Data modeling and retrieval re-ranking methods for cloud-based product design processes

doi:10.11996/JG.j.2095-302X.2025040899

Abstract

Abstract:

An unstructured data modeling and retrieval method tailored for cloud-based product design was proposed to address the challenges of unstructured data processing in product design, and to overcome the limitations of conventional retrieval systems with fixed ranking strategies and lack of precision for specific industry data First, a framework for unstructured data processing was developed to meet the practical needs of innovation and decision-making for cloud-based product design. Next, a novel approach redefined layout analysis of scientific documents as an object detection problem, building a multi-element layout analysis and recognition model within the context of domain-specific scientific document databases. By constructing a data feature space and label features, combined with the LambdaMART algorithm, dynamic ranking and efficient retrieval of domain-specific scientific document data were achieved. Finally, case studies validated the proposed method’s potential for application in product innovation, providing novel support for data-driven design iteration and precise decision-making.

Key words: cloud-based product design, unstructured data, data aggregation, layout analysis, LambdaMART

CLC Number:

TB472

SU Zhaojing, GUO Kaiyuan, YANG Mei, CONG Hongyu, YU Suihuai, HUANG Yuexin. Data modeling and retrieval re-ranking methods for cloud-based product design processes[J]. Journal of Graphics, 2025, 46(4): 899-908.

Figures/Tables 15

References 41

[1]	余隋怀, 王鹏超, 王磊, 等. 基于知识工程的产品设计研究综述[J]. 机械工程学报, 2024, 60(13): 216-234.
	YU S H, WANG P C, WANG L, et al. Research review of product design based on knowledge engineering[J]. Journal of Mechanical Engineering, 2024, 60(13): 216-234 (in Chinese).
[2]	LI L. 数据智能市场趋势分析[R]. 互联网数据中心, 2024.
	LI L. Data intelligence market trend analysis[R]. Internet Data Center, 2024 (in Chinese).
[3]	屈鹏飞. 复杂产品生命周期设计知识大数据集成和应用研究[D]. 杭州: 浙江大学, 2016.
	QU P F. Knowledge big data integration and application research of life cycle design for complex product[D]. Hangzhou: Zhejiang University, 2016 (in Chinese).
[4]	HOU X G, GOU B C, CHEN D K, et al. A semantic data-driven knowledge base construction method to assist designers in design inspiration based on traditional motifs[J]. Advanced Engineering Informatics, 2023, 56: 101987.
[5]	MATA M P, AHMED-KRISTENSEN S, SHEA K. Implementation of design rules for perception into a tool for three-dimensional shape generation using a shape grammar and a parametric model[J]. Journal of Mechanical Design, 2019, 141(1): 11101.
[6]	ABDALLAH R, MOHAMED HUSSEIN F. Impact of semiotics and morphological semantics on self-evident product (café chair as a sample)[J]. Journal of Design Sciences and Applied Arts, 2022, 3(2): 336-344.
[7]	张书涛, 王世杰, 刘世锋, 等. 产品形态多意象蛛网灰靶决策模型[J]. 图学学报, 2022, 43(3): 548-557.
	ZHANG S T, WANG S J, LIU S F, et al. Cobweb grey target decision-making model of multi-Kansei image in product form[J]. Journal of Graphics, 2022, 43(3): 548-557 (in Chinese).
[8]	罗仕鉴, 边泽, 张宇飞, 等. 基于形态匹配的产品仿生设计融合[J]. 计算机集成制造系统, 2020, 26(10): 2633-2641. DOI
	LUO S J, BIAN Z, ZHANG Y F, et al. Product bionic fusion design based on shape matching[J]. Computer Integrated Manufacturing Systems, 2020, 26(10): 2633-2641 (in Chinese).
[9]	AVIKAL S, SINGH R, RASHMI R. QFD and Fuzzy Kano model based approach for classification of aesthetic attributes of SUV car profile[J]. Journal of Intelligent Manufacturing, 2020, 31(2): 271-284.
[10]	LI F Z, KANT S, ARAKI S, et al. Neural networks for fashion image classification and visual search[EB/OL]. [2024-06-12]. https://arxiv.org/abs/2005.08170.
[11]	KANG X H, NAGASAWA S Y, WU Y X, et al. Emotional design of bamboo chair based on deep convolution neural network and deep convolution generative adversarial network[J]. Journal of Intelligent and Fuzzy Systems, 2023, 44(2): 1977-1989.
[12]	HUANG J Y, ZHANG X F. Application of fashion element trend prediction model integrating AM and EfficientNet-b7 models in art design[J]. Scalable Computing: Practice and Experience, 2024, 25(4): 2756-2769.
[13]	苏兆婧, 余隋怀, 初建杰, 等. 面向云服务平台的产品感性评价及标注模型[J]. 计算机集成制造系统, 2021, 27(3): 868-877. DOI
	SU Z J, YU S H, CHU J J, et al. Evaluation and annotation model of product Kansei attributes on cloud service platform[J]. Computer Integrated Manufacturing Systems, 2021, 27(3): 868-877 (in Chinese).
[14]	CONG Y F, YU S H, CHU J J, et al. A small sample data-driven method: user needs elicitation from online reviews in new product iteration[J]. Advanced Engineering Informatics, 2023, 56: 101953.
[15]	REN P J, LIU X D, ZHANG W G. Consumer preference analysis: diverse preference learning with online ratings[J]. Omega, 2024, 125: 103019.
[16]	WANG J W, HU K, ZHONG Z Y, et al. Detect-order-construct: a tree construction based approach for hierarchical document structure analysis[J]. Pattern Recognition, 2024, 156: 110836.
[17]	郭鑫, 黄泽川, 王杰, 等. 人机混合交互的产品设计知识图谱构建及智能推理方法[J]. 机械工程学报, 2025, 61(3): 142-153.
	GUO X, HUANG Z C, WANG J, et al. Knowledge graph construction and intelligent reasoning methods for human-computer hybrid interaction in product design[J]. Journal of Mechanical Engineering, 2025, 61(3): 142-153 (in Chinese).
[18]	吕伶, 李华, 王武. 基于增强特征提取网络与语义特征融合的多方向文本检测[J]. 图学学报, 2024, 45(1): 56-64. DOI
	LV L, LI H, WANG W. Multi-directional text detection based on the fusion of enhanced feature extraction network and semantic feature[J]. Journal of Graphics, 2024, 45(1): 56-64 (in Chinese). DOI
[19]	王鹏, 朱韦龙. 基于大数据的产品族本体造型意象挖掘方法研究[J]. 图学学报, 2021, 42(6): 1051-1060.
	WANG P, ZHU W L. Research on product family ontology modeling image mining method based on big data[J]. Journal of Graphics, 2021, 42(6): 1051-1060 (in Chinese).
[20]	方伟光, 郭宇, 廖文和, 等. 基于本体的复杂产品设计知识表示和标注方法[J]. 计算机集成制造系统, 2016, 22(9): 2063-2071.
	FANG W G, GUO Y, LIAO W H, et al. Knowledge representation and annotation method based on ontology for complex products' design[J]. Computer Integrated Manufacturing Systems, 2016, 22(9): 2063-2071 (in Chinese).
[21]	代风, 翟翔, 施国强, 等. 面向航天产品研制的知识网络本体建模方法[J]. 浙江大学学报(工学版), 2018, 52(10): 2023-2034.
	DAI F, ZHAI X, SHI G Q, et al. Modeling ontological knowledge network for aerospace equipment development[J]. Journal of Zhejiang University (Engineering Science), 2018, 52(10): 2023-2034 (in Chinese).
[22]	LI M D, LOU S H, ZHENG H, et al. A cognitive analysis-based key concepts derivation approach for product design[J]. Expert Systems with Applications, 2024, 236: 121289.
[23]	YIN Y, DING S Y, ZHANG X Y, et al. Cultural product design concept generation with symbolic semantic information expression using GPT[EB/OL]. [2024-06-12]. https://my.idc.com/getdoc.jsp?containerId=CHC51598824&pageType=PRINTFRIENDLY.
[24]	赵芳华, 吴雪镕, 张新新, 等. 跨模态视角下产品形态设计方法[EB/OL]. 计算机集成制造系统. (2024-04-30) [2024-06- 12]. https://doi.org/10.13196/j.cims.2023.0494.
	ZHAO F H, WU X R, ZHANG X X, et al. Product form design method from a cross modal perspective[EB/OL]. Computer Integrated Manufacturing Systems. (2024-04-30)[2024-06-12]. https://doi.org/10.13196/j.cims.2023.0494. (in Chinese).
[25]	LI X G, WANG Y, SHA Z H. Deep learning methods of cross-modal tasks for conceptual design of product shapes: a review[J]. Journal of Mechanical Design, 2023, 145(4): 041401.
[26]	朱上上, 于慧伶, 董烨楠, 等. 融合消费者群体创造的产品创意设计方法[J]. 机械工程学报, 2024, 60(5): 276-287.
	ZHU S S, YU H L, DONG Y N, et al. A product creative design method that incorporates the creation of consumer groups[J]. Journal of Mechanical Engineering, 2024, 60(5): 276-287 (in Chinese).
[27]	WU J H. A design methodology for form-based knowledge reuse and representation[J]. Information & Management, 2009, 46(7): 365-375.
[28]	KANG Y B, KRISHNASWAMY S, ZASLAVSKY A. A retrieval strategy for case-based reasoning using similarity and association knowledge[J]. IEEE Transactions on Cybernetics, 2014, 44(4): 473-487.
[29]	UNGER C, BÜHMANN L, LEHMANN J, et al. Template-based question answering over RDF data[C]// The 21st International Conference on World Wide Web. New York: ACM, 2012: 639-648.
[30]	GUO J F, CAI Y Q, FAN Y X, et al. Semantic models for the first-stage retrieval: a comprehensive review[J]. ACM Transactions on Information Systems (TOIS), 2022, 40(4): 66.
[31]	YANG S, LI Q, LI W H, et al. Dual-level representation enhancement on characteristic and context for image-text retrieval[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(11): 8037-8050.
[32]	沈思, 严大钰, 卞嘉欣, 等. 基于学术知识图谱的增强语义表示与检索[J]. 湖南大学学报(自然科学版), 2024, 51(6): 108-118.
	SHEN S, YAN D Y, BIAN J X, et al. Enhanced semantic representation and retrieval based on academic knowledge graph[J]. Journal of Hunan University (Natural Sciences), 2024, 51(6): 108-118 (in Chinese).
[33]	XU Z T, CRUZ M J, GUEVARA M, et al. Retrieval-augmented generation with knowledge graphs for customer service question answering[C]// The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2024: 2905-2909.
[34]	李洁. 数据驱动下数字图书馆知识发现服务创新模式与策略研究[D]. 吉林: 吉林大学, 2019.
	LI J. Data-driven knowledge discovery innovation in digital library: modes and strategies[D]. Jilin: Jilin University, 2019 (in Chinese).
[35]	GE Z, LIU S T, WANG F, et al. YOLOX:exceeding YOLO series in 2021[EB/OL]. [2024-0612]. https://arxiv.org/abs/2107.08430.
[36]	QIN T, LIU T Y, XU J, et al. LETOR: a benchmark collection for research on learning to rank for information retrieval[J]. Information Retrieval, 2010, 13(4): 346-374.
[37]	CHAPELLE O, CHANG Y. Yahoo! Learning to rank challenge overview[EB/OL]. [2024-07-12]. https://dl.acm.org/doi/10.5555/3045754.3045756.
[38]	谢康. 基于在线排序学习的生物通路检索方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2021.
	XIE K. Research on biological pathway retrieval method based on online learning to rank[D]. Harbin: Harbin Institute of Technology, 2021 (in Chinese).
[39]	LUCCHESE C, NARDINI F M, ORLANDO S, et al. Interpretable ranking using LambdaMART[EB/OL]. [2024-08-12]. https://dblp.uni-trier.de/db/conf/iir/iir2022.html#Lucchese N00V22.
[40]	韩保礼. 基于图知识库的分布式信息检索集合选择方法[D]. 杭州: 浙江大学, 2017.
	HAN B L. Graph-knowledge-bases based collection selection for distributed information retrieval[D]. Hangzhou: Zhejiang University, 2017 (in Chinese).
[41]	RUSSELL B C, TORRALBA A, MURPHY K P, et al. LabelMe: a database and web-based tool for image annotation[J]. International Journal of Computer Vision, 2008, 77(1): 157-173.

数据来源	数据类型	数目
科技文献数据库	期刊论文	2212
	会议论文	166
	年鉴	6
专利数据库	发明专利	1380
	实用新型专利	2868
	外观设计专利	289
设计标准库	国家标准	2
设计标准库	行业标准	8
新闻信息	新闻	28
新闻信息	报纸	0
行业观点	行业观点	79
研究报告	研究报告	13

数据来源	数据类型	数目
科技文献数据库	期刊论文	2212
	会议论文	166
	年鉴	6
专利数据库	发明专利	1380
	实用新型专利	2868
	外观设计专利	289
设计标准库	国家标准	2
设计标准库	行业标准	8
新闻信息	新闻	28
新闻信息	报纸	0
行业观点	行业观点	79
研究报告	研究报告	13

特征类型	特征内容
词频	题目的归一化词频
	摘要的归一化词频
	正文的归一化词频
	全文的归一化词频
	题目的对数词频
	摘要的对数词频
	正文的对数词频
	全文的对数词频
逆文档频率	题目的逆文档频率
	摘要的逆文档频率
	正文的逆文档频率
	全文的逆文档频率
词频-逆文档频率	题目的词频-逆文档频率
	摘要的词频-逆文档频率
	正文的词频-逆文档频率
	全文的词频-逆文档频率
BM25	题目的BM25
	摘要的BM25
	正文的BM25
	全文的BM25
线性插值平滑的 LMIR	题目基于线性插值平滑的LMIR分数
	摘要基于线性插值平滑的LMIR分数
	正文基于线性插值平滑的LMIR分数
	全文基于线性插值平滑的LMIR分数
狄里克雷 (Dirichlet) 平滑方法的 LMIR	题目基于Dirichlet平滑方法的LMIR分数
	摘要基于Dirichlet平滑方法的LMIR分数
	正文基于Dirichlet平滑方法的LMIR分数
	全文基于Dirichlet平滑方法的LMIR分数
绝对折扣平滑法的 LMIR	题目基于绝对折扣平滑法的LMIR分数
	摘要基于绝对折扣平滑法的LMIR分数
	正文基于绝对折扣平滑法的LMIR分数
	全文基于绝对折扣平滑法的LMIR分数

特征类型	特征内容
词频	题目的归一化词频
	摘要的归一化词频
	正文的归一化词频
	全文的归一化词频
	题目的对数词频
	摘要的对数词频
	正文的对数词频
	全文的对数词频
逆文档频率	题目的逆文档频率
	摘要的逆文档频率
	正文的逆文档频率
	全文的逆文档频率
词频-逆文档频率	题目的词频-逆文档频率
	摘要的词频-逆文档频率
	正文的词频-逆文档频率
	全文的词频-逆文档频率
BM25	题目的BM25
	摘要的BM25
	正文的BM25
	全文的BM25
线性插值平滑的 LMIR	题目基于线性插值平滑的LMIR分数
	摘要基于线性插值平滑的LMIR分数
	正文基于线性插值平滑的LMIR分数
	全文基于线性插值平滑的LMIR分数
狄里克雷 (Dirichlet) 平滑方法的 LMIR	题目基于Dirichlet平滑方法的LMIR分数
	摘要基于Dirichlet平滑方法的LMIR分数
	正文基于Dirichlet平滑方法的LMIR分数
	全文基于Dirichlet平滑方法的LMIR分数
绝对折扣平滑法的 LMIR	题目基于绝对折扣平滑法的LMIR分数
	摘要基于绝对折扣平滑法的LMIR分数
	正文基于绝对折扣平滑法的LMIR分数
	全文基于绝对折扣平滑法的LMIR分数

要素名称	要素数量
要素名称	训练集	验证集	测试集
题目(Title)	407	86	46
作者(Author)	463	96	57
摘要(Abstract)	366	77	43
正文(Text)	3634	703	365
表格(Table)	513	85	41
插图(Figure)	2027	399	204