| Summary: | 碩士 === 中華大學 === 營建管理學系碩士班 === 99 === As the advent of creative economy era, more and more organizations have realized the importance of technology innovation to their prodcut competitiveness in the market. Among the many technological repositories, patent databases have stored the most advanced and economically valuable technological information. Such information is not only useful for planning the technological development strategies, but also a precious source of technological know-hows, which can be adopted in developing innovative technologies. However, due to background differences in training and specialty, technology innovators usually construct the technology’s function model differently. As a result, to achieve a consistent and stable result in model the function model of a patented technology is an important issue in effective utilization of patent database. To tackle the above problem, the current research has proposed a text mining method for the automated analysis of the function model for a patent. Not only the model for automated analysis of function model, but also a prototype computer program is developed to test the feasibility of the proposed method. After a case study of fourteen patents, it is found that the proposed method is able to improve the analysis speed by 56.2% and achieve a analysis accuracy rate from 84.6~86% (using 100% as perfect accuracy) while compared with the results of manual analysis method. It is concluded that the proposed computer aided text mining method for patent function model analysis is able improve the efficiency and consistency of the result with a high accuracy. The proposed method can be employed by the innovators of construction and other technology domains in analyzing the patented technology documents.
|
|---|
