It is crucial to understand the technical groups of intra-industry and to master the competition in the field of technology. In order to provide valuable information for industry participants and policymakers, a process model for mining technical competitor groups based on IPC classification number is put forward. Firstly, the patent numbers under each IPC are counted for building feature vectors for competitors. Then, technical similarities between each pairs of competitors are computed. Finally, the LinLog graph clustering algorithm is carried out to discover three levels of groups, i.e. institution, province and country. To obtain patent data for this research, an acquisition system for Chinese patent data is developed. Experiments on the field of fuel cell is conducted and the results show the technique is helpful and effective.
Copyright © 2015 for the individual papers by the papers' authors. Copying permitted for private and academic purposes.
This volume is published and copyrighted by its editors.
Published at Ceur-ws.org Proceedings of the Second International Workshop on Patent Mining and its Applications (IPAMIN). May 27–28, 2015, Beijing, China.
Competitiveness is a typical characteristic for industrial technology (Yoon, 2008) [1]. Practically, for almost every emerging industry, some kinds of technology will become leading and predominant after developing over a period of time. Agglomeration is common for an industry. When the industrial technology agglomerates to a certain extent so that it can meet the needs of product functions well, the industry will become mature, and the industrial technology system is established. On the other hand, the technology owner compete reciprocally into different technical groups. According to Porter's theory of competitive advantage, the real competitors inside an industry are companies similar to a company (Lee, 2006) [2]. These similar companies constitute a strategic group and become a sub-industry. A company has barriers to enter different strategy groups. Therefore companies which have very similar industrial technology are likely to be main competitors.
The clustering method of dividing data into several clusters can reflect relational schema of the data and the knowledge hidden in the data. The method of competitor group analysis of industrial technology is to use appropriate clustering algorithm to divide competitors into several groups, and thus identify similar competitors inside an industry competitions and their reciprocal influences. The level of technical competitor group analysis can be from different aspects such as countries, provinces, and institutions. The purpose of the analysis is to understand the technical groups inside an industry, and to master the competition in the field of technology from higher levels, and to provide valuable information for industry participants and policymakers. Some common clustering algorithms can be used to identify the competitor group of industrial technology, such as self-organizing mapping (SOM), K-means (Lee, 2009) [3], factor analysis, etc. In these models, each competitor is usually expressed as a feature vector which are measured by several technical characteristics. Similar objects will be clustered into one group by calculating distances between them. For example, (Pilkington, 2004)[4] used UPC number and IPC classification respectively as the technical features for competitors and used the factor analysis model to cluster 52 companies in the field of fuel cell into five groups. Literature studies found that many researchers have used visualization methods. The traditional clustering algorithm is based on the unsupervised learning so people often doubt the effectiveness of the analysis results. The visualization method can display abstract data using graph or picture because it combines the computer technology and human cognitive ability effectively. Therefore, the visualization method enhances the user’s confidence for the analysis results, so it has been widely accepted in recent years. Considering the advantages of visualization, the proposed method will use graph clustering method to find technical competitor groups.
LinLog algorithm was first put forward by (Noack, 2007) [5]. The aim of the algorithm is to produce ideal and visual clustering graphs. Figure 1 shows an example mentioned in Noack's paper (Noack, 2005) [6]. In the example, Spring and LinLog algorithm were employed respectively for graph clustering using the same data. Comparatively, LinLog algorithm clearly divided data into two large clusters which are connected by two nods, Dan and Upton, while Spring algorithm positioned nodes with high degree in the center and nodes with low degree near the borders. (a) Spring model
(b) LinLog model The LinLog model does not conform to the traditional aesthetic standard, it aims to group nodes of closely connected and separate nodes of partially connected. There are two kinds of LinLog models: node-repulsion model and edge-repulsion model(Coscia, 2009) [7]. The two models are based on two famous clustering standards respectively (Li, 2008) [8], namely density of cut and normalized cut. Normalized cut and edge-repulsive model can produce unbiased results, therefore it is especially suitable for normally distributed data. In this paper, LinLog algorithm of Barnes and Hut hierarchy algorithms is used to draw clustered graphs (Stegmann, 2003) [9]. After the algorithm draw graphics, it also divide nodes into several clusters. 2.2 IPC IPC means the international patent classification. IPC is an international standard which is used by the patent offices of all countries or regions in the world. Although some countries or regions make its own patent classification system, such as CPC system of USPTO, ECLA system of EPO, they provide the IPC classification number. Chinese patent classification system also use IPC system. A patent has at least one IPC number, but is not limited to one IPC classification number. In other words, some patents are endowed with two or more IPC classification numbers. The first classification number is called the main classification number when there are multiple patent classification numbers. According to the characteristics of technical topics of the invention, the technology fields in IPC system are divided into 8 sections. Each section represents a kind of technology, designated by one of the capital letters A through H as shown in Table1.
The structure of IPC classification system is hierarchical. Sections are the highest level of hierarchy in the system. Each section is subdivided into classes which are the second hierarchical level. Each class comprises one or more subclasses which are the third hierarchical level. Each subclass is broken down into subdivisions referred to as “groups”, which are either main groups (the fourth hierarchical level) or subgroups (lower hierarchical levels dependent upon the main group level). A complete classification symbol comprises the combined symbols representing the section, class, subclass and main group or subgroup, as shown in Figure 2. Currently, there are approximately 70,000 subdivisions in the classification system. Figure 3 is a sample of the hierarchical structure.
An industrial technology field can be divided into several
subfields, and each subfield may have smaller technology
subfields. Technology competitors often have different research
background, bases, objectives and priorities. Competitors with
similar technology may be competitors or partners on the market,
and they are likely to interact with each other. IPC classification
codes are designated by patent examiner with professional
knowledge. Therefore IPC provide an effective way to know
industrial hot points, and research and development directions of
technology competitors. A technology competitor tend to invest
research in several technical subfields, so it is difficult to
determine whether two competitors have similar research
technology only from the IPC count statistics. Therefore, a graph
clustering method based on main IPC number is put forward to
identify technology competitor groups within an industrial
technology field. Figure 4 shows the process model of this method.
Firstly, selecting a clustering level from three categories:
institutions, provinces and countries. Then, counting the patent
number under each main IPC classification number for each
technology competitor. Then the association matrix is established
between technology competitors and the main IPC classification
number (Dibattista, 1994)[10]. Each technology competitor is
expressed as a feature vector whose attributes are IPC
classification numbers. The value of each attribute item is the
number of patents under the main IPC classification number.
Finally, calculating the similarity between each pair of
technological competitors by using cosine formula(Fruchterman,
1991)[11]. Let IPC as the number of the IPC main classification
number covered by industrial technology, and the patent number
of competitor i under k-th IPC classification number is IPCki .
The equation (
IPC IPCki IPCkj k 1 IPC IPCki2 k 1
IPC
IPCkj
k 1
2
(
Nowadays, almost all patent offices of major countries and regions provide patent databases on their official web sites. People can connect these websites any time and everywhere via the Internet to obtain the patent data freely. In order to get patent data quickly, a patent data acquisition system (Laura, 2008) [13] is developed. The model of the system model is shown in Figure 5. The acquisition system can fetch HTML web pages which contains the patent description information from the official website of the state intellectual property office of China (http://www.sipo.gov.cn/). After the patent information is collected, it can automatically obtain the items of description and legal status of patents through the content analysis of web pages and save them into the local databases. In order to test the effectiveness of proposed method, the patent acquisition system is run to download patent data in the field of fuel cell technology. 6346 patents are collected totally. The following preprocessing steps and the empirical analysis will employ the downloaded patent data.
The collected data often have some problems, and it must be preprocessed before the formal analysis. In the experiment, the patent data will be preprocessed to meet the analysis requirements, including identifying the patent categories, countries and provinces of applicants, and categories of applicants, etc. If the first applicants are Chinese individuals or organizations, the addresses of the applicants often contain the information of its province (Kayal, 1999) [14]. Generally, the first 6 digits of the address description is the applicant’s postcode, so the province information can be obtained according to the postcode. If the first applicants are foreign individuals or organizations, the priority item and the international publication item in patent descriptions contain the state information. For example, the priority item of a patent is "1999.8.27 JP 242132/1999", where JP means that the applicant is a Japanese.
For the purpose of the research, applicants are divided into 5 categories: company, university, research institute, personal and the other. The categories are identified by the keywords in the applicant names. The corresponding relation of keywords and categories are shown in Table 2. If there are more than one applicants in a patent description, only the first applicant is considered. For example, there are two applicants of the patent No. 00112136.7: Nanjing Normal University and Changchun Institute of Applied Chemistry Chinese Academy of Sciences, the system will designate "university" category to the patent. company, partnership university, college research institution, committee, association, foundation
In order to have clear visual map, we choose top 20 research and development institutions for graph clustering algorithm. The result is shown in Figure 6. In the map, the size of nodes represents the number of granted invention patents, and the color of nodes shows the group they belong to (Reinhard, 2007) [15]. In the case, the LinLog algorithm identified two technology competitor groups (shown in Figure 6). The group with red node color is the first group, including 10. They are: Samsung (177), Chinese Academy of Sciences(128), Antiq(74), General Motors(56), Honda(52), Wuhan University of Technology(49), Shanghai Jiaotong University(38), Sanyo(37), BYD(32), and Harbin Institute of Technology(26); The group with orange node color is the second group, including 10 other institutions. They are: Shanghai Shen-Li High Tech(194), Panasonic(154), Toyota(120), Tsinghua university(72), Nissan(62), Toshiba(48), Sunrise Power(26), Hitachi (24), LG(20) and UTC (19). The numbers in parentheses after company names means the numbers of their granted invetion patents. Table 3 shows corresponding English names of Chinese Names in Figure 6.
In the case, totally 22 provinces are extracted in all fuel cell
patents. The graph clustering result is shown in figure 7. The
biggest node in the picture is Shanghai, which means the research
strength of Shanghai province is the strongest one in China. While
the smallest node is Hebei, which means Hebei province is the
weakest one on the research of fuel cell in these provinces.
In the province level, two technology competitor groups are
identified. The group with red nodes is the first group, including
10 provinces: Shanghai (311), Taiwan (152), Liaoning (127),
Jiangsu (41), Tianjin(40), Shandong(23), Shaanxi(
In the case, totally 17 countries or regions are extracted in all fuel
cell patents. The graph clustering result is shown in Figure 8.
Obviously, the biggest node in the graph is China, the granted
patent number of which is 1123. While the smallest nodes are
Denmark and Finland. The granted patent number of both country
are 3.
In the country level, four technology competitor groups are
identified, containing 16 countries and regional organizations.
The group with red node color represents the first group,
including seven countries and regional organizations: China
(1123), Germany (58), Britain (28), France (16), EPO (
EPO
In the paper, a graph clustering algorithm is used to obtain technology competitor group analysis based on IPC. The proposed method consists of four stages. First, the clustering level is determined. There are three levels for selected, i.e. institute, province and country. Second, the numbers of patents are counted under each IPC for each object (competitor) in the selected level. Third, each object is expressed with a vector, the attributes of which are IPC classification codes, and the value of each attribute is corresponding patent count. Fourth, technology similarities are computed between each pair of competitors. Finally, Linlog algorithm is used to cluster competitors into groups and display them in a graph to improve the confidence of analysis results. Experimental results on fuel cell demonstrate the effectiveness of the proposed method.
This work is partially supported by National Natural Science Foundation of China (Project 71473237), and partially supported by the Key Work Project of Institute of Scientific and Technical Information of China (ISTIC) (ZD2014-7-1). Authors are grateful to the National Natural Science Foundation of China and the Ministry of Science and Technology of China for financial support to carry out this work. on Advances in Social Network Analysis and Mining (ASONAM).