Abstract
With the development of industry and technology innovation in China, the number of patent applications in the field of machinery has been increasing year by year. Mechanical patents contain rich and latest technical and legal information. The mining of mechanical patents play an important practical role. In knowledge graph construction and infringement judgment for mechanical patents, extracting the technology and efficacy is an important step. In this paper, we propose a model combining bidirectional long and short-term memory neural network and conditional random field to achieve the technology and efficacy extraction from mechanical patents abstract texts. The model in this paper achieves an accuracy rate of 94.31%, a recall rate of 94.34%, and an F1 value of 94.31%. The results show that the model in this paper can accurately extract the technology and efficacy of patents in the mechanical field.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ma, J., Zhang, B., Zhang, S., Liu, S.: Named entity recognition of new energy vehicles based on active MCNN-SCRF. Comput. Eng. Appl. 55(07), 23–29 (2019)
Qu, D., Yang, T., Zhu, Y., Hu, K.: Research on entity extraction of four diagnosis information of BiGRU-CRF lung cancer medical case based on word. Mod. Tradit. Chin. Med. Materia Medica World Sci. Technol. 23(09), 3118–3125 (2021)
Shi, Z., Ma, Y., Zhao, F., Ma, B.: Chinese entity recognition based on CNN head transformer encoder. Comput. Eng. 48(10), 1–10 (2022)
Saad, F., Aras, H., Hackl-Sommer, R.: Improving named entity recognition for biomedical and patent data using bi-LSTM deep neural network models. In: Métais, E., Meziane, F., Horacek, H., Cimiano, P. (eds.) NLDB 2020. LNCS, vol. 12089, pp. 25–36. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-51310-8_3
Yu, H., Huang, H., Yu, Z., Tan, X., Lu, S.: Entity recognition of government official documents based on BiLSTM-CRF. Program. Skills Maint., 119–121 (2022)
Yang, Y., Li, Y., Zhong, X., Xu, L.: Named entity recognition of TCM medical records based on BiLSTM-CRF. Inf. Tradit. Chin. Med. 38(11), 15–21 (2021)
Deng, N., Fu, H., Chen, X.: Named entity recognition of traditional Chinese medicine patents based on BiLSTM-CRF. Wirel. Commun. Mob. Comput. 2021, 1–12 (2021)
Lafferty, J., Mccallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th International Conference on Machine Learning, pp. 282–289 (2001)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Yang, P., Xie, Z.: Research on entity identification in judicial field based on BiLSTM-CRF. Mod. Comput. 38(11), 3–8 (2020)
Zhao, L.: Research on a method of named entity recognition based on BiLSTM-CRF. Comput. Inf. Technol. 29(02), 8–11+19 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cui, R., Deng, N., Zheng, C. (2023). Technology and Efficacy Extraction of Mechanical Patents Based on BiLSTM-CRF. In: Barolli, L. (eds) Advances in Internet, Data & Web Technologies. EIDWT 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 161. Springer, Cham. https://doi.org/10.1007/978-3-031-26281-4_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-26281-4_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26280-7
Online ISBN: 978-3-031-26281-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)