欢迎访问《图学学报》 分享到:

图学学报 ›› 2025, Vol. 46 ›› Issue (4): 899-908.DOI: 10.11996/JG.j.2095-302X.2025040899

• 工业设计 • 上一篇    下一篇

面向产品云设计过程的数据建模与检索重排序方法

苏兆婧1,2(), 郭开元1, 杨梅1(), 丛宏宇1, 余隋怀2, 黄悦欣2   

  1. 1.山东科技大学艺术学院工业设计系,山东 青岛 266590
    2.西北工业大学工业设计与人机工效工信部重点实验室,陕西 西安 710072
  • 收稿日期:2024-10-12 修回日期:2025-03-12 出版日期:2025-08-30 发布日期:2025-08-11
  • 通讯作者:杨梅(1973-),女,教授,硕士。主要研究方向为工业设计理论及方法等。E-mail:skdyangmei@163.com
  • 第一作者:苏兆婧(1992-),女,讲师,博士。主要研究方向为计算机辅助工业设计、智能设计方法。E-mail:suzjid@gmail.com
  • 基金资助:
    教育部人文社会科学研究青年项目(24YJCZH260);山东省自然科学基金(ZR2024QG216);山东省社科规划专项重点项目(23BLYJ04)

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

SU Zhaojing1,2(), GUO Kaiyuan1, YANG Mei1(), CONG Hongyu1, YU Suihuai2, HUANG Yuexin2   

  1. 1. Department of Industrial Design, School of Art, Shandong University of Science and Technology, Qingdao Shandong 266590, China
    2. Key Laboratory of Industrial Design and Ergonomics, Ministry of Industry and Information Technology, Northwest Polytechnic University, Xi’an Shaanxi 710072, China
  • Received:2024-10-12 Revised:2025-03-12 Published:2025-08-30 Online:2025-08-11
  • First author:SU Zhaojing (1992-), lecturer, Ph.D. Her main research interests cover computer-aided industrial design, intelligent design methods. E-mail:suzjid@gmail.com
  • Supported by:
    Humanities and Social Sciences Research Project of the Ministry of Education(24YJCZH260);Shandong Provincial Natural Science Foundation(ZR2024QG216);Key Project of Social Science Planning in Shandong Province(23BLYJ04)

摘要:

为应对产品设计过程非结构化数据处理的挑战,解决通用检索系统排序策略固定、推送特定行业数据缺乏精细度的局限,提出了一种面向产品云设计过程的非结构化数据建模与检索方法。首先,面向产品云设计创新和决策过程的实际需求,构建非结构化数据处理框架。随后,提出了将科技文档版面分析问题视作目标检测问题的新思路,在领域科技文档数据库的基础上,构建了产品设计领域多要素版面分析与识别模型。通过构建数据特征空间和标签特征,结合LambdaMART算法,实现了领域科技文档数据的动态排序与高效检索。最后,通过案例验证了该方法在产品技术革新中的应用潜力,为数智驱动的设计迭代与精准决策提供了创新支持。

关键词: 产品云设计, 非结构化数据, 数据聚合, 版面分析, LambdaMART

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

中图分类号: