Add development roadmap.

@@ -471,6 +471,16 @@ We welcome all forms of contributions!
 - New features need corresponding test cases
 - Update related documentation
 
+## 🦖 Next Development Plan
+
+The system has currently completed only the first two steps of the "three-step approach": requirement input -> detailed analysis. The missing step is prediction, and directly handing this over to LLM lacks persuasiveness.
+
+<div align="center">
+<img src="static/image/banner_compressed.png" alt="banner" width="800">
+</div>
+
+Currently, after a long period of crawling and collection, we have accumulated massive data on topic popularity trends over time, trending events, and other change patterns across the entire network. We now have the conditions to develop prediction models. Our team will apply our technical reserves in time series models, graph neural networks, multimodal fusion, and other prediction model technologies to achieve truly data-driven public opinion prediction functionality.
+
 ## 📄 License
 
 This project is licensed under the [GPL-2.0 License](LICENSE). Please see the LICENSE file for details.

@@ -471,6 +471,16 @@ class DeepSearchAgent:
 - 新功能需要包含相应的测试用例
 - 更新相关文档
 
+## 🦖 下一步开发计划
+
+现在系统只完成了"三板斧"中的前两步，即：输入要求->详细分析，还缺少一步预测，直接将他继续交给LLM是不具有说服力的。
+
+<div align="center">
+<img src="static/image/banner_compressed.png" alt="banner" width="800">
+</div>
+
+目前我们经过很长一段时间的爬取收集，拥有了大量全网话题热度随时间、爆点等的变化趋势热度数据，已经具备了可以开发预测模型的条件。我们团队将运用时序模型、图神经网络、多模态融合等预测模型技术储备于此，实现真正基于数据驱动的舆情预测功能。
+
 ## 📄 许可证
 
 本项目采用 [GPL-2.0许可证](LICENSE)。详细信息请参阅LICENSE文件。