Product Color Emotional Design Based on Knowledge Hypergraph

doi:10.3901/JME.2024.17.339

Abstract

Abstract: Aiming at the problems of multi-color collision, fuzzy calculation of color contribution value, and difficulty in simulating color synergy mechanism in product color emotion design at the present stage, a product color emotion design method based on knowledge hypergraph is proposed. Firstly, the product color emotion data set is constructed by using the theme web crawler and natural semantic word segmentation technology. Then the product color emotion image association model based on the RotatE knowledge map is constructed. then the hypergraph technology is used to construct the product color emotion design model based on the knowledge hypergraphh, and visualized with the Steiner tree method to realize the structured and explicit expression of the complex dynamic relationship between product color and user emotion. Finally, taking the color design of vacuum cleaner as an example, the effectiveness and applicability of the method proposed are verified.

Key words: product color emotional design, color synergy mechanism, RotatE knowledge graph, knowledge hypergraph

CLC Number:

TG156

DING Man, SUN Mingyu, ZHANG Xinxin, FENG Guangyu. Product Color Emotional Design Based on Knowledge Hypergraph[J]. Journal of Mechanical Engineering, 2024, 60(17): 339-348.

References

[1] 薛塬, 臧冀原, 孔德婧, 等. 面向智能制造的产业模式演变与创新应用[J]. 机械工程学报, 2022, 58(18):303-318. XUE Yuan, ZANG Jiyuan, KONG Dejing, et al. Evolution and innovative application of industrial model for intelligent manufacturing[J]. Journal of mechanical engineering, 2022, 58(18):303-318
[2] 李柏姝, 张刚, 黄燕飞. 基于产品全生命周期的产品规划建模与应用[J]. 机械工程学报, 2017, 53(19):201-208. LI Baishu, ZHANG Gang, HUANG Yanfei. Modeling and application of product planning based on product life cycle[J]. Journal of mechanical engineering, 2017, 53(19):201-208.
[3] 冯毅雄, 娄山河, 王绪鹏, 等. 面向性能的定制产品感性意象评价方法研究[J]. 机械工程学报, 2020, 56(9):181-190. FENG Yixiong, LOU Shanhe, WANG Xupeng, et al. Research on performance oriented sensory image evaluation method for customized products[J]. Journal of Mechanical Engineering, 2020, 56(9):181-190.
[4] 丁满, 袁云磊, 张新新, 等. 基于深度学习的产品色彩情感化设计[J]. 计算机集成制造系统, 2023, 29(5):1647-1656. DING Man, YUAN Yunlei, ZHANG Xinxin, et al. Emotional design of product colors based on deep learning[J]. Computer Integrated Manufacturing System, 2023, 29(5):1647-1656.
[5] ZHANG Xinxin, YANG Minggang, SU Jianning, et al. Research on product color design decision driven by brand image[J]. Color Research & Application, 2020, 45(6):1202-1216.
[6] YEH Y. Prediction of optimized color design for sports shoes using an artificial neural network and genetic algorithm[J]. Applied Sciences, 2020, 10(5):1560-1579.
[7] DING Man, CHENG Yu, ZHANG Jinyong, et al. Product color emotional design based on a convolutional neural network and search neural network[J]. Color Research & Application, 2021, 46(6):1332-1346.
[8] 赵黎, 杨连贺, 黄新. 基于多目标蜂群优化算法的计算机辅助配色[J]. 计算机集成制造系统, 2018, 24(2):381-389. ZHAO Li, YANG Lianhe, HUANG Xin. Computer assisted color matching based on multi-objective bee colony optimization algorithm[J]. Computer Integrated Manufacturing System, 2018, 24(2):381-389.
[9] YANG Yanpu, TIAN Xing. Combining users' cognition noise with interactive genetic algorithms and trapezoidal fuzzy numbers for product color design[J]. Computational Intelligence and Neuroscience, 2019.
[10] GUO Fu, LI Fengxiang, MITSUO N, et al. Research on color optimization of tricolor product considering color harmony and users' emotion[J]. Color Research & Application, 2020, 45(1):156-171.
[11] WANG Yong, SONG Fanghao, LIU Yan, et al. Application of binary programming theory to product color planning with multiple constraints[J]. Color Research & Application, 2021, 46(5):1091-1105.
[12] 张栋豪, 刘振宇, 郏维强, 等. 知识图谱在智能制造领域的研究现状及其应用前景综述[J]. 机械工程学报, 2021, 57(5):90-113. ZHANG Donghao, LIU Zhenyu, JIA Weiqiang, et al. Review of the research status and application prospects of knowledge graph in intelligent manufacturing[J]. Journal of Mechanical Engineering, 2021, 57(5):90-113.
[13] 于泽源, 赵武, 张凯, 等. 支持产品迭代设计的知识推送方法[J]. 机械工程学报, 2022, 58(18):292-302. YU Zeyuan, ZHAO Wu, ZHANG Kai, et al. A knowledge push method for supporting product iterative design[J]. Journal of Mechanical Engineering, 2022, 58(18):292-302.
[14] 张祎, 孟小峰. InterTris:三元交互的领域知识图谱表示学习[J]. 计算机学报, 2014(8):1535-1548. ZHANG Yi, MENG Xiaofeng. InterTris:Domain knowledge graph representation learning for ternary interaction[J]. Journal of Computer Science, 2014(8):1535-1548.
[15] 刘鹏程, 孙林夫. 基于第三方云平台的服务价值链多链知识图谱构建[J]. 计算机集成制造系统, 2022, 28(2):612-627. LIU Pengcheng, SUN Linfu. Construction of a multi chain knowledge graph for service value chain based on third-party cloud platforms[J]. Computer Integrated Manufacturing System, 2022, 28(2):612-627.
[16] SUN Z, DENG Z H, NIE J Y, et al. RotatE:Knowledge graph embedding by relational rotation in complex space[J]. 2019:1-13.
[17] 刘高, 黄沈权, 龙安, 等. 基于超图网络的产品设计知识智能推荐方法研究[J]. 计算机应用研究, 2022, 39(10):2962-2967. LIU Gao, HUANG Shenquan, LONG An, et al. Research on intelligent recommendation method for product design knowledge based on hypergraph networks[J]. Computer Application Research, 2022, 39(10):2962-2967.
[18] 郭彩华, 王斌, 朱怀杰, 等. 增量的动态社会网络匿名化技术[J]. 计算机研究与发展, 2016, 53(6):1352-1364. GUO Caihua, WANG Bin, ZHU Huaijie, et al. Incremental dynamic social network anonymization technology[J]. Computer Research and Development, 2016, 53(6):1352-1364.
[19] MAO Mingson, LU Jie, HAN Jialin. Multiobjective e-commerce recommendations based on hypergraph ranking[J]. Information Sciences, 2018, 471:269-287.
[20] 郭正山, 左劼, 段磊, 等. 面向知识超图链接预测的生成对抗负采样方法[J]. 计算机研究与发展, 2022, 59(8):1742-1756. GUO Zhengshan, ZUO Jie, DUAN Lei, et al. Generative adversarial negative sampling method for knowledge hypergraph link prediction[J]. Computer Research and Development, 2022, 59(8):1742-1756.
[21] SHAFFI S, MUTHULAKSHMI I. Weighted PageRank algorithm search engine ranking model for web pages[J]. Intelligent Automation & Soft Computing, 2022, 36(1):183-192.
[22] BHUPINGERJIT S, DEEPAK K G, RAJ M S. Improved architecture of focused crawler on the basis of content and link analysis[J]. International Journal of Modern Education and Computer Science, 2017, 9(11):33-40.
[23] SUMITA G, NEELAM D, POONAM B. An approach for focused crawler to harvest digital academic documents in online digital libraries[J]. International Journal of Information Retrieval Research, 2019, 9(3):23-47.
[24] GU Jiakai, VO D N. Contextual Word2Vec model for understanding chinese out of vocabularies on online social media[J]. International Journal on Semantic Web and Information Systems, 2022, 18(1):1-14.
[25] LIU Ye, CHENG Wei, NIU Heran, et al. Review mining for experiential products incorporating Word2vec and review sentiment tendencies[J]. Procedia Computer Science, 2022, 214:1492-1499.
[26] LIANG Minhui, NIU Tiansen. Research on text classification techniques based on improved TF-IDF algorithm and LSTM inputs[J]. Procedia Computer Science, 2022, 208:460-470.
[27] LAURANS G, DESMET P. Introducing PrEmo2:New directions for the non-verbal measurement of emotion in design[J]. Industrial Design Engineering, , 2012:1-13.
[28] LOUISE C, DEN U, GERRY J, et al. Self-reported food-evoked emotions of younger adults, older normosmic adults, and older hyposmic adults as measured using the PrEmo2 tool and the affect grid[J]. Food Quality and Preference, 2016, 51:109-117.
[29] BODLAENDER H L, BRETTELL N, JOHNSON M, et al. Steiner trees for hereditary graph classes:a treewidth perspective[J]. Theoretical Computer Science, 2021, 867:30-39