Research on a Framework for Chinese Argot Recognition and Interpretation by Integrating Improved MECT Models.

In underground industries, practitioners frequently employ argots to communicate discreetly and evade surveillance by investigative agencies. Proposing an innovative approach using word vectors and large language models, we aim to decipher and understand the myriad of argots in these industries, providing crucial technical support for law enforcement to detect and combat illicit activities. Specifically, positional differences in semantic space distinguish argots, and pre-trained language models' corpora are crucial for interpreting them. Expanding on these concepts, the article assesses the semantic coherence of word vectors in the semantic space based on the concept of information entropy. Simultaneously, we devised a labeled argot dataset, MNGG, and developed an argot recognition framework named CSRMECT, along with an argot interpretation framework called LLMResolve. These frameworks leverage the MECT model, the large language model, prompt engineering, and the DBSCAN clustering algorithm. Experimental results demonstrate that the CSRMECT framework outperforms the current optimal model by 10% in terms of the F1 value for argot recognition on the MNGG dataset, while the LLMResolve framework achieves a 4% higher accuracy in interpretation compared to the current optimal model.The related experiments undertaken also indicate a potential correlation between vector information entropy and model performance.

A Framework for Analyzing Fraud Risk Warning and Interference Effects by Fusing Multivariate Heterogeneous Data: A Bayesian Belief Network.

In the construction of a telecom-fraud risk warning and intervention-effect prediction model, how to apply multivariate heterogeneous data to the front-end prevention and management of telecommunication network fraud has become one of the focuses of this research. The Bayesian network-based fraud risk warning and intervention model was designed by taking into account existing data accumulation, the related literature, and expert knowledge. The initial structure of the model was improved by utilizing City S as an application example, and a telecom-fraud analysis and warning framework was proposed by incorporating telecom-fraud mapping. After the evaluation in this paper, the model shows that age has a maximum sensitivity of 13.5% to telecom-fraud losses; anti-fraud propaganda can reduce the probability of losses above 300,000 yuan by 2%; and the overall telecom-fraud losses show that more occur in the summer and less occur in the autumn, and that the Double 11 period and other special time points are prominent. The model in this paper has good application value in the real-world field, and the analysis of the early warning framework can provide decision support for the police and the community to identify the groups, locations, and spatial and temporal environments prone to fraud, to combat propaganda and provide a timely warning to stop losses.