates a Goal Predicate. Figure 2-1) indicates one patent type. Figure 2-2) relation type is X-type. X- type is a case involving several Approaches and several Goal Predicates mapped to one Goal Object. Figure 2-3) relation type is Y- type. The Y- type is a case involving several Approaches mapped to a Goal Object and Goal Predicate pair. Figure 2-4) relation type is inverted Y- type. The inverted Y-type is a case of several Goal Predicates mapped to an Approach and Goal Object pair. Figure 2-5) relation type is V- type. In the V-type, several Goal Objects and several Figure 1. Patent analytics model Procedure Approaches are mapped to one Goal Predicate. Figure 2-6) relation type is inverted V-type. In the fifth inverted V-type, several Goal Objects and Predicates are mapped to one Approach. Table 2. Semantic stopword dictionaries The ◇ type is a case involving several Goal Objects mapped to an Approach and Goal Predicate pair. Finally Figure 2-8) refers to Semantic Stopword General Stopword the Double X type having the several approaches, Goal Object, System and Method Optimum and Goal Predicate. X type of relationship types can also have resulted in multiple forms, but we studied only Double X type of Apparatus and method Effective relationship type. Method and System For 2.4. Evolution Model Definition System and Apparatus About In this section, a definition is provided for the evolution model. Framework Included The evolution model is made using the characteristics of relation types based on the time-series data of a certain organization. System At Figure 3 shows a model that can evolve according to the relation : : type. As an example of an evolvable model, “A type can evolve to B type” refers to a case where the condition of B type is satisfied when A type and B type are combined. In other words, when A Table 3. Distinguishing word dictionaries type and B type are combined , it should be B type. A-G Distinguishing word A-G Distinguishing word Based on Applied Based Through Using By Centered According to Table 3 used is a terminology dictionary for classifying Approach and Goal. After classifying Approach and Goal, the remaining words are processed as useless words. In fact, the words of Korean are more than English word. So Table 3 is smaller than Korean dictionaries. Figure 3. Evolution model 3.3. Statistics The statistics produced when applying the unnecessary word All relation types can evolve into the type of each one. Ø and I dictionary for 82 cases are shown. Goal Object and Goal Predicate relation types can be evolved into all relative types. In addition, were extracted in all 82 cases, and Approach was extracted in only all relation types can evolve into all relative types. However, Y 44 cases. We made the statistics about the relation type and and can evolve into the X relation types. evolution model. Table 4 shows the cumulative statistics of relation cases from 2005 to 2013. The X-type type appeared most, 3. EXPERIMENT followed by V-type. 3.1. Data Set Table 4. Statistics of relation type The data set was composed of 82 patents of the Computer Base X Y V Λ ◇ Intelligence Lab of Korea Institute of Science and Technology Information (KISTI) from 2005 to 2013. At first we started 99 2005 1 0 0 0 0 0 0 data but 17 titles having parallel structures were discarded. 2006 0 1 0 0 0 0 0 3.2. User Defined Dictionaries 2007 1 1 0 0 1 0 0 As explained in the overall process stage, a process involving 2008 3 1 0 0 0 0 0 analysis and tagging of a sentence structure was performed. Based 2009 2 3 0 0 1 1 0 on the patent title set, several word dictionaries were built. Modeling was performed to identify similar results through 2010 2 4 1 1 4 2 0 cognitive analysis. Tables 2 and 3 is a dictionary to translate Korean to English. Table 2 shows the part of dictionary used for 2011 2 4 2 1 5 3 1 refining useless words. 2012 3 5 3 1 5 3 1 2013 3 6 3 1 5 3 1 Sum 3 6 3 1 5 3 1 Table 5. Statistics of evolution model I I X X XX Y Ø Ø Ø → → → → → → → → → XX X X XX XX XX I V Y 2005 0 0 0 0 0 0 1 0 0 2006 0 1 0 0 0 0 0 0 0 2007 0 0 0 1 0 0 1 0 0 2008 0 0 0 0 0 0 2 0 0 2009 1 1 0 0 1 0 2 1 0 2010 0 1 0 1 3 0 1 0 1 2011 0 0 2 1 0 1 0 0 0 Figure 5. Evolution model in KISTI 2012 0 1 1 0 1 0 1 0 0 2013 0 0 0 0 1 0 0 0 0 Sum 1 4 3 3 6 1 8 1 1 The Evolution Model which can be discovered in KISTI patent among 30 Evolution Model is 9. The numbers in Figure 5 is the Table 5 is statistics of evolution model. It was the most abundant probability to go in the direction of the arrow. I type, Y type , V to evolve into the Ø types from I type. This evolution case means type are evolved from the O type. The probability of evolving into new patent is indicated in KISTI. I types is 0.8, the probability of evolving into Y and V types are 0.1. The types which can be evolved from I type are X and XX 3.4. Result type. The probability of evolving into X type is 0.8 and the probability of evolving into XX type is 0.2. The types which can In this section, we compare the actual results with the evolution be evolved from X types are X types and XX type. And each model proposed in this paper. probability is 0.5. The XX type is only type which can be evolved from Y type and XX type evolves into XX type. The inversed Y type, Λ type and ◇ type of evolution model are not observed in KISTI patent. By predicting the future evolution type KISTI patent based on this result, it can be extract keywords that match the type of evolution. For example, when the patent evolves into the patent of X types from I type, we can predict that KISTI will research about Goal Object. 4. CONCLUSIONS In this paper, we proposed the patent evolution model through the patent title analysis of the specified affiliation. We presented the new possibility by studying the Korean title which was not active in the existing research. We removed the stop words at the patent title of the specified affiliation and we separated the Approach, Goal Object, and Goal Predicate. By using separated three keywords, we drew the connection network in the patent title based on time series. It defined the types of relationships that may Figure 4. Relation network of KISTI patent appear between the patent through the network connection in a given year. And then we can know the relation case of organization based on the result of test. Figure 4 shows the final relation network of Approach, Goal Object, and Goal Predicate for 2013. The network was drawn by Patent analysis systems and related methods currently rely on NodeXL [11]. The evolution of relation types was examined by basic visualization techniques and patent maps, such as bar graph, drawing the relation network for patent titles keywords of 2005 to pie chart, separate table, and bubble diagram. Relation types 2013, as shown in Figure 4. Figure 4 shows the evolution model between patents and an evolution model of relations were produced from the KISTI patents. Figure 5 shows the evolution proposed only using the titles of patents. model produced from the KISTI patents. In a follow-up study, we plan to perform the same analysis for a different organization, and compare it with the evolution result of this study; further, we plan to examine the expandability of the proposed model. In particular, we aim to further develop the proposed patent evolution model so that it can be applied to patent titles of other countries in addition to those of South Korea. Furthermore, we expect to use it in convergence technology prediction by predicting a relation type, in which a patent relation of certain relation type will evolve, through the evolution model. international conference on Communities and technologies, pp. 255-264, 2009. Acknowledgments This work was supported by the IT R&D program of MSIP/IITP. [B010-15-0353, High performance database solution development for Integrated big data monitoring and Analytics] 5. REFERENCES [1] Sang-cheol Kil, Sung-min Kang, "The study of an Analysis on Patent Management Affecting the Company Performance, " In Proceedings of the Korea Technology Innovation Society 2008, Vol. 11, No. 2, pp. 171-193, 2008. [2] SeongTaek Park, Youngki Kim, Taeung Kim, "A Study on Infuencing Factors of Patent Activities on Magnagement Performance," In Journal of Entrue Journal of Information Technology 2013, Vol. 12, No. 3, pp. 121-129, 2013. [3] Hwan Lim, Hosun Rhim, Myungho Sohn, "Study for Improving the Patent Management Schema by Using Citation Index in Public-sector R&D Institute : Case Study on K Institute," In Journal of the Korea Society of IT services, Vol. 7, No. 3, pp. 115-127, 2008. [4] Mu-hsuan Huang, Li-yun Chiang, Dar-zen Chen,. " Constructing a patent citation map using bibliographic coupling : A study of Taiwan’s high-tech companies," In Proceedings of the Scientometrics , Vol. 58, No. 3, pp 489-506, 2003 [5] Sunghae Jun, Sang-Sung Park, Young-Geun Shin, Dong-Sik Jang, HoSeok Chung, "Forecasting Vacant Technology of Patent Analysis System using Self Organizing Map and Matrix Analysis," In Journal of the Korea Contents Association , Vol. 10, No. 2, pp. 462-480, 2010. [6] Jin-Hyo Joseph Yun, Oh-Jin Kwon, Jinseo Park, Eui-seob Jeong, "A Study on the Development and Adaption of Open Innovation Analysis Model," In Proceedings of the Korea Technology Innovation Society 2010, Vol. 13, No. 1, pp. 99-123, 2010. [7] Aidong, Peng. "The Application of Patent Citation Analysis in Enterprise Competitive Intelligence," In Proceedings of the Information Studies: Theory & Application, Vol. 27, No. 3, pp no. 16, 2004. [8] Lingyun Sun,, Yu Song, "Research on Clustered Patent Mapping Visualization and Interaction," In Proceedings of the Computer-Aided Industrial Design and Conceptual Design, pp. 1130-1133, 2008. [9] Jinho Choi, Junguk Kim, "Analysis of Assortativity in the Keyword-based Patent Network Evolution," In Journal of Internet Computing and Services, Vol. 14, No. 6, pp. 107-115, 2013. [10] Xian Wu,, Li Zhang, " SIMPLE: A Strategic Information Mining Platform for Licensing and Execution," In Data Mining Workshops, pp. 270-275, 2009. [11] Marc Smith, Ben Shneiderman, Natasa Milic-Frayling, Eduarda Mendes Rodrigues, Vladimir Barash, Cody Dunne, Tony Capone, Adam Perer, Eric Gleave, "Analyzing (Social Media) Networks with NodeXL," In Proceedings of the fourth