HDBSCAN-based semantic clustering model in classifying incidents on security and environmental conservation management

In social production and daily life, safety production plays a crucial role. The management of safety and environmental conservation generates a significant number of documents. Traditional manual methods in processing records involve inherent drawbacks such as subjectivity, low efficiency, and untimely warnings. In recent years, natural language processing (NLP) has gained significant attention and application in processing large volumes of documents. Therefore, this research proposes a semantic clustering model for identifying incidents related to security and environmental conservation management. The relation-enhanced attention mechanism and noise adversarial training were introduced during the pre-training of the corpus based on the records of security and environmental conservation management, aiming to generate a high-dimensional understanding of the text in the specific domain. A novel high-density spatial hierarchical clustering algorithm (HDBSCAN) was applied in clustering analysis on the text embedding, achieving effective semantic hierarchical clustering of records. The results indicate that this method can effectively capture semantics within the dataset. In comparison to traditional clustering methods such as K-Means and DBSCAN, HDBSCAN demonstrates superior performance in terms of clustering effectiveness and stability. Through this approach, this research aims to implement automatic classification of incidents in safety and environmental conservation management based on records, facilitating the safeguarding of social production and daily life. This research provides a new perspective and tool for the automated analysis of environmental events, with significant practical implications for environmental safety management.