Academic Journal of Computing & Information Science, 2024, 7(1); doi: 10.25236/AJCIS.2024.070112.
Xiaoang Chen1, Xin Tong1, Hailun Lin2, Yunfei Xing1
1School of Information Network Security, People's Public Security University of China, Beijing, China
2Institute of Information Engineering, CAS, Beijing, China
At present, the public security department has a large number of case records, which contain information such as the alarm people, the time of the crime, the place of the crime, the modus operandi, the carrier involved, and the amount of money involved. Maximizing the use of this information is one of the key factors for the police to quickly solve the case and prevent crime. Using information extraction[1] technology to automatically classify police information and extract entities from case records can not only improve the efficiency of information analysis and enable the police to clarify the context of the case more quickly, but also have more significance for the further use of these information.
Deep learning, Pre training language model, Alarm entity identification, Bert, Bilstm, CRF
Xiaoang Chen, Xin Tong, Hailun Lin, Yunfei Xing. Entity Recognition Method for Key Information of Police Records Based on Bert-Bilstm-Selfatt-Crf. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 1: 78-85. https://doi.org/10.25236/AJCIS.2024.070112.
[1] Liu Pengbo, Che Haiyan, Chen Wei. Overview of knowledge extraction technology [J]. computer application research, 2010 (9): 3222-3226
[2] Luo Dongmei, Liu Ruijun, Lin Xiping. Application of artificial intelligence language processing technology in unstructured case data [J]. Computer system applications, 2021,30 (04): 234-240
[3] DENGL, LIUY. Deep learning in natural language processing [M]. Berlin: Springer, 2018.
[4] He Y,Wu D,Beyazit E, et al. Supervised data synthesizing and evolving a framework for real-world trafficcrash severity classification [C] // IEEE. 2018 IEEE 30thInternational Conference on Tools with Artificial Intelligence (ICTAI).New York: IEEE,2018: 163-170.
[5] Nadeau D, Sekine S. A Survey of Named Entity Recognition and Classification [J]. Lingvisticae Investigationes, 2007, 30(1):3-26.
[6] Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding [J]. arXiv preprint arXiv, 2018:1810.04805.
[7] SundermeyerM, SchlüterR, NeyH. Lstm Neural Networks for Language Modeling [C]. Thirteenth Annual Conference of the International Speech Communication Association, United States, 2012: 682-697.
[8] Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Alignand Translate [J].Computer Science, 2014, 18(10):475-489.
[9] Charles A, et al. Conditional Random Fields: Factorized Probabilistic Models for Labeling and Segmenting Sequence Data [J]. Journal of Machine Learning Research, 2007, 8(14):642-661.