Intelligent Design of Agricultural Product Packaging Layout Based on Reinforcement Learning

被引:0
|
作者
Wang, Jianing [1 ]
Zhang, Yuan [1 ]
Zhu, Lei [2 ]
机构
[1] Beijing Inst Graph Commun, Sch Mech & Elect Engn, Beijing, Peoples R China
[2] Beijing Inst Graph Commun, Postal Technol R&D Ctr, Beijing, Peoples R China
关键词
Packaging of agricultural products; Automatic layout; Reinforcement learning;
D O I
10.1007/978-981-19-9024-3_55
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Along with the rapid development of e-commerce logistics, the volume of business in online sales of agricultural products is also growing, but e-commerce for agricultural products also suffers from a lack of funding for packaging design and difficulties in matching the packaging image with the product itself. One of the solutions to these problems is to create an intelligent design platform through a machine learning paradigm that can quickly and inexpensively meet the personalised design needs of users. One of the key technologies is intelligent layout design. In this paper, a deep deterministic strategic gradient (DDPG) algorithm is used to output the layout of the packaging layout by taking the graphic design elements of the packaging as input data, while taking into account constraints such as aesthetic principles, to achieve automatic layout and automatic output of the layout of the packaging appearance. Finally, through a user survey, it is found that the packaging layout designed using the algorithms in this paper can basically meet the requirements.
引用
收藏
页码:440 / 445
页数:6
相关论文
共 50 条
  • [41] An intelligent stock trading system based on reinforcement learning
    Lee, JW
    Kim, SD
    Lee, J
    Chae, J
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2003, E86D (02): : 296 - 305
  • [42] An Intelligent Offloading System Based on Multiagent Reinforcement Learning
    Weng, Yu
    Chu, Haozhen
    Shi, Zhaoyi
    SECURITY AND COMMUNICATION NETWORKS, 2021, 2021
  • [43] Research on Product Design Strategy Based on User Preference and Machine Learning Intelligent Recommendation
    Wu, Jie
    WIRELESS COMMUNICATIONS & MOBILE COMPUTING, 2022, 2022
  • [44] An Intelligent Routing Technology Based on Deep Reinforcement Learning
    Sun P.-H.
    Lan J.-L.
    Shen J.
    Hu Y.-X.
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2020, 48 (11): : 2170 - 2177
  • [45] Optimised design of soil reinforcement layout
    Gonzalez-Castejon, Javier
    Smith, Colin C.
    GEOTECHNIQUE, 2022, 72 (06): : 486 - 495
  • [46] Enhancing architectural space layout design by pretraining deep reinforcement learning agents
    Kakooee, Reza
    Dillenburger, Benjamin
    JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING, 2025, 12 (01) : 149 - 166
  • [47] Automatic Facility Layout Design Using Reinforcement Learning and a Analytic Hierarchy Process
    Ikeda H.
    Nakagawa H.
    Akagi H.
    Sekimoto F.
    Tsuchiya T.
    Journal of Japan Industrial Management Association, 2023, 74 (03) : 142 - 152
  • [48] Reinforcement Learning for Layout Planning - Modelling the Layout Problem as MDP
    Unger, Hendrik
    Boerner, Frank
    ADVANCES IN PRODUCTION MANAGEMENT SYSTEMS: ARTIFICIAL INTELLIGENCE FOR SUSTAINABLE AND RESILIENT PRODUCTION SYSTEMS (APMS 2021), PT III, 2021, 632 : 471 - 479
  • [49] Design of a reinforcement learning-based intelligent car transfer planning system for parking lots
    Guo, Feng
    Xu, Haiyu
    Xu, Peng
    Guo, Zhiwei
    MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2024, 21 (01) : 1058 - 1081
  • [50] Study on Usability of Agricultural Product Web Page Layout Based on Eye Tracker
    Liu lulu
    He Xiangzhen
    Wan Fucheng
    Xiong Zhangyuan
    PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON AUTOMATIC CONTROL AND INFORMATION ENGINEERING (ICACIE), 2016, 64 : 78 - 82