Please wait a minute...
浙江大学学报(工学版)  2022, Vol. 56 Issue (4): 803-808    DOI: 10.3785/j.issn.1008-973X.2022.04.020
计算机技术、信息工程     
基于改进加权协同过滤的集群用户黑箱个性意象预测
林丽(),任丽,阳明庆
贵州大学 机械工程学院,贵州 贵阳 550025
Prediction of black-box personality image of cluster users based on improved weighted collaborative filtering
Li LIN(),Li REN,Ming-qing YANG
School of Mechanical Engineering, Guizhou University, Guiyang 550025, China
 全文: PDF(679 KB)   HTML
摘要:

为了解决传统意象定位中感性意象部分信息丢失及用户模糊的个性化需求不完全表达的问题,提出基于改进加权SO(WSO)算法的集群用户个性意象预测研究. 建立用户特征域,基于K-modes算法计算用户差异度,确立用户集群. 对甄选样本实施兴趣度排序及自主性意象评价,创建集群意象因子集. 引入用户相似度优化WSO算法,增强集群用户间的内在联系,精准预测目标用户黑箱的个性意象分值. 基于语义差异问卷及平均绝对误差分析验证黑箱意象,输出集群中单一用户的个性化意象,实现意象预测. 以无人机为例,预测用户的个性意象,误差小于0.5被舍去,表明该方法能够较好地实现用户模糊的意象黑箱透明化,且预测的意象符合用户的个性化需求,可以有效辅助设计师有针对性地设计.

关键词: 感性产品设计黑箱个性化意象集群理论潜在需求    
Abstract:

A prediction study of cluster user personality image based on improved weighted slope one (WSO) algorithm was proposed in order to solve the problems of partial information loss of perceptual image and incomplete expression of fuzzy personalized needs of users in traditional image localization. The user characteristic domain was established, and user cluster was established based on K-modes algorithm in order to calculate user differences. Interest ranking and independent image evaluation were conducted to create a subset of cluster image factors. The user similarity optimization WSO algorithm was introduced to enhance the internal connection between cluster users and accurately predict the personality image score of the target user’s black box. Black box image was verified by semantic difference questionnaire and mean absolute error analysis, and personalized image of single user in cluster was output to achieve image prediction. UAV was taken as an example to predict user’s personality image. The error less than 0.5 was omitted. The method can better realize the transparency of user’s fuzzy image black box and the predicted image meets user’s personalized needs, which can effectively assist designers in targeted design.

Key words: perceptual product design    personalized image of black-box    cluster theory    latent demand
收稿日期: 2021-05-19 出版日期: 2022-04-24
CLC:  TB 472  
基金资助: 国家自然科学基金资助项目(51865003);贵州省科技计划资助项目(黔科合基础-ZK[2021]重点055);黔科合平台人才计划资助项目([2018]5781);贵州大学培育项目(贵大培育[2019]06)
作者简介: 林丽(1973—),女,教授,博导,从事产品创新设计、感性工学、传统文化创意设计的研究. orcid.org/0000-0001-6160-1000. E-mail: linlisongbai@163.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
林丽
任丽
阳明庆

引用本文:

林丽,任丽,阳明庆. 基于改进加权协同过滤的集群用户黑箱个性意象预测[J]. 浙江大学学报(工学版), 2022, 56(4): 803-808.

Li LIN,Li REN,Ming-qing YANG. Prediction of black-box personality image of cluster users based on improved weighted collaborative filtering. Journal of ZheJiang University (Engineering Science), 2022, 56(4): 803-808.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2022.04.020        https://www.zjujournals.com/eng/CN/Y2022/V56/I4/803

图 1  改进WSO算法的集群用户个性化意象预测方法框架
图 2  用户特征树状图
用户编号 特征类目下的特征元编码
1 2 3 4 5 6 7
1 2 2 1 1 4 1 3
2 2 2 1 1 3 2 3
3 1 3 2 2 3 2 2
4 1 3 2 1 3 3 3
5 2 1 1 1 3 1 3
6 1 2 1 1 3 1 1
7 2 3 2 2 4 3 1
$ \vdots $ $ \vdots $ $ \vdots $ $ \vdots $ $ \vdots $ $ \vdots $ $ \vdots $ $ \vdots $
47 1 1 2 1 3 1 2
48 2 2 1 1 4 1 3
49 1 2 2 2 3 1 3
表 1  部分用户特征编码
集群 集群人数 用户编号
$ {k_1} $ 12 2、5、6、17、18、23、24、32、37、38、40、41
$ {k_{\text{2}}} $ 5 7、11、30、36、39
$ {k_{\text{3}}} $ 13 3、4、9、10、12、13、16、25、31、33、44、46、49
$ {k_{\text{4}}} $ 10 1、14、15、19、21、42、43、45、47、48
$ {k_{\text{5}}} $ 9 8、20、22、26、27、28、29、34、35
表 2  用户所属集群表
图 3  代表性样本收敛集
集群 意象因子集
$ {k_1} $ 稳定、简约、冰冷、可靠、科技、坚固、炫酷、昂贵
$ {k_{\text{2}}} $ 轻巧、圆润、前卫、耐用、高级
$ {k_{\text{3}}} $ 简洁、清新、现代、科技、时尚、明快、稳定、
硬朗、亲和、轻巧
$ {k_{\text{4}}} $ 前卫、科技、灵敏、圆润、高级、可靠、简约
$ {k_{\text{5}}} $ 科技、耐用、灵敏、现代、便携、圆润、有趣
表 3  样本1下5个集群意象因子集
意象 意象因子
自主性意象 高级、科技
集群意象 高级、科技、前卫、灵敏、
圆润、可靠、简约
黑箱意象 前卫、灵敏、圆润、可靠、简约
表 4  用户 ${{{{\boldsymbol{x}}_{{{{\mathbf{42}}}}}}}} $的意象对比
分值类型 黑箱意象分值
前卫 灵敏 圆润 可靠 简约
预测值 4.0 3.6 4.6 4.3 3.3
取整 4 4 5 4 3
表 5  用户 ${{{{\boldsymbol{x}}_{{{{\mathbf{42}}}}}}}}$的样本1黑箱意象预测分值及取整
意象因子 实际评分 意象因子 实际评分
前卫 4 可靠 4
灵敏 4 简约 3
圆润 5
表 6  用户 $ {x_{{\text{42}}}} $的样本1黑箱意象验证评分
1 朱上上, 楼晓霏, 李文杰, 等 基于可拓设计的产品个性化定制方法[J]. 计算机集成制造系统, 2020, 26 (10): 2661- 2669
ZHU Shang-shang, LOU Xiao-fei, LI Wen-jie, et al Personalized customization method based on extension design[J]. Computer Integrated Manufacturing System, 2020, 26 (10): 2661- 2669
2 林丽, 郭主恩, 阳明庆 面向产品感性意象的造型优化设计研究现状及趋势[J]. 包装工程, 2020, 41 (2): 65- 79
LIN Li, GUO Zhu-en, YANG Ming-qing Current research situation and trend of product image-based modeling optimization[J]. Packaging Engineering, 2020, 41 (2): 65- 79
3 罗仕鉴, 朱上上, 应放天, 等 产品设计中的用户隐性知识研究现状与进展[J]. 计算机集成制造系统, 2010, 16 (4): 673- 688
LUO Shi-jian, ZHU Shang-shang, YING Fang-tian, et al Statues and progress of research on users’ tacit knowledge in product design[J]. Computer Integrated Manufacturing System, 2010, 16 (4): 673- 688
4 OSGOOD C, SUCI G, TANNENBAUM P. The measurement of meaning [M]. Urbana: University of Illinois Press, 1957.
5 GUO F, QU Q X, NAGAMACHI M, et al A proposal of the event-related potential method to effectively identify kansei words for assessing product design features in kansei engineering research[J]. International Journal of Industrial Ergonomics, 2020, 76: 102940
6 WANG Y H, YU S H, MA N, et al. Prediction of product design decision making: an investigation of eye movements and EEG features [J]. Advanced Engineering Informatics, 2020, 45: 101095.
7 朱斌, 杨程, 俞春阳, 等 基于深度学习的产品意象识别[J]. 计算机辅助设计与图形学学报, 2018, 30 (9): 1778- 1784
ZHU Bin, YANG Cheng, YU Chun-yang, et al Product image recognition based on deep learning[J]. Journal of Computer-Aided Design and Computer Graphics, 2018, 30 (9): 1778- 1784
8 HAN Y, MOGHADDAM M Analysis of sentiment expressions for user-centered design[J]. Expert Systems with Applications, 2021, 171 (4): 114604
9 CHANG Y, CHEN C Kansei assessment of the constituent elements and the overall interrelations in car steering wheel design[J]. International Journal of Industrial Ergonomics, 2016, 56: 97- 105
10 刘征宏, 谢庆生, 黄海松, 等 多维变量感性工学模型构建及其性能评估[J]. 四川大学学报:工程科学版, 2016, 48 (2): 198- 206
LIU Zheng-hong, XIE Qing-sheng, HUANG Hai-song, et al Construction and performance evaluation for multi-dimensional variable KE model[J]. Journal of Sichuan University: Engineering Science Edition, 2016, 48 (2): 198- 206
11 XUE L, YI X, ZHANG Y Research on optimized product image design integrated decision system based on Kansei engineering[J]. Applied Sciences-Basel, 2020, 10 (4): 1198
doi: 10.3390/app10041198
12 科特勒·菲利普, 凯勒·凯文. 营销管理[M]. 北京: 中国人民大学出版社, 2012.
13 HU L, XING Y, GONG Y, et al Nonnegative matrix trifactorization with user similarity for clustering in point-of-interest[J]. Neurocomputing, 2019, 363 (21): 58- 65
14 吴莹莹, 肖旺群 基于因子聚类分析的儿童陪伴机器人用户细分[J]. 包装工程, 2020, 41 (14): 216- 221
WU Ying-ying, XIAO Wang-qun User segmentation of children partner robots based on factor and clustering analysis[J]. Packaging Engineering, 2020, 41 (14): 216- 221
15 CHEN H, ZHANG L, CHU X, et al. Smartphone customer segmentation based on the usage pattern [J]. Advanced Engineering Informatics. 2019, 42: 101000.
16 WANG X, TAN Q, GOH M Attention-based deep neural network for Internet platform group users’ dynamic identification and recommendation[J]. Expert Systems with Applications, 2020, 160: 113728
doi: 10.1016/j.eswa.2020.113728
17 LEMIRE D, MACLACHLAN A. Slope one predictors for online rating-based collaborative filtering [C]// Proceedings of the 2005 SIAM International Conference on Data Mining. Newport Beach: SIAM, 2005: 471-475.
18 WANG Q, LUO X, LI Y, et al Incremental slope-one recommenders[J]. Neurocomputing, 2018, 272: 606- 618
19 董立岩, 金佳欢, 方塬程, 等 基于非负矩阵分解的Slope One算法[J]. 浙江大学学报:工学版, 2019, 53 (7): 1349- 1353
DONG Li-yan, JIN Jia-huan, FANG Yuan-cheng, et al Slope one algorithm based on nonnegative matrix factorization[J]. Journal of Zhejiang University: Engineering Science, 2019, 53 (7): 1349- 1353
20 ZHANG J, WANG Y, YUAN Z, et al Personalized real-time movie recommendation system: practical prototype and evaluation[J]. Tsinghua Science and Technology, 2020, 25 (2): 180- 191
doi: 10.26599/TST.2018.9010118
[1] 王憬鸾,陈登凯,朱梦雅,王晗宇,孙意为. 基于卷积姿态机的潜航员作业姿态识别方法[J]. 浙江大学学报(工学版), 2022, 56(1): 26-35.
[2] 杨延璞,龚政,兰晨昕,雷紫荆,王欣蕊. 工业设计决策网络构建及其动态演化仿真[J]. 浙江大学学报(工学版), 2021, 55(12): 2298-2306.
[3] 周爱民,刘宏斌,张书涛,欧阳晋焱. 面向汽车主客观审美评价的不确定性推理模型[J]. 浙江大学学报(工学版), 2021, 55(3): 419-429.
[4] 周爱民,周彩霞,欧阳晋焱,张书涛. 基于指标适度标准化的界面风格美综合评价模型[J]. 浙江大学学报(工学版), 2020, 54(12): 2273-2285.
[5] 陈健,莫蓉,余隋怀,初建杰,陈登凯,宫静. 云环境下众包产品造型设计方案多目标群体决策[J]. 浙江大学学报(工学版), 2019, 53(8): 1517-1524.
[6] 刘征, 鲁娜, 吴剑锋. 基于设计认知的草图研究综述[J]. J4, 2010, 44(12): 2376-2382.
[7] 武守飞, 王正肖, 潘晓弘, 等. 基于粗集理论的产品属性定制权重确定方法[J]. J4, 2009, 43(12): 2250-2253.