ABSTRACT
Aiming at the problem that the existing high-value patent recognition methods rely on experts' subjective experience judgment and the patent recognition model cannot fully extract the feature information of the patent text, which leads to the unsatisfactory recognition efficiency of high-value patents, we propose a high-value patent identification method using deep learning based language understanding:MBCA.The experimental results in the chinese text classification dataset from Fudan University show that the accuracy of this method has improved by 1.59% compared with the optimal baseline method, and the empirical results in chinese patent dataset of lithography field show that the accuracy of this method has improved by 3.42% compared with the optimal baseline method, indicating that this method can fully improve the identification performance of high-value patents, which can provide an effective way for the intelligent identification of high-value patents and promote the effective transformation of patents, and has practical application value.
- Chunjuan Luan, Jing Bai. 2021.A Comparative Study on Patent Quality of Chinese Academic lnstitutions, Chinese Enterprises andAmerican Academic Institutions.Science and Technology Management Research.41(10):136-142.Google Scholar
- Sipei Wang,Tao Han.2020.Research on Potential High Value Patent Prediction Method Based on Random Forest Algorithm.Information Science.38(05):120-125.Google Scholar
- Yihui Qiu,Chiyu Zhang,Shuixuan Chen.2017.Research of Patent-value Assessment Indictor SystemBased on Classification and Regression Tree Algorithm.Journal of Xiamen University (Natural Science).56(02):244-251.Google Scholar
- MIKOLOV T, CHEN K, CORRADO G, 2013.Efficient estimation of word representations in vector space.Computer Science,1301,3781. https://doi.org/10.48550/arXiv. 1301.3781.Google ScholarCross Ref
- Shaoping Fan,Yuxuan Zhao,Xinying An.et al.2021.Classification Model for Medical Entity Relations with Convolutional Neural Network.Data Analysis and Knowledge Discovery. 5(09):75-84.Google Scholar
- SINGH U,KEDAS S,PRASABTH S,et al.2020 Design of a recurrent neural network model for machine reading comprehension.Procedia Computer Science.167:1791-1800.https://doi. org/10.1016/j.procs.2020.03.388.Google Scholar
- Dai J,Chen C,Li Y.2019. A Backdoor Attack Against LSTM-Based Text Classification Systems. IEEE Access,7:138872-138878.https://doi.org/10.1109/ACCESS.2019.2941376.Google ScholarCross Ref
- DEVIN J,CHANG M W,LEE K.et al.2019.BERT:Pre-training of deep bidirectional transformers for language understanding.Proceedings of the 2019 Conference of the North American Chapter of the Assocation for Computational Linguistics:Human Language Technologies.Stroudsburg,Minneapolis,USA,Jun.2-7,2019.Stroudsburg.2019:4171- 4186.https://doi.org/10.48550/arXiv.1810.04805.Google ScholarCross Ref
- JIANG C Q,ZHOU Y R,CHEN B. 2023.Mining semantic features in patent text for financial distress prediction.Technological Forecasting & Social Change.190(2023):122450.https://doi.org/10.1016/j.techfore.2023.122450.Google ScholarCross Ref
- XIANG M H,FU D,LV K. 2023.Identifying and predicting trends of disruptive technologies:an empirical study based on text mining and time series forecasting.Sustainability.15(6):5412-5412.https://doi.org/10.3390/su15065412.Google ScholarCross Ref
Index Terms
- MBCA:Identification of high-value patents using deep learning based language understanding
Recommendations
Capturing the economic value of triadic patents
This study provides a comprehensive analysis of patent family characteristics of triadic patents. We test specific features of triadic patent families to highlight common correlation patterns between patent value, as measured by patent forward citation ...
Mining High-Value Patents Leveraging Massive Patent Data
Algorithms and Architectures for Parallel ProcessingAbstractA patent is an inventor’s way of protecting its intellectual property. In recent years, the trend of patent filings has become more prevalent than ever as commercial competition among firms has intensified. While patents have promoted our society ...
Software patents: a replication study
OpenSym '15: Proceedings of the 11th International Symposium on Open CollaborationPrevious research has documented the legal and economic aspects of software patents. To study the evolution in the granting of software patents we reproduced and extended part of the empirical study on software patents conducted by Bessen and Hunt. The ...
Comments