| 71 | 0 | 54 |
| 下载次数 | 被引频次 | 阅读次数 |
中国老年人口的快速增加，代表着中国的国家发展取得了成就和社会文明迈入新的阶段，同时带来了新的机遇和挑战.面对日益增长的老年人健康需求和即将到来的“银发经济”时代，市场上将更多地出现针对老年人的健康服务技术，如智能健康监测、辅助生活技术等.相关技术如何从基本的被动式健康服务进化到无须人工干预的更为智能化的管家式服务将成为未来“银发经济”市场角逐的关键.鉴于此，本文结合近来备受关注的以Deep Seek为代表的大语言模型，提出一个将具备自然语言理解能力的、生成式的人工智能技术引入到智慧家庭中的针对老年人健康监测和分析的技术框架，以提升服务的智能化水平，向实现人性化的人工智能管家目标迈进.
Abstract：The rapid growth of China's elderly population represents the achievements of China's national development and the entry of social civilization into a new stage, while bringing new opportunities and challenges. Facing the growing health needs of the elderly and the upcoming era of “silver economy”, more health service technologies for the elderly will appear in the market, such as intelligent health monitoring, assisted living technology, etc. How related technologies for the elderly evolve from basic passive health services to more intelligent butler services without human intervention will become the key to compete in the silver market in the future. In view of this, combined with the large language model represented by Deep Seek,which has attracted much attention recently, a technical framework is proposed for health monitoring and analysis of the elderly, which introduces the generative AI technology with natural language understanding ability into the smart home, so as to improve the intelligent level of service and move towards the goal of realizing the humanized AI Butler.
[1]林梅.当代中国年轻人的压力与焦虑[J].人民论坛，2019(33):78-80.
[2]柳明月，李玉童.家庭养老功能弱化视角下老年人监护制度完善[J].品牌（下半月），2015(3):275.
[3]ZHONG Y. Collaboration of IoT devices in smart home scenarios:algorithm research based on graph neural networks and federated learning[J]. Discover Internet of Things,2025,5(1):1-19.
[4]巩莉.面向智慧家庭的用户日常行为识别算法的研究[D].重庆：重庆邮电大学，2018.
[5]BENSAID R,LABRAOUI N,SAIDI H,et al. Securing fog-assisted IoT smart homes:a federated learning-based intrusion detection approach[J]. Cluster Computing,2025,28(1):1-19.
[6]李振.基于数字孪生的家庭健康检测方法及应用研究[D].徐州：中国矿业大学，2021.
[7]KASMI M,BAHLOUL F,TKITEK H. Smart home based on Internet of Things and cloud computing[C]//2016 7th International Conference on Sciences of Electronics,Technologies of Information and Telecommunications(SETIT). IEEE,2016:82-86.
[8]COLETI T A,BALANCIERI R,MENOLLI A,et al. Handling of personal data by smart home equipment:an exploratory analysis in the context of LGPD[J]. Journal on Interactive Systems, 2024, 15(1):311-322.
[9]RIVKIN D,HOGAN F,FERIANI A,et al. AIoTsmart home via autonomous LLM agents[J]. IEEE Internet of Things Journal,2025,12(3):2458-2472.
[10]GUO D,YANG D,ZHANG H,et al. Deepseek-r1:Incentivizing reasoning capability in llms via reinforcement learning[EB/OL].[2025-04-09]. https://arxiv.org/pdf/2501.12948.
[11]SHANNON C E. A mathematical theory of communication[J]. The Bell System Technical Journal ,1948,27(3):379-423.
[12]RABINER L R. A tutorial on hidden markov models and selected applications in speech recognition[J].Readings in Speech Recognition,1990,77(2):267-296.
[13]LAFFERTY J D,MCCALLUM A,PEREIRA F C N. Conditional random fields:Probabilistic models for segmenting and labeling sequence data[C]//Eighteenth International Conference on Machine Learning.Barcellona:Morgan Kaufmann Publishers Inc,2001:282-289.
[14]PASCANU R,MIKOLOV T,BENGIO Y. On the difficulty of training recurrent neural networks[C]//International Conference on Machine Learning. Pmlr,2013:1310-1318.
[15]VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[J]. Advances in Neural Information Processing Systems,2017:30.
[16]BROWN T,MANN B,RYDER N,et al. Language models are few-shot learners[J]. Advances in Neural Information Processing Systems,2020,33:1877-1901.
[17]TOUVRON H,LAVRIL T,IZACARD G,et al. Llama:Open and efficient foundation language models[EB/OL].[2025-04-09]. https://arxiv.org/abs/2302.13971.
[18]DU Z,QIAN Y,LIU X,et al. Glm:General language model pretraining with autoregressive blank infilling[EB/OL].[2025-04-09]. https://arxiv.org/abs/2103.10360.
[19]YANG A,YANG B,ZHANG B,et al. Qwen2.5 technical report[EB/OL].[2025-04-09]. https://arxiv.org/pdf/2412.15115.
[20]JORDAN M I,JACOBS R A. Hierarchical mixtures of experts and the EM algorithm[J]. Neural Computation,1994,6(2):181-214.
[21]SHAZEER N,MIRHOSEINI A,MAZIARZ K,et al. Outrageously large neural networks:the sparselygated mixture-of-experts layer[C]//International Conference on Learning Representations. 2017.
[22]FEDUS W,ZOPH B,SHAZEER N. Switch transformers:Scaling to trillion parameter models with simple and efficient sparsity[J]. Journal of Machine Learning Research,2022,23(120):1-39.
[23]KWOLEK B,KEPSKI M. Human fall detection on embedded platform using depth maps and wireless accelerometer[J]. Computer Methods and Programs in Biomedicine,2014,117(3):489-501.
[24]ANSARI M A,SAXENA C,AHMAD T. JMI at SemEval 2024 Task 3:Two-step approach for multimodal ECAC using in-context learning with GPT and instruction-tuned Llama models[C]//Proceedings of the 18th International Workshop on Semantic Evaluation(SemEval-2024). 2024:1561-1576.
[25]HU E J,SHEN Y,WALLIS P,et al. Lora:Low-rank adaptation of large language models[J]. ICLR,2022,1(2):3.
[26]REBUFFI S A,KOLESNIKOV A,SPERL G,et al. Icarl:Incremental classifier and representation learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017:2001-2010.
基本信息:
中图分类号:TP18;D669.6
引用信息:
[1]江帆,吴守朴,姜大志.智慧家庭中老年人群的行为检测与健康评估系统的构建[J].汕头大学学报(自然科学版),2026,41(01):53-64.
基金信息:
广东省科技创新战略专项资助项目（STKJ2021005、STKJ202209002、STKJ2023076）
2026-02-15
2026-02-15