Identification of promising patents for technology transfers using TRIZ evolution trends

• Published in: Expert systems with applications Vol. 40; no. 2; pp. 736 - 743
• Main Authors: Park, Hyunseok, Ree, Jason Jihoon, Kim, Kwangsoo
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01.02.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Criteria; Economics; Evolution; Exact sciences and technology; Expert systems; Firm modelling; General aspects; Information systems. Data bases; Memory organisation. Data processing; Open innovation; Operational research and scientific management; Operational research. Management science; Patent analysis; Patent evaluation; Patent mining; SAO; Software; Speech and sound recognition and synthesis. Linguistics; Subject–Action–Object; Tasks; Technology evaluation; Technology transaction; Technology transfer; Text mining; Trends; Wind turbines; Technology transaction; Text mining; SAO; Patent evaluation; Patent mining; Subject–Action–Object; Technology evaluation; Open innovation; Patent analysis; Performance evaluation; Very large databases; Wind generator; Data mining; Innovation; Systems engineering; Technology transfer; Object oriented; Advanced technology; Patents; Text; Transaction processing; High value; Organizational models; Intellectual property; Open systems; Patent rights; Subject-Action-Object
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2012.08.008

► We propose a new method to identify promising patents for technology transfer. ► We adopt TRIZ trends as criteria to evaluate technologies in patents. ► TRIZ trends can be classified by considering characteristics of lifecycle stage. ► We adopt SAO-based text mining to analyze big patent data automatically. ► We verified the method by applying it to floating wind turbine technology. Technology transfer is one of the most important mechanisms for acquiring knowledge from external sources to secure innovative and advanced technologies in high-tech industries. For successful technology transfer, identification of high-value technologies is a fundamental task. In particular, identifying future promising patents is important, because most technology transfer transactions are aimed at acquiring technologies for future uses. This paper proposes a new approach to identification of promising patents for technology transfer. We adopted TRIZ evolution trends as criteria to evaluate technologies in patents, and Subject–Action–Object (SAO)-based text-mining technique to deal with big patent data and analyze them automatically. The applicability of the proposed method was verified by applying it to technologies related to floating wind turbines.