KLCBL: An Improved Police Incident Classification Model
It addresses classification challenges for grassroots police agencies, enhancing informatization and resource allocation, with incremental improvements in method integration.
The paper tackled the problem of inefficient police incident classification by proposing KLCBL, a multichannel neural network model that integrates KAN, LERT, CNN, and BiLSTM, achieving 91.9% accuracy on real data and outperforming baselines.
Police incident data is crucial for public security intelligence, yet grassroots agencies struggle with efficient classification due to manual inefficiency and automated system limitations, especially in telecom and online fraud cases. This research proposes a multichannel neural network model, KLCBL, integrating Kolmogorov-Arnold Networks (KAN), a linguistically enhanced text preprocessing approach (LERT), Convolutional Neural Network (CNN), and Bidirectional Long Short-Term Memory (BiLSTM) for police incident classification. Evaluated with real data, KLCBL achieved 91.9% accuracy, outperforming baseline models. The model addresses classification challenges, enhances police informatization, improves resource allocation, and offers broad applicability to other classification tasks.