| 宗杰,赵卫国,张振江,旭日尕.基于神经网络的产品文化符号意象认知评价方法研究[J].包装工程,2021,42(8):261-267. |
| 基于神经网络的产品文化符号意象认知评价方法研究 |
| Image Cognitive Evaluation Method of Product Cultural Symbols Based on Neural Network |
| 投稿时间：2020-12-09 |
| DOI：10.19554/j.cnki.1001-3563.2021.08.035 |
| 中文关键词: 神经网络 感性工学 产品文化符号 意象认知 |
| 英文关键词: neural network Kansei engineering product cultural symbol image cognition |
| 基金项目: |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 利用神经网络建立产品文化符号特征元素与意象认知的映射关系，将文化符号的特征元素与用户的感知意象相关联。方法 首先，收集意象认知词汇，通过焦点小组选择符合整体意象认知的词汇，根据词频统计提取核心语义词汇;然后，利用里克特量表法针对测试样本进行核心语义词汇符合程度评价，并对语义核心词汇进行主成分分析，提取主成分权重系数，得到测试样本的综合意象评价值;最后，运用神经网络工具箱将特征元素与综合意象评价值进行映射关系分析。结果 将抽样数据与神经网络得出的数据进行对比验证，数值基本接近，将全部随机变量输入神经网络得到综合意象评价值最高和最低的特征元素组合，剔除相关性弱的特征元素。结论 通过基于神经网络的产品文化符号意象认知的评价方法可以建立文化符号特征元素与综合意象评价认知的映射关系，得到相关性强的特征元素，为运用理性的思维设计出满足用户文化需求的产品提供了数据与图形结构参考。 |
| 英文摘要: |
| The neural network is used to establish the mapping relationship between the characteristic elements of product cultural symbols and image cognition, and the characteristic elements of cultural symbols are associated with the user’s perceived images. We first collected the image cognitive vocabularies, selected the vocabularies that conform to the overall image cognition through focus group, and extracted the core semantic vocabulary according to the word frequency statistics, then used the Likert scale method to evaluate the core semantic vocabulary conformance of the test sample. The vocabulary was subjected to principal component analysis, and the principal component weight coefficients were extracted to obtain the comprehensive image evaluation value of the test sample. Finally, a neural network toolbox was used to analyze the mapping relationship between the feature elements and the comprehensive image evaluation value. The sample data and the data obtained by the neural network are compared and verified, and the values are basically close. All random variables were input into the neural network to obtain the combination of the highest and lowest feature elements with comprehensive image evaluation values, and the feature elements with weak correlation were eliminated. Through the evaluation method of product cultural symbol image cognition based on neural network, the mapping relationship between cultural symbol characteristic elements and comprehensive image evaluation cognition can be established, and feature elements with strong correlation can be obtained, which can be used to design rational thinking to meet the user's cultural needs. The product provides a reference for data and graphical structure. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|
