Optimization of a big data-driven public security policy and regulation Q&A system

With the rapid development of artificial intelligence technology, intelligent question answering systems have shown great potential in various fields. The public security question and answer system is an important application for providing information query and services to public security officers and the general public. However, existing systems often suffer from issues such as low accuracy, slow knowledge updates, and insufficient intelligence. In response to these issues, this article constructs a police policy and regulation Q&A system based on big data-driven and professional knowledge base. The system integrates retrieval enhanced generation technology and LoRA fine-tuning technology, effectively improving the accuracy and compliance of question answering, optimizing user experience, enhancing model efficiency and adaptability, and enhancing knowledge updating capabilities. The experimental results show that the system significantly improves the performance of police Q&A work, provides strong technical support for public security work, and promotes the intelligent and scientific development of public security work.