Computer Network Security Situation Assessment Integrating Least Squares Support Vector Machines and Optimized Bidirectional Long Short-Term Memory Network Algorithm

Accurately evaluating and forecasting the state of computer network security has become essential due to the rise in network threats. The study proposed a model to build a systematic computer network security situation assessment index system by combining the optimized BiLSTM (Bidirectional Long Short-Term Memory) and the least squares support vector machine. This model addresses the issues of low accuracy and lack of prediction ability with current assessment methods. And validate the model performance through a complex and dynamic dataset of 200 samples, the research results show that the least squares support vector machine model shows higher evaluation accuracy, with an average evaluation accuracy of 96.12%. The model combining the least squares support vector machine and the optimized BiLSTM is more consistent with the real situation value, with an average absolute error of about 0.05. The outcomes of the simulation indicate that the least squares support vector machine has a high degree of fitting and clearly illustrates its better scenario assessment performance. The research model's prediction of computer network security situation shows overall high results. The research results provide decision-makers with more accurate and timely intelligence support, helping them respond quickly and reduce potential security risks.