ABSTRACT
Analyzing technical contradictions according to TRIZ theory can help us solve the innovative and inventive problems effectively. However, the existing analysis and extraction methods of technical contradiction mainly rely on manual rule formulation and make less use of the semantics information, which limits the improvement of the efficiency and accuracy of the extraction. Consequently, this paper proposed an extraction method based on patent semantic space mapping. It adopted the Doc2Vec model to construct the semantic space of the patent text and trained extraction model by using feature vectors covering rich semantic relationships, which could make us recognize the technical contradictions from patents better. This paper used patent data in the automobile field as a sample to perform experiments. The accuracy of the technical contradiction recognition was improved compared with the baseline model based on rule formulation.
- Alʹtshuller, G. S. 1999. The Innovation Algorithm: TRIZ, Systematic Innovation and Technical Creativity. Technical innovation center, Inc., Worcester.Google Scholar
- Savransky, S. 2000. Engineering of Creativity. CRC Press, New York.Google ScholarCross Ref
- Orloff, M. 2012. Modern TRIZ. Springer, Berlin.Google Scholar
- He, C., Loh H. T. 2010. Pattern-oriented Associative Rule-based Patent Classification. Expert Systems with Applications, 37, 3(Mar. 2010), 2395-2404.Google Scholar
- Park, H., Ree, J. J., Kim, K. 2013. Identification of Promising Patents for Technology Transfers Using TRIZ Evolution Trends. Expert Systems with Applications, 40, 2(Feb. 2013), 736-743.Google Scholar
- Zhai, D. S., Xia, J., Zhang, J., Li Q., Luan, B. Y. 2015. Research on Construction of Technology Tree Based on Patent Feature Extraction. Journal of the China Society for Scientific and Technical Information, 34, 7(Jul. 2015), 717-724.Google Scholar
- Du, X. J., Xiong, Y., Liu, L. F., Shi, Q. 2017. Patent Knowledge Representation and Organization Based on Multi-attribute. Chinese Journal of Engineering Design, 24, 1(Jan. 2017), 1-7.Google Scholar
- Li, R., Sa, R. N., Huang, X. J. 2017. Patent Information Organization Based on TRIZ: A Case Study in the Field of New Energy Car Battery. Journal of the China Society for Scientific and Technical Information, 36, 2(Feb. 2017), 111-122.Google Scholar
- Lin, L., Rasovska, I., De, Guio R., Dubois, S. 2013. Algorithm for identifying generalised technical contradictions in experiments. Journal Européen des Systèmes Automatisés, 47, 4-8, 563-588.Google Scholar
- Montecchi, T., Russo, D. 2015. Knowledge based approach for formulating TRIZ contradictions. Procedia Engineering, 131, 451-463.Google ScholarCross Ref
- Wei, Z., Li, Q., Wang, D., Tian, Y. 2009. The Application of LT-Table in TRIZ Contradiction Resolving Process. In Growth and Development of Computer-Aided Innovation. Springer, Heidelberg, 266-275.Google Scholar
- Tseng, C. K., Chung, C. H., Dai, B. R. 2014. Classifying the TRIZ Contradiction Problem of the Patents Based on Engineering Parameters. In Technologies and Applications of Artificial Intelligence in Cham. Springer, Berlin, 344-353.Google Scholar
- Hu, Z. Y., Fang, S., Zhang, X., Wen, Y., Liang, T. 2015. Study on Personalized Semantic TRIZ. Library and Information Service, 59, 7(Jul. 2015), 121-131.Google Scholar
- Campr, M., Ježek, K. 2015. Comparing Semantic Models for Evaluating Automatic Document Summarization. In Text, Speech, and Dialogue. Springer International Publishing, Cham, 252-260.Google Scholar
- Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., Dean, J. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems. Curran Associates Inc., in Nevada, 3111-3119.Google Scholar
- Le, Q., Mikolov, T. 2014. Distributed representations of sentences and documents. In Proceedings of The 31st International Conference on Machine Learning. Journal of Machine Learning Research, Beijing, 1188-1196.Google Scholar
- Mann, D., Dewulf, S., Zlotin, B., Zusman, A. 2003. Matrix 2003: Updating the TRIZ Contradiction Matrix. CREAX Press, Belgium.Google Scholar
Recommendations
A TRIZ-based Trimming method for Patent design around
Patent design around is an effective way to walk around competitive patents and avoid patent infringement. This paper proposes a TRIZ-based Trimming method for Patent design around. The 4 stages of Patent design around include design around target ...
Patent litigation precaution method: analyzing characteristics of US litigated and non-litigated patents from 1976 to 2010
This study aims to propose an early precaution method which allows predicting probability of patent infringement as well as evaluating patent value. To obtain the purposes, a large-scale analysis on both litigated patents and non-litigated patents ...
Patent surrogate extraction and evaluation in the context of patent mapping
Patent documents contain important research results. They are often collectively analyzed and organized in a visual way to support decision making. However, they are lengthy and rich in technical ...
Comments