A patent quality evaluation model based on ALBERT and BiGRU

Yijiang Zhang; Shengnan Zhang; Jinyu Mu

doi:10.1117/12.3031032

19 July 2024 A patent quality evaluation model based on ALBERT and BiGRU

Yijiang Zhang, Shengnan Zhang, Jinyu Mu

Proceedings Volume 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024); 131818L (2024) https://doi.org/10.1117/12.3031032
Event: Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 2024, Beijing, China

Abstract

Accurately and efficiently evaluating patent quality is an important issue in the field of patents, demanding high-quality methods for patent assessment. This paper investigates quality evaluation indicators and patent quantification and proposes a patent quality assessment model based on the ALBERT-BiGRU network. Firstly, a patent quality evaluation indicator system is constructed, and the numerical indicators of patents are quantified. By integrating numerical indicators and text summaries, the patent evaluation model, ALBERT-BiGRU, is developed and trained and tested on a patent dataset with patent grade labels. The experimental results achieve an accuracy of 80.8%. This approach addresses the existing research gap where many methods overlook the textual features of patents. The proposed solution significantly improves the effectiveness of patent quality evaluation, providing a new perspective and approach for patent protection and intellectual property management.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yijiang Zhang, Shengnan Zhang, and Jinyu Mu "A patent quality evaluation model based on ALBERT and BiGRU", Proc. SPIE 13181, Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024), 131818L (19 July 2024); https://doi.org/10.1117/12.3031032

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available