College of Furnishings and Industrial Design, Nanjing Forestry University, Nanjing 210037, China
Show less
文章历史+
Received
Published
Revised
2025-06-11
2026-04-18
2025-11-19
Online Date
2026-06-08
PDF (5828K)
摘要
为精准识别智能办公桌用户的核心需求要素,探究智能办公桌产品设计要素与用户需求感知的映射关系,为智能办公桌的设计优化提供科学依据。首先通过爬取淘宝和京东平台智能办公桌评论数据30 015条,经数据清洗、分词等处理后,运用LDA(latent dirichlet allocation)模型聚类确定四个需求大类,并细分出32项子类;以需求大类为外源潜在变量、小类为观测变量,结合五级李克特量表问卷获取数据,构建结构方程与人工神经网络(structural equation modeling and artificial neural networks,SEM-ANN)混合模型。SEM路径分析表明“使用体验”对“满意度”的正向影响最为显著。SEM-ANN模型在各测量项上的R2较SEM平均提升0.15~0.18,均方根差明显下降,表明非线性拟合能力显著增强。综合权重排序显示,“气味/环保性”“表面触感”“升降安全”“自组装安装”等为最关键的设计优化点。通过融合在线评论挖掘与SEM-ANN混合建模,有效揭示了智能升降办公桌微观设计要素与宏观用户感知之间的映射关系,为产品设计提供了具有优先级的改进清单。该方法论可推广至其他智能硬件或复杂消费品的用户需求分析与设计优化实践。
Abstract
In order to identify the core demand elements of smart desk users, the mapping relationship between product design elements and user demand perception was explored,which provides a scientific basis for the design optimization of smart desks. A total of 30 015 online reviews of smart desks were collected from Taobao and Jingdong platforms. After data cleaning and word segmentation, the latent dirichlet allocation (LDA) model was applied to cluster user needs into four major categories and thirty-two subcategories. These demand categories were treated as exogenous latent variables and the subcategories as observed variables. Questionnaire data were collected using a five-point Likert scale, and a hybrid model combining structural equation modeling and artificial neural networks (SEM-ANN) was established. The SEM analysis indicated that the positive effect of “experience of use” on “satisfaction” was the most significant. The R2 values of the SEM-ANN model increased by about 0.15~0.18 compared with the SEM model, while the RMSE(root mean square error)decreased significantly, showing enhanced nonlinear fitting ability. The comprehensive weight analysis identified odor and environmental friendliness, surface touch, lift safety, and self-assembly installation as the key design optimization points. By integrating online review mining with SEM-ANN hybrid modeling, the mapping between micro design elements and macro user perception of smart lifting desks was revealed. The proposed method provides a prioritized improvement list for design optimization and can be extended to user requirement analysis of other smart hardware and complex consumer products.
FU Si-jie, XIONG Xian-qing, YUE Xin-yi.
Design Optimization on Smart Desk Design Based on Online Review Mining and SEM-ANN Fusion Models[J].
Science Technology and Engineering, 2026, 26(11): 4758-4768 DOI:10.12404/j.issn.1671-1815.2504361
在产品设计领域,SEM常用于分析设计特征对用户满意度、使用意图等感知变量的影响,有助于揭示各设计要素的作用机制与重要性排序[23]。如张玲玲等,将适老化橱柜的外观、功能、结构等6个设计维度设为外源潜变量,以用户消费意愿和创新性为内生潜变量,通过路径分析识别显著影响路径[24]。SEM的可解释性强,模型结构清晰,拟合优度评估标准丰富,如比较拟合指数(comparative fit index, CFI)、塔克-刘易斯指数(Tucker-Lewis index, TLI)、近似误差均方根(root mean square error of approximation, RMSEA)等,使其在理论验证中具有广泛应用价值[25]。
ChaoYao, JinQianru, ShenLiming, et al. A method for determining the comfort of office chair based on body pressure distribution and PCA-BP neural network model[J]. Journal of Forest Engineering, 2021, 6(5): 183-190.
[3]
ChenJ, ShiH. Research on North American office furniture industry based on steep analysis technology[J]. Frontiers in Business, Economics and Management, 2024, 16(1): 28-31.
[4]
MejíaS, AguilarJ. A demand forecasting system of product categories defined by their time series using a hybrid approach of ensemble learning with feature engineering[J]. Computing, 2024, 106(12): 3945-3965.
WuLei, ShengQinqin, ZhaoRuisi. Research on user experience evaluation of human-machine interface of automobile automatic driving takeover system[J]. Journal of Graphics, 2025, 46(2): 459-468.
NiZhaoxin, ShuFan. Influencing factors of fresh logistics service quality by CNN-BiLSTM based on self-attention mechanism[J]. Science Technology and Engineering, 2025, 25(16): 6821-6830.
HeFeng, WangTianci, YangYuyan, et al. Improved textual semantic prior-guided scene text image super-resolution[J]. Science Technology and Engineering, 2025, 25(25): 10821-10828.
CaoMeng, XiongXianqing, ZhaoYan. Research on intelligent desk design based on home office users' needs[J]. Furniture and Interior Decoration(6): 62-67.
XiongXianqing, GuoWeijuan, HuangQiongtao, et al. Research on quality control technology of furniture digital manufacturing[J]. Journal of Forestry Engineering, 2017, 2(4): 152-157.
WangZeyang, ZhangXinyu, XiangZerui, et al. Optimization method of suspended monorail train appearance design based on fuzzy hierarchical analysis[J]. Science Technology and Engineering, 2025, 25(3): 977-984.
LüXin, LiuYuyun. Research on the evaluation of child safety seat design options based on AHP-TOPSIS method[J]. Packaging Engineering, 2019, 40(14): 150-155.
ChenGuoqiang, HaoYaping, ShenZhengyi, et al. Design of special delivery holding tanker based on fuzzy Kano model and topological innovation method[J]. Packaging Engineering, 2023, 44(6): 205-214, 240.
ShenYan, WangQian. Deep semantic enhancement expert recommendation algorithm based on BERT-MHA[J]. Science Technology and Engineering, 2025, 25(25): 10810-10820.
XiongXianqing, LiRongrong, BaiHongtao. Status quo and development trend of China's intelligent furniture industry[J]. Journal of Forestry Engineering, 2021, 6(1): 21-28.
[32]
MihalceaR, BiesterL, BoydR L, et al. How developments in natural language processing help us in understanding human behaviour[J]. Nature Human Behaviour, 2024, 8(10): 1877-1889.
LinLi, ZhangYunkun, NiuYafeng, et al. An unbiased design method for product perceptual imagery based on network evaluation data[J]. Journal of Southeast University (Natural Science Edition), 2020, 50(1): 26-32.
KongDeyang, HuangSirui, MaShujie. A perceptual evaluation method for automotive styling design based on sentiment analysis[J]. Journal of Tongji University (Natural Science Edition), 2022, 50(12): 1817-1824.
[37]
YangC, WuL, TanK, et al. Online user review analysis for product evaluation and improvement[J]. Journal of Theoretical and Applied Electronic Commerce Research, 2021, 16(5): 1598-1611.
HuaYuwen, LiHongchen, WangMeng, et al. Impact of digitization of public cultural services on digital burden of elderly users—a hybrid approach based on SEM and ANN[J]. Intelligence Information Work, 2025, 46(3): 65-72.
ZhangLingling, DaiXiangdong, LiJiaying, et al. Analysis of influencing factors of aging-friendly cabinet design based on PLS-SEM model[J]. Journal of Central South Forestry University of Science and Technology, 2025, 45(4): 211-224.
DingMan, DingTingting, SongMeijia, et al. Emotional design of product color based on implicit measurement and BP neural network[J]. Computer Integrated Manufacturing Systems, 2023, 29(2): 616-627.
[48]
SongZ, KusiakA. Optimising product configurations with a data-mining approach[J]. International Journal of Production Research, 2009, 47(7): 1733-1751.