Ontology-based knowledge discovery and exploring technology influencers from patent data

Abstract

A patent is an important document issued by the government to protect inventions or product design. Inventions consist of mechanical structures, production processes, quality improvements of products, and so on. Generally, goods or appliances in everyday life are a result of an invention or product design that has been published in patent documents. A new invention contributes to the standard of living, improves productivity and quality, reduces production costs for industry, or delivers products with higher added value. Patent documents are considered to be excellent sources of knowledge in a particular field of technology, leading to inventions. Technology trend forecasting from patent documents depends on the subjective experience of experts. However, accumulated patent documents consist of a huge amount of text data, making it more difficult for those experts to gain knowledge precisely and promptly. Therefore, technology trend forecasting using objective methods is more feasible. There are many statistical methods applied to the patent analysis, for example, to technology overview, investment volume, and the technology life cycle. There are also data analytic methods by which patent documents can be classified, such as by technical characteristics, to support business decision-making as well as a taxonomy of concepts for knowledge representation by developing an ontology-based semantic search. The main contributions of this study were to extract knowledge from a patent relational database into two approaches; 1) Develop an ontology-based from patent data to provide an effective search for technological concepts, and 2) Explore technology influencers from patents using data analytics. We experimented with our techniques on data retrieved from the European Patent Office (EPO) website. In the first approach, the patent data was defined as terms, concepts, classes, and properties to create a patent ontology. A patent ontology consisted of the relations of each concept that were represented as an ontology map. Next, a patent database was created to integrate with the ontology map to develop an ontology-based application. The result from this stage was an ontology-based that facilitates as a recommender system. The second approach related to exploring technology influencers from patent data. The technique includes K-means clustering, text mining, and association rule mining methods. The patent data being analyzed by which the association rule mining was applied to find associative relationships among patent data, then combined with social network analysis (SNA) to further analyze technology trends. SNA provided metric measurements to explore the most influential technology as well as visualize data in various network layouts. This study demonstrated 2 approaches for knowledge discovery from patent data by which; 1) the expected output from the ontology-based will be used to support information searching for more relevant and precise information, and 2) the resultsfrom data analytics showed emerging technology clusters, their meaningful patterns, and a network structure, and suggested information for the development of technologies and inventions.