|
|
基于多模态融合的智慧街镇基层治理平台
|
Abstract:
数字技术和人工智能技术赋能基层治理是适应基层政府数字化转型发展的必然要求，也是提升基层治理能力现代化水平的重要途径。本文提出了一种基于多模态数据融合的智慧街镇基层治理平台，旨在通过整合多源数据，构建高效、智能的基层治理新模式。该平台以多模态融合的基层治理大模型为底座，结合大小模型协同技术，实现了事件的自动填报、精准派发和智能处置，有效提升了基层治理的自动化和智能化水平。通过多源设备联动和应用迭代，平台推动了基层治理从模糊到精准、从被动应对到主动研判的转变，为街镇基层治理提供了有力的技术支撑。
Empowering grassroots governance with digital technology and artificial intelligence technology is an inevitable requirement for adapting to the digital transformation and development of grassroots governments, and is also an important way to improve the modernization level of grassroots governance capabilities. This paper proposes a smart street and town management platform based on multimodal data fusion, aiming to build an efficient and intelligent new model of grassroots governance by integrating multi-source data. The platform is based on a large model of grassroots governance with multimodal fusion, and combines large and small model collaboration technology to achieve automatic reporting, accurate distribution and intelligent handling of events, effectively improving the automation and intelligence level of grassroots governance. Through the linkage of multi-source equipment and application iteration, the platform has promoted the transformation of grassroots governance from fuzzy to precise, from passive response to active research and judgment, and provided strong technical support for grassroots governance in streets and towns.
| [1] | 王海侠. 基层社会治理存在的十大突出问题[EB/OL]. 经济导刊. https://www.jingjidaokan.com/icms/null/null/ns:LHQ6LGY6LGM6MmM5ZTg0NzU4Y2EwZTU4YjAxOGU5ZGExY2MwZjAwNDIscDosYTosbTo=/show.vsml, 2025-03-05. |
| [2] | 求是网. 以数字技术赋能基层治理[EB/OL]. http://www.qstheory.cn/qshyjx/2024-09/18/c_1130202758.htm, 2025-03-05. |
| [3] | 司海燕. 推动人工智能赋能基层治理[EB/OL]. 新华日报. https://theory.jschina.com.cn/sxzk/xl/zxtj/202502/t20250226_8460582.shtml, 2025-03-08. |
| [4] | 吴锦良. “枫桥经验”演进与基层治理创新[J]. 浙江社会科学, 2010(7): 43-49, 29, 126. |
| [5] | 中华人民共和国中央人民政府. 谱写基层善治新篇章——坚持和发展新时代“枫桥经验”综述[EB/OL]. https://www.gov.cn/yaowen/liebiao/202311/content_6913690.htm, 2025-03-08. |
| [6] | 冯献, 李瑾, 崔凯. 乡村治理数字化: 现状, 需求与对策研究[J]. 电子政务, 2020(6): 73-85. |
| [7] | 李友梅, 黄晓春. 上海城市数字化治理现状及推进思路[J]. 科学发展, 2022(12): 5-13. |
| [8] | 银江技术股份有限公司. 镇街大脑[EB/OL]. http://www.enjoyor.net/solution_judicial.html, 2025-03-05. |
| [9] | 海淀统战. 海淀: 深化“大家商量着办”践行“围着基层转”共建美好家园[EB/OL]. https://paper.people.com.cn/rmrb/pc/content/202505/22/content_30074711.html, 2024-09-20. |
| [10] | 任泽裕, 王振超, 柯尊旺, 等. 多模态数据融合综述[J]. 计算机工程与应用, 2021, 57(18): 49-64. |
| [11] | Huawei Technologies Co., Ltd. (2022) Huawei MindSpore AI Development Framework. In: Huawei Technologies Co., Ltd., Eds., Artificial Intelligence Technology, Springer, 137-162. https://doi.org/10.1007/978-981-19-2879-6_5 |
| [12] | Tong, Z., Du, N., Song, X. and Wang, X. (2021) Study on MindSpore Deep Learning Framework. 2021 17th International Conference on Computational Intelligence and Security (CIS), Chengdu, 19-22 November 2021, 183-186. https://doi.org/10.1109/cis54983.2021.00046 |
| [13] | 王永威, 沈弢, 张圣宇, 等. 大小模型端云协同进化技术进展[J]. 中国图象图形学报, 2024, 29(6): 1510-1534. |
| [14] | 范建, 刘京, 武建双, 等. 基于人工智能, 大数据技术在智慧城市基层治理的应用与分析[J]. 人工智能与机器人研究, 2025(14): 427-438. |
| [15] | Zhang, D., Yu, Y., Dong, J., Li, C., Su, D., Chu, C., et al. (2024) MM-LLMs: Recent Advances in MultiModal Large Language Models. Findings of the Association for Computational Linguistics ACL 2024, Bangkok, 11-16 August 2024, 12401-12430. https://doi.org/10.18653/v1/2024.findings-acl.738 |
| [16] | Wu, J., Gan, W., Chen, Z., Wan, S. and Yu, P.S. (2023) Multimodal Large Language Models: A Survey. 2023 IEEE International Conference on Big Data (BigData), Sorrento, 15-18 December 2023, 2247-2256. https://doi.org/10.1109/bigdata59044.2023.10386743 |
| [17] | Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al. (2020) An Image Is Worth 16 × 16 Words: Transformers for Image Recognition at Scale. arXiv: 2010.11929. |
| [18] | Wang, Y., Huang, R., Song, S., et al. (2021) Not All Images Are Worth 16 × 16 Words: Dynamic Transformers for Efficient Image Recognition. Advances in Neural Information Processing Systems, 34, 11960-11973. |
| [19] | Masoudnia, S. and Ebrahimpour, R. (2012) Mixture of Experts: A Literature Survey. Artificial Intelligence Review, 42, 275-293. https://doi.org/10.1007/s10462-012-9338-y |
| [20] | Xue, F., Zheng, Z., Fu, Y., et al. (2024) Openmoe: An Early Effort on Open Mixture-Of-Experts Language Models. arXiv: 2402.01739. |
| [21] | Wu, X., Huang, S. and Wei, F. (2024) Mixture of Lora Experts. arXiv: 2404.13628. |
| [22] | Mao, Y., Ge, Y., Fan, Y., Xu, W., Mi, Y., Hu, Z., et al. (2024) A Survey on Lora of Large Language Models. Frontiers of Computer Science, 19, Article No. 197605. https://doi.org/10.1007/s11704-024-40663-9 |
| [23] | Chen, J., Lin, H., Han, X. and Sun, L. (2024) Benchmarking Large Language Models in Retrieval-Augmented Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 17754-17762. https://doi.org/10.1609/aaai.v38i16.29728 |
| [24] | Mahajan, Y., Freestone, M., Aakur, S., et al. (2025) Revisiting Word Embeddings in the LLM Era. arXiv: 2502.19607. |
| [25] | Jiang, T., Song, M., Zhang, Z., et al. (2024) E5-v: Universal Embeddings with Multimodal Large Language Models. arXiv: 2407.12580. |
| [26] | Guo, W., Wang, J. and Wang, S. (2019) Deep Multimodal Representation Learning: A Survey. IEEE Access, 7, 63373-63394. https://doi.org/10.1109/access.2019.2916887 |
| [27] | Wang, J., Yi, X., Guo, R., Jin, H., Xu, P., Li, S., et al. (2021) Milvus: A Purpose-Built Vector Data Management System. Proceedings of the 2021 International Conference on Management of Data, 20-25 June 2021, 2614-2627. https://doi.org/10.1145/3448016.3457550 |
