Cultural heritage management poses significant challenges for museums due to fragmented data, limited intelligent frameworks, and insufficient applications. In response, a digital cultural heritage management approach based on knowledge graphs and deep learning algorithms is proposed to address the above challenges. A joint entity-relation triple extraction model is proposed to automatically identify entities and relations from fragmented data for knowledge graph construction. Additionally, a knowledge completion model is presented to predict missing information and improve knowledge graph completeness. Comparative simulations have been conducted to demonstrate the effectiveness and accuracy of the proposed approach for both the knowledge extraction model and the knowledge completion model. The efficacy of the knowledge graph application is corroborated through a case study utilizing ceramic data from the Palace Museum in China. This method may benefit users since it provides automated, interconnected, visually appealing, and easily accessible information about cultural heritage.

The acquisition of valuable design knowledge from massive fragmentary data is challenging for designers in conceptual product design. This study proposes a novel method for acquiring design knowledge by combining deep learning with knowledge graph. Specifically, the design knowledge acquisition method utilises the knowledge extraction model to extract design-related entities and relations from fragmentary data, and further constructs the knowledge graph to support design knowledge acquisition for conceptual product design. Moreover, the knowledge extraction model introduces ALBERT to solve memory limitation and communication overhead in the entity extraction module, and uses multi-granularity information to overcome segmentation errors and polysemy ambiguity in the relation extraction module. Experimental comparison verified the effectiveness and accuracy of the proposed knowledge extraction model. The case study demonstrated the feasibility of the knowledge graph construction with real fragmentary porcelain data and showed the capability to provide designers with interconnected and visualised design knowledge.

Evaluating the quality of the user experience (UX) of existing products is important for new product development. Conventional UX evaluation methods, such as questionnaire, have the disadvantages of the great subjective influence of investigators and limited number of participants. Meanwhile, online product reviews on e-commerce platforms express user evaluations of product UX. Because the reviews objectively reflect the user opinions and contain a large amount of data, they have potential as an information source for UX evaluation. In this context, this study explores how to evaluate product UX through using online product reviews. A pilot study is conducted to define the key elements of a review. Then, a systematic method of product UX evaluation based on reviews is proposed. The method includes three parts: extraction of key elements, integration of key elements, and quantitative evaluation based on rough number. The effectiveness of the proposed method is demonstrated by a case study using reviews of a wireless vacuum cleaner. Based on the proposed method, designers can objectively evaluate the UX quality of existing products and obtain detailed suggestions for product improvement.

Prolonged sitting in a fixed or constrained position exposes aircraft passengers to long-term static loading of their bodies, which has deleterious effects on passengers’ comfort throughout the duration of the flight. The previous studies focused primarily on office and driving sitting postures and few studies, however, focused on the sitting postures of passengers in aircraft. Consequently, the aim of the present study is to detect and recognize the sitting postures of aircraft passengers in relation to sitting discomfort. A total of 24 subjects were recruited for the experiment, which lasted for 2 h. Furthermore, a total of 489 sitting postures were extracted and the pressure data between subjects and seat was collected from the experiment. After the detection of sitting postures, eight types of sitting postures were classified based on key parts (trunk, back, and legs) of the human bodies. Thereafter, the eight types of sitting postures were recognized with the aid of pressure data of seat pan and backrest employing several machine learning methods. The best classification rate of 89.26% was obtained from the support vector machine (SVM) with radial basis function (RBF) kernel. The detection and recognition of the eight types of sitting postures of aircraft passengers in this study provided an insight into aircraft passengers’ discomfort and seat design.

Comfort is becoming one of the most important principles in the process of design and evaluation of civil aircraft cabins. However, the comprehensive quantitative evaluation of comfort in an aircraft cabin is a complicated issue because of the subjectivity of comfort perception and a large number of factors involved in the whole complex cabin system. A hybrid model combined with the Decision Making Trial and Evaluation Laboratory (DEMATEL) method and fuzzy comprehensive evaluation is proposed, which considers both the interrelation between the criteria and the fuzziness of subjective comfort perception concurrently. The result of the empirical study from the questionnaire survey in flight was consistent with that of the hybrid model. The proposed model is effective. It could provide a more reasonable priority to improve comfort in the aircraft cabin. According to the measured results of the cabin environment, the cabin facilities and layout, seats and service, the specific differences between the criteria can be displayed clearly, which is helpful to improve the cabin comfort level.