Search

• Adopting the theme network crawler technology and natural language processing technology to deeply excavate product color emotion information from fragmented data, while using the RotatE knowledge graph to realize the transition from the color scheme as a whole to the color individual, and touching the sensitive and fine-grained user's emotional needs from the color root, and then completing the integration of the fragmented fuzzy front-end. • A product color-emotion association model based on a RotatE knowledge graph is proposed, which effectively handles product color synergistic relationship by using RotatE rotational characteristics and realizes the in-depth fusion of product color-emotion knowledge, and meanwhile the construction of a 3D Knowledge Graph also solves the problem of color emotion knowledge representation. • The PageRank algorithm is employed to calculate the contribution weights of primary and auxiliary colors. Moreover, the product color synergy value is calculated, the simulation of the product color synergy mechanism is realized, and accurately output the product color emotion design that meets the user's emotional needs. Thus, the efficiency of the product color design greatly improves, and the problem of color emotion knowledge conversion ambiguity is solved. To address the problem of fragmentation, integration difficulties in fuzzy front-end information, and ambiguity in color emotion knowledge representation and conversion within the current product color emotion design stage, this paper proposes a method based on 3D Knowledge Graph. The proposed approach aims to integrate product color emotion design into the "data knowledge + artificial intelligence" growth model, facilitating a beneficial knowledge output cycle driven by data. As for the proposed approach, it divides the design problem into three stages: in the first one, big data web crawler technology and natural language processing were employed to extract knowledge related to product color emotion design. In the second phase, the construction of a product color emotion imagery association model using the RotatE knowledge graph, thereby achieving knowledge fusion of product color emotion design, and all accumulated knowledge data is integrated into a 3D Knowledge Graph for visualization. Finally, in the third phase, the PageRank algorithm is applied to calculate primary and auxiliary color weight parameters, simulating the product color synergy mechanism and determining the color synergy effects. Then, realize the knowledge generation of product color emotional design. This approach combines the human visual experience feedback with extensive big data analysis, and accurately outputs the product color emotion design scheme that meets the user's emotional needs. Moreover, the effectiveness and applicability of the method are verified by an illustrative example involving modern machine tool. [ABSTRACT FROM AUTHOR]

• Constructed the correlation between user feature label and user emotion, and realized the judgment of user emotions by inputting feature labels. • Constructed the correlation between user emotion and product color, and used deep learning to complete the automatic generation of product color scheme. • Realized one-stop conversion from user feature label to product color, avoiding the result error caused by unclear information of user's own emotion. • Avoid the problem of incomplete expression of emotions in the generated results by mining potential user emotions. Current research in Product Color Emotional Design (PCED) often encounters limitations due to the ambiguity in users' emotional information expression, potentially compromising the effectiveness of the design scheme. This paper presents a novel PCED methodology that integrates dynamic field theory with deep learning, thus enabling one-stop generation from user feature labels to product color. Consequently, a product color design system is established, capable of generating color design schemes that align with users' emotional needs by solely incorporating user feature labels. This approach mitigates potential inaccuracies in generation results that could stem from users' direct expression of emotional information. The validity and applicability of the proposed method are demonstrated through a case study focusing on the color emotion design of an electric motorcycle. [ABSTRACT FROM AUTHOR]

The detection of volatile amines is necessary due to the serious toxicity hazards they pose to human skin, respiratory systems, and nervous systems. However, traditional amines detection methods require bulky equipment, high costs, and complex measurements. Herein, we report a new simple, rapid, convenient, and visual method for the detection of volatile amines based on the gas–solid reactions of tetrachloro-p-benzoquinone (TCBQ) and volatile amines. The gas–solid reactions of TCBQ with a variety of volatile amines showed a visually distinct color in a time-dependent manner. Moreover, TCBQ can be easily fabricated into simple and flexible rapid test strips for detecting and distinguishing n-propylamine from other volatile amines, including ethylamine, n-butyamine, n-pentamine, n-butyamine and dimethylamine, in less than 3 s without any equipment assistance. [ABSTRACT FROM AUTHOR]