Research on product target image cognition based on complex network theory and game theory

Abstract

Customer knowledge of a target image is an important and primary research topic related to the product design and development process. This paper presents research on product target image reasoning based on complex network theory and game theory. First, through an evaluation of the correlations among images, a complex network structure diagram with image words as nodes is constructed, and the network attributes of node degree, betweenness and closeness to the centre of the network are calculated. Then, based on the related methods of game theory, the weights of the three network attributes are evaluated, and a comprehensive calculation is carried out on the image to obtain the target image. Finally, an image entropy algorithm is used to validate the results. Taking a scooter as an example, a complex network of 12 image words is constructed by collecting the evaluations of a total of 12 subjects from different professional fields on 8 scooter samples; thus, the verification of the case is completed. This paper provides a more efficient and accurate target image evaluation method for product design or development, which is a new proposal for the product intelligent design process.

Research on the Intelligent Modeling Design of a Truck Front Face Driven by User Imagery

“…The group members focused on the emotional imagery words that were selected more than 4 times, confirming that there were 63 imagery words that needed to be removed. (2) The focus group used the KJ method to cluster the screened imagery words according to their semantic similarity and clustered the semantically similar imagery words into one category. In order to reduce cognitive differences between people and enhance the accuracy of semantic classification, this study uses an open-source word forest program based on the extended version of the synonym word forest as an auxiliary tool for synonym clustering.…”

“…Emotional imagery refers to a specific image or feeling in line with inner expectations produced by the fusion of the Kansei attributes of a certain object and one's own psychological cognitive state [1]. It is a deep-level consciousness activity of people's emotional cognition [2]. In product modeling design, imagery refers to the emotional associations related to cognition conveyed through modeling elements.…”

“…The contribution of this paper can be described as three innovations: (1) A self-made truck front face modeling dataset based on image pattern and imagery classification, and unsupervised learning using generative adversarial networks to obtain a truck front face generation model with the best generation effect under different imagery semantics, completing the exploration of rapid generation of imagery-driven intelligent design solutions for truck front face modeling. (2) The EEG experiments were used to obtain the EEG waveform maps of the subjects. Then, extract the ERP components related to cognition and evaluate the degree and accuracy of the generated solutions in line with the emotional imagery words to verify the feasibility and reliability of the user imagery-driven intelligent design method for truck front-end modeling.…”