WordNet: a lexical database for English
Communications of the ACM
Artificial Intelligence - Special volume on empirical methods
Algorithm 447: efficient algorithms for graph manipulation
Communications of the ACM
ConceptNet — A Practical Commonsense Reasoning Tool-Kit
BT Technology Journal
A patent document retrieval system addressing both semantic and syntactic properties
PATENT '03 Proceedings of the ACL-2003 workshop on Patent corpus processing - Volume 20
Text mining techniques for patent analysis
Information Processing and Management: an International Journal
Identification of promising patents for technology transfers using TRIZ evolution trends
Expert Systems with Applications: An International Journal
A patent intelligence system for strategic technology planning
Expert Systems with Applications: An International Journal
Hi-index | 0.01 |
This paper suggests a method for Subject---Action---Object (SAO) network analysis of patents for technology trends identification by using the concept of function. The proposed method solves the shortcoming of the keyword-based approach to identification of technology trends, i.e., that it cannot represent how technologies are used or for what purpose. The concept of function provides information on how a technology is used and how it interacts with other technologies; the keyword-based approach does not provide such information. The proposed method uses an SAO model and represents "key concept" instead of "key word". We present a procedure that formulates an SAO network by using SAO models extracted from patent documents, and a method that applies actor network theory to analyze technology implications of the SAO network. To demonstrate the effectiveness of the SAO network this paper presents a case study of patents related to Polymer Electrolyte Membrane technology in Proton Exchange Membrane Fuel Cells.