Article Details

Abstract

In order to improve the intelligence level of engineering construction quality inspection in offshore oil industry, a quality problem classification algorithm based on Chinese pre-training model of Chinese-BERT and BiLSTM is proposed. Chinese-BERT model can better extract Chinese text features and improve the accuracy of text vector semantic representation by using Chinese pre-training, while BiLSTM further extracts key information from Chinese-BERT feature vectors. The validity of the model is verified in real data and the results show that the proposed model outperforms other comparative models in terms of classification performance, and it can effectively solve quality problem classification problems.

Keywords

offshore oil industry; quality problem; text classification; Chinese-BERT; BiLSTM

References

1. [1] CAHYANI D E，PATASIK I. Performance Comparison of TF-IDF and Word2Vec Models for Emotion Text Classification [J].Bulletin of Electrical Engineering and Informatics，2021，10（5）：2780-2788.
2. [2] Wang Lei Research on Chinese Short Text Classification Method Based on Hybrid Neural Network [D]. Hangzhou: Zhejiang University of Technology, 2019
3. [3] Wang Tiejun, Yan Yue, Guo Xiaoran, etc Tangka question classification model integrating multi-scale CNN and bidirectional LSTM [J]. Science, Technology and Engineering, 2024, 24 (22): 9490-9497
4. [4] BAHDANAU D，CHO K，BENGIO Y. Neural Machine Translation by Jointly Learning to Align and Translate [J/OL].arXiv:1409.0473 [cs.CL].[2024-10-03].https://arxiv.org/abs/1409.0473?context=stat.ML.
5. [5] LI Z，XU H，ZHANG Y，et al. Hierarchical Attention Networks for Hyperspectral Image Classification [C]//MIPPR 2019: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications.Wuhan：SPIE，2020：114320D.https://doi.org/10.1117/12.2538278.
6. [6] SHEM TOV E，SIPPER M，ELYASAF A. BERT Mutation: Deep Transformer Model for Masked Uniform Mutation in Genetic Programming [J].Mathematics，2025，13（5）：779-779.
7. [7] CUI Y，CHE W，LIU T，et al. Pre-Training with Whole Word Masking for Chinese BERT [J].IEEE/ACM Transactions on Audio, Speech, and Language Processing，2021，29：3504-3514.
8. [8] Anrui, Chen Hailong, Aisiyu, etc Research on Aerospace Text Classification Based on BERT-LSTM Model [J]. Journal of Harbin Institute of Technology, 2024, 29 (4): 40-49
9. [9] Huang Yuan, Dai Xiaohong, Huang Weijian, etc Text classification based on A-BiLSTM and CNN [J]. Computer Engineering and Design, 2024, 45 (5): 1428-1434
10. [10] DUAN S，ZHAO H. Attention Is All You Need for Chinese Word Segmentation [C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing （EMNLP）.Association for Computational Linguistics，2020：3862-3872.
11. [11] Chen Xiaojiang, Yang Xiaoqi, Chen Guanghao, etc Low time complexity short text classification using a combination of BERT and width learning [J]. Journal of Shandong University: Engineering Edition, 2024, 54 (4): 51-58+66
12. [12] DU J，VONG C M，CHEN C L P. Novel Efficient RNN and LSTM-Like Architectures: Recurrent and Gated Broad Learning Systems and Their Applications for Text Classification [J].IEEE Transactions on Cybernetics，2020：1-12.
13. [13] Hao Chao, Qiu Hangping, Sun Yi, etc Research progress on multi label text classification [J]. Computer Engineering and Applications, 2021, 57 (10): 48-56
14. [14] YOGATAMA D，DYER C，LING W，et al. Generative and Discriminative Text Classification with Recurrent Neural Networks [J/OL].arXiv:1703.01898 [stat.ML].[2024-09-27].https://arxiv.org/abs/1703.01898?context=cs.CL.
15. [15] Zheng Chengyu, Wang Xin, Wang Ting, etc Chinese Short Text Classification Algorithm Based on Stacking Bert Ensemble Learning [J]. Science, Technology and Engineering, 2022, 22 (10): 4033-4038
16. [16] Dai Linlin, Zhang Chaoqun, Tang Weidong, etc A hierarchical multi label text classification model integrating contrastive learning and BERT [J]. Computer Engineering and Design, 2024, 45 (10): 3111-3119

Funding

National Key Research and Development Program (2022YFC2806100)

About the authors

Cai Yuhua (1992-), male, Han nationality, from Wen'an, Hebei, engineer, undergraduate, research direction: quality supervision; An Xinpeng (1999-), male, Han ethnicity, from Zibo, Shandong, is currently pursuing a master's degree in computer technology; Corresponding author: Ma Yongjun (1970-), male, Han ethnicity, from Rizhao, Shandong, professor, PhD, research direction: machine learning.