物联网应用开发与生成：从低代码到智能原生

束方磊; 刘佳伟; 李博睿; 王帅

doi:null

您当前的位置：

首页 >

文章列表页 >

物联网应用开发与生成：从低代码到智能原生

更新时间：2026-02-09

- 物联网应用开发与生成：从低代码到智能原生
- IoT Application Development and Generation: From Low-Code to AI-Native
- 物联网学报 2026年页码：1-12
- 作者机构：
  
  东南大学，江苏南京 211189
- 作者简介：
- 基金信息：
  
  国防重点实验室基金重点资助项目(6142006240401)
- DOI：
  中图分类号：
- 修回：2025-06-17，
  
  录用：2025-07-18，
  
  网络首发：2026-02-09，
- 稿件说明：
移动端阅览
束方磊,刘佳伟,李博睿等.物联网应用开发与生成：从低代码到智能原生[J].物联网学报,

SHU Fanglei,LIU Jiawei,LI Borui,et al.IoT Application Development and Generation: From Low-Code to AI-Native[J].Chinese Journal on Internet of Things,
束方磊,刘佳伟,李博睿等.物联网应用开发与生成：从低代码到智能原生[J].物联网学报, DOI：10.11959/j.issn.2096-3750..00510.

SHU Fanglei,LIU Jiawei,LI Borui,et al.IoT Application Development and Generation: From Low-Code to AI-Native[J].Chinese Journal on Internet of Things, DOI：10.11959/j.issn.2096-3750..00510.

摘要

物联网（IoT）技术通过设备、传感器和网络的互联，实现了物与物、物与人之间的智能交互和数据共享，已广泛应用于智能家居、智慧交通和工业自动化等领域。传统的物联网开发流程依赖于人工的软硬协同开发，具有较高的技术门槛。低代码开发技术则通过图形化编程界面和高度抽象的编程接口，显著降低了开发门槛，但仍存在定制化能力不足的问题。随着以大语言模型为代表的人工智能及其相关技术的成熟，使用人工智能模型将物联网应用的开发流程表征出来的“智能原生”物联网计算任务生成方式，成为物联网应用开发的新机遇。为此，本文在梳理物联网应用开发技术的发展的基础上，提出了智能原生物联网计算任务生成框架，将开发过程划分为物联网应用计算意图解析与计算规划生成两个阶段。在此基础上，本文系统性分析了智能原生物联网应用生成的关键技术和挑战，探讨了其最新研究进展，最后对其未来发展方向进行了展望。

Abstract

The Internet of Things (IoT) enables intelligent interaction and data sharing

facilitating connectivity among objects and humans. It has been widely applied in smart homes

intelligent transportation

industrial automation

etc. Traditional IoT development processes rely on manual hardware-software collaborative development

which involves a high technical barrier. Low-code development technology significantly lowers this barrier by providing graphical interfaces and highly abstracted programming APIs. Nevertheless

it still faces limitations in customization capabilities. With the maturity of artificial intelligence (AI) and related technologies represented by large language models

the "AI-native" computing task generation for IoT

which means refactoring the development process of IoT software with AI models

has emerged as a new direction for IoT application development. Therefore

on the basis of reviewing the development of software development technology for the IoT

this paper proposes an AI-native framework for generating computing tasks of IoT

which is divided into two stages: intent understanding and task planning. Based on this

this paper systematically analyzes the key technologies and challenges

provides a comprehensive review of the latest research

and finally looks forward to the future development directions of AI-native computing task generation.

关键词

Keywords

references

吴吉义 , 李文娟 , 曹健 , 等 . 智能物联网 AIoT 研究综述 [J ] . 电信科学 , 2021 , 37 ( 8 ): 1 - 17 .

WU J. Y. , LI W. J. , CAO J. , et al . ( 2021 ). A survey on the research of intelligent Internet of Things (AIoT) . Telecommunication Science , 37 ( 8 ), 1 - 17 .

智能物联网：概念、体系架构与关键技术 [J ] . 计算机学报 , 2023 ( 11 vo 46 ): 2259 - 2278 .

Intelligent Internet of Things: Concepts, System Architecture, and Key Technologies . Journal of Computer Science , 46 ( 11 ), 2259 - 2278, 2023 .

袁牧 , 张兰 , 姚云昊 , 等 . 面向智能物联网的资源高效模型推理综述 [J ] . 计算机学报 , 2024 , 47 ( 10 ): 2247 - 2273 .

YUAN M. , ZHANG L. , YAO Y. H. , et al . ( 2024 ). A survey on resource-efficient model inference for intelligent Internet of Things . Journal of Computer Science , 47 ( 10 ), 2247 - 2273 .

面向物联网应用的人工智能相关技术研究 [J ] . 电信技术 , 2016 (5 vo): 16 - 19 , 23 .

Research on Artificial Intelligence-Related Technologies for Internet of Things Applications . Telecommunication Technology , 2016 ( 5 ), 16 - 19, 23 .

DONG W , LI B , GUAN G , et al . TinyLink: a holistic system for rapid development of IoT applications [J ] . ACM Trans. Sen. Netw. , 2020 , 17 ( 1 ).

GUAN G , LI B , GAO Y , et al . TinyLink 2.0: integrating device, cloud, and client development for IoT applications [C ] // Proceedings of the 26th Annual International Conference on Mobile Computing and Networking . New York, NY, USA : Association for Computing Machinery , 2020 .

李博睿 , 董玮 , 高艺 , 等 . 物联网软件低代码开发 [J ] . 中国计算机学会通讯 , 2022 .

LI B. R. , DONG W. , GAO Y. , et al . ( 2022 ). Low-code development for Internet of Things software . Communications of the Chinese Computer Federation .

低代码开发平台发展现状及标准化研究 [J ] . 信息技术与标准化 , 2024(Z1 vo): 17- 21 .

Research on the Development Status and Standardization of Low-code Development Platforms . Information Technology and Standardization , 2024 (Z 1 ), 17 - 21 .

RICHARDSON C , RYMER J . New development platforms emerge for customer-facing applications . Forrester [M ] . 2023 .

GUPTA T , KEMBHAVI A . Visual programming: compositional visual reasoning without training [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . 2023 : 14953 - 14962 .

HU Y , YANG J , CHEN L , et al . Planning-oriented autonomous driving [C ] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . 2023 : 17853 - 17862 .

陈慕涵 , 郭佳佳 , 李潇 , 等 . 基于深度学习的大规模MIMO信道状态信息反馈 [J ] . 物联网学报 , 2020 , 4 ( 1 ): 33 - 44 .

CHEN Muhan , GUO Jiajia , LI Xiao , et al . Deep learning-based feedback of large-scale MIMO channel state information [J ] . Journal of Internet of Things , 2020 , 4 ( 1 ): 33 - 44 .

廖勇 , 姚海梅 , 花远肖 . 一种基于深度学习的物联网信道状态信息获取算法 [J ] . 物联网学报 , 2019 , 3 ( 1 ): 8 - 13 .

LIAO Yong , YAO Haimei , HUA Yuanxiao . A deep learning-based algorithm for channel state information acquisition in Internet of Things [J ] . Journal of Internet of Things , 2019 , 3 ( 1 ): 8 - 13 .

BECKER B A , DENNY P , FINNIE-ANSLEY J , et al . Programming is hard - or at least it used to Be: educational opportunities and challenges of AI code generation [C ] // Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1 . New York, NY, USA : Association for Computing Machinery , 2023 : 500 - 506 .

LIU J , XIA C S , WANG Y , et al . Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation [C ] //OH A, NAUMANN T, GLOBERSON A, et al. Advances in Neural Information Processing Systems : Vol . 36 . AssociatesCurran, Inc., 2023 : 21558 - 21572 .

DONG Y , JIANG X , JIN Z , et al . Self-Collaboration Code Generation via ChatGPT [J ] . ACM Transactions on Software Engineering and Methodology , 33 ( 7 ).

CHANG Y , WANG X , WANG J , et al . A Survey on Evaluation of Large Language Models [J ] . 15 ( 3 ).

ZHAO W X , ZHOU K , LI J , et al . A survey of large language models [Z ] . ( 2024 ).

HADI M U , TASHI A , QURESHI R , et al . A survey on large language models: applications, challenges, limitations, and practical usage [C ] .

CHENG Y , ZHANG C , ZHANG Z , et al . Exploring large language model based intelligent agents: definitions, methods, and prospects [Z ] . ( 2024 ).

XI Z , CHEN W , GUO X , et al . The rise and potential of large language model based agents: a survey [J ] . Science China Information Sciences , 2025 , 68 ( 2 ): 121101 .

大语言模型发展综述 [J ] . 统计学报 , 2024 ( 4 vo 5 ): 13 - 18 .

A Survey on Intelligent Agent Construction Based on Large Language Models . Communication Technology , 2024 ( 9 ), 57, 873 - 879 .

HUANG X , LIU W , CHEN X , et al . Understanding the planning of LLM agents: a survey [Z ] . ( 2024 ).

基于大语言模型的智能体构建综述 [J ] . 通信技术 , 2024 ( 9 vo 57 ): 873 - 879 .

A Survey on Intelligent Agent Construction Based on Large Language Models . Communication Technology , 2024 ( 9 ), 57, 873 - 879 .

王文晟 , 谭宁 , 黄凯 , 等 . 基于大模型的具身智能系统综述 [Z ] //自动化学报: 卷 51 . 2025 : 1 - 19 .

WANG W. S. , TAN N. , HUANG K. , et al . ( 2025 ). A survey on embodied intelligent systems based on large models . Acta Automatica Sinica , 51 , 1 - 19 .

ZHANG D , YU Y , DONG J , et al . MM-LLMs: recent advances in MultiModal large language models [Z ] . ( 2024 ).

GAO Y , XIONG Y , GAO X , et al . Retrieval-augmented generation for large language models: a survey [Z ] . ( 2024 ).

基于大型语言模型的检索增强生成综述 [J ] . 计算机工程与应用: 1 - 31 .

A Survey on Retrieval-Augmented Generation Based on Large Language Models . Computer Engineering and Applications , 1 - 31 .

FAN X , DENG X , XIA Y , et al . Tensor-based confident information coverage reliability of hybrid internet of things [J ] . IEEE Transactions on Mobile Computing , 2024 , 23 ( 3 ): 2171 - 2185 .

GONG W , LIU K , LIU Y . Directional diagnosis for wireless sensor networks [J ] . IEEE Transactions on Parallel and Distributed Systems , 2015 , 26 ( 5 ): 1290 - 1300 .

DENG X , WANG B , LIU W , et al . Sensor scheduling for multi-modal confident information coverage in sensor networks [J ] . IEEE Transactions on Parallel and Distributed Systems , 2015 , 26 ( 3 ): 902 - 913 .

LIU K , MA Q , GONG W , et al . Self-diagnosis for detecting system failures in large-scale wireless sensor networks [J ] . IEEE Transactions on Wireless Communications , 2014 , 13 ( 10 ): 5535 - 5545 .

SAHAY A , INDAMUTSA A , DI RUSCIO D , et al . Supporting the understanding and comparison of low-code development platforms [C ] // 2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA) . 2020 : 171 - 178 .

浙江大学 . 物联网低代码开发平台及应用 [J ] . 2021 .

ZHEJIANG UNIVERSITY . Internet of Things Low-Code Development Platform and Applications . 2021 .

LUO Y , LIANG P , WANG C , et al . Characteristics and challenges of low-code development: the practitioners’ perspective [C ] // Proceedings of the 15th ACM / IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) . New York, NY, USA : Association for Computing Machinery , 2021 .

周彤 . 基于端云一体化的可重构物联网系统平台设计 [D ] . 杭州 : 杭州电子科技大学 , 2022 .

ZHOU T . ( 2022 ). Design of Reconfigurable Internet of Things System Platform Based on Edge-Cloud Integration . Hangzhou : Hangzhou University of Electronic Science and Technology .

LI B , DONG W . EdgeProg: edge-centric programming for IoT applications [C ] // 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS) . 2020 : 212 - 222 .

LI B , DONG W . Automatic generation of IoT device platforms with AutoLink [J ] . IEEE Internet of Things Journal , 2021 , 8 ( 7 ): 5893 - 5903 .

GONG W , STOJMENOVIC I , NAYAK A , et al . Fast and scalable counterfeits estimation for large-scale RFID systems [J ] . IEEE/ACM Transactions on Networking , 2016 , 24 ( 2 ): 1052 - 1064 .

WANG Q , CHEN S , ZHAO J , et al . RapidRider: efficient WiFi backscatter with uncontrolled ambient signals [C ] // IEEE INFOCOM 2021 - IEEE Conference on Computer Communications . 2021 : 1 - 10 .

WANG G , HAN L , CHANG Y , et al . Cross-technology communication between visible light and battery-free RFIDs [J ] . Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 2023 , 7 ( 3 ): 1 - 20 .

DOSOVITSKIY A , BEYER L , KOLESNIKOV A , et al . An image is worth 16x16 words: transformers for image recognition at scale [Z ] .( 2021 ).

CHEN S , WU Y , WANG C , et al . BEATs: audio pre-training with acoustic tokenizers [Z ] . ( 2022 ).

CHEN F , HAN M , ZHAO H , et al . X-LLM: bootstrapping advanced large language models by treating multi-modalities as foreign languages [Z ] . ( 2023 ).

YUAN J , YANG C , CAI D , et al . Mobile foundation model as firmware [C ] // Proceedings of the 30th Annual International Conference on Mobile Computing and Networking . New York, NY, USA : Association for Computing Machinery , 2024 : 279 - 295 .

HUANG K , YANG B , GAO W . Modality plug-and-play: elastic modality adaptation in multimodal LLMs for embodied AI [Z ] . ( 2023 ).

SURIS D , MENON S , VONDRICK C . ViperGPT: Visual Inference via Python Execution for Reasoning [J ] .

LIU Z , HE Y , WANG W , et al . InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language [M ] . arXiv , 2023 .

SHEN Y , SONG K , TAN X , et al . HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face [J ] .

QIAN C , LIU W , LIU H , et al . ChatDev: communicative agents for software development [Z ] . ( 2024 ).

HONG S , ZHUGE M , CHEN J , et al . MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework [M ] . arXiv , 2024 .

SHEN L , ZHENG Y . IoTCoder: A Copilot for IoT Application Development [C ] // Proceedings of the 30th Annual International Conference on Mobile Computing and Networking . 2024 : 1647 - 1649 .

GONG K , DONG W , PENG Y , et al . Poster: Enabling IoT Application Programming in Natural Language with IoTPilot [C ] // Proceedings of the 22nd ACM Conference on Embedded Networked Sensor Systems . 2024 : 903 - 904 .

YANG H , LI M , HAN M , et al . EmbedGenius: Towards Automated Software Development for Generic Embedded IoT Systems [J ] . arXiv preprint arXiv: 2412.09058 , 2024 .

CHENG Y , XU M , ZHANG Y , et al . AutoIoT: Automated IoT Platform Using Large Language Models [J ] . IEEE Internet of Things Journal , 2024 .

GAO Y , XIAO K , LI F , et al . ChatIoT: Zero-code Generation of Trigger-action Based IoT Programs [J ] . Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies , 2024 , 8 ( 3 ): 1 - 29 .

HU C , FU J , DU C , et al . ChatDB: augmenting LLMs with databases as their symbolic memory [Z ] . ( 2023 ).

ZHOU X . DB-GPT: Large Language Model Meets Database [J ] .

ChatExcel AI Excel处理和数据分析 [Z ] .

ChatExcel AI Excel Processing and Data Analysis [Z ]

KING E , YU H , LEE S , et al . Sasha: Creative Goal-Oriented Reasoning in Smart Homes with Large Language Models [J ] . 8 ( 1 ).

RIVKIN D , HOGAN F , FERIANI A , et al . AIoT Smart Home via Autonomous LLM Agents [J ] . IEEE Internet of Things Journal , 2024 .

BROWN T , MANN B , RYDER N , et al . Language models are few-shot learners [C ] //LAROCHELLE H, RANZATO M, HADSELL R, et al. Advances in Neural Information Processing Systems : Vol . 33 . AssociatesCurran, Inc., 2020 : 1877 - 1901 .

WEI J , WANG X , SCHUURMANS D , et al . Chain-of-thought prompting elicits reasoning in large language models [C ] //KOYEJO S, MOHAMED S, AGARWAL A, et al. Advances in Neural Information Processing Systems : Vol . 35 . AssociatesCurran, Inc., 2022 : 24824 - 24837 .

KOJIMA T , GU S S , REID M , et al . Large Language Models are Zero-Shot Reasoners [J ] .

WANG X , WEI J , SCHUURMANS D , et al . Self-consistency improves chain of thought reasoning in language models [Z ] . ( 2023 ).

YAO S , YU D , ZHAO J , et al . Tree of thoughts: deliberate problem solving with large language models [C ] //OH A, NAUMANN T, GLOBERSON A, et al. Advances in Neural Information Processing Systems : Vol . 36 . AssociatesCurran, Inc., 2023 : 11809 - 11822 .

YAO S , ZHAO J , YU D , et al . ReAct: synergizing reasoning and acting in language models [Z ] . ( 2023 ).

MADAAN A , TANDON N , GUPTA P , et al . Self-refine: iterative refinement with self-feedback [C ] //OH A, NAUMANN T, GLOBERSON A, et al. Advances in Neural Information Processing Systems : Vol . 36 . AssociatesCurran, Inc., 2023 : 46534 - 46594 .

ZHOU D , SCHÄRLI N , HOU L , et al . Least-to-most prompting enables complex reasoning in large language models [Z ] . ( 2023 ).

SHINN N , CASSANO F , GOPINATH A , et al . Reflexion: language agents with verbal reinforcement learning [C ] //OH A, NAUMANN T, GLOBERSON A, et al. Advances in Neural Information Processing Systems : Vol . 36 . AssociatesCurran, Inc., 2023 : 8634 - 8652 .

GOU Z , SHAO Z , GONG Y , et al . CRITIC: large language models can self-correct with tool-interactive critiquing [Z ] . ( 2024 ).

王浩彬 , 皇甫伟 , 刘娅汐 , 等 . 基于计算图的移动通信网络物联网业务覆盖优化算法及实现 [J ] . 物联网学报 , 2019 , 3 ( 2 ): 100 - 107 .

WANG Haobin , HUANGFU Wei , LIU Yaxi , et al . Computation graph-based optimization algorithm and implementation for IoT service coverage in mobile communication networks [J ] . Journal of Internet of Things , 2019 , 3 ( 2 ): 100 - 107 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

面向智慧旅游物联网设备的身份认证方法的研究

频偏下基于张量分解的联合设备活跃性检测和信道估计

物联网中模型剪枝技术：现状、方法和展望

基于联邦强化学习的面向边缘网络的入侵检测方法研究

认证加密算法SM4-GCM的低成本硬件架构设计与实现