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
Introduction to the special issue on patent processing
Information Processing and Management: an International Journal
Grouping of TRIZ Inventive Principles to facilitate automatic patent classification
Expert Systems with Applications: An International Journal
Expert Systems with Applications: An International Journal
The Stanford typed dependencies representation
CrossParser '08 Coling 2008: Proceedings of the workshop on Cross-Framework and Cross-Domain Parser Evaluation
A patent examining expert system using pattern recognition
Expert Systems with Applications: An International Journal
Identification of trends from patents using self-organizing maps
Expert Systems with Applications: An International Journal
Analyzing interdisciplinarity of technology fusion using knowledge flows of patents
Expert Systems with Applications: An International Journal
Hi-index | 12.05 |
Patents are an up-to-date and reliable knowledge source of innovative technologies, and therefore patent analysis has been a vital tool for understanding technological trends and formulating technology strategies. One method of patent analysis is citation-based patent analysis. However, one criticism of the citation-based approach is that it may underestimate new patents because they tend to be less cited. This problem gets worse in fast-moving industries where technology life-cycles shorten and innovative technologies are actively patented. As a remedy, this paper proposes a property-function based patent network using an analysis of patent contents. Properties and functions as the innovation concepts of a system can be extracted using grammatical analysis of patent text. First, this paper represents each patent into a matrix codifying properties, functions and their co-occurrences, and then it constructs a patent network by measuring patent similarities. As a result, the proposed network reveals the internal relationships among patents in a given patent set that many new patents. Furthermore, using several analysis indices, this paper suggests a way to identify technological implications from the network such as the technological importance of new patents, the technological capability of applicants with new patents and the pace of technological progress of new patents. The proposed method is illustrated using silicon-based thin film solar cells. We expect that the proposed method can be incorporated into R&D planning processes to assist researchers and R&D policy makers to identify technological implications related to new patents in fast-moving industries.