Resource Optimization Configuration Method for Communication Engineering Projects Based on Large Language Models

Traditional methods for resource optimization configuration in communication engineering projects suffer from several limitations: they require precise mathematical modeling, struggle with qualitative constraints, and produce results lacking interpretability. This paper proposes a resource optimization configuration framework based on large language models (LLMs). The framework comprises four core modules—requirement understanding, constraint parsing, solution generation, and result interpretation—leveraging the natural language understanding capability of LLMs to achieve end-to-end transformation from natural language requirement descriptions to interpretable optimization solutions. Experiments on simulated data center construction projects demonstrate that, compared with traditional methods, the proposed framework improves resource utilization by approximately 15%, constraint satisfaction rate by approximately 20%, and can effectively handle qualitative constraints. This study provides a new technical pathway for the intelligent transformation of communication engineering project management.