Code summarization is essential for enhancing the efficiency of software development, enabling developers to swiftly comprehend and maintain software projects. Recent efforts utilizing large language models (LLMs) for generating precise code summaries have shown promising performance, primarily due to their advanced generative capabilities. LLMs that employ continuous prompting techniques can explore a broader problem space, potentially unlocking greater capabilities. However, they also present specific challenges, particularly in aligning with task-specific situations—a strength of discrete prompts. Additionally, the inherent differences between programming languages and natural languages can complicate comprehension for LLMs, impacting the accuracy and relevance of the summaries in complex programming scenarios. These challenges may result in outputs that do not align with actual task needs, underscoring the necessity for further research to enhance the effectiveness of LLMs in code summarization. To address these limitations, we propose an enhanced prompting framework for Code Summarization with Large Language Models(EP4CS). Firstly, we design \textit{\textbf{Mapper}}, which undergoes pre-training on code corpora and facilitates the optimization and updating of prompt vectors based on the outputs of LLMs. Additionally, we developed a \textit{\textbf{Struct-Agent}} that enables LLMs to more accurately interpret the complex semantic structures of programming languages by in-depth analysis of their syntax and structural characteristics. Experimental results indicate that, compared to existing baseline methods, our enhanced prompting learning framework significantly improves performance while maintaining the same parameter scale. Specifically, our framework improves scores by 4.45%, 3.77%, and 10.32% on the standard machine translation evaluation metrics BLEU, METEOR, and ROUGE-L, respectively.