Materials of different allogeneic or xenogeneic or autologous origins are widely used as soft-tissue fillers or structural scaffolds in the field of cosmetic surgery, while complications including prosthesis infection, donor site deformity and filler embolization have always been difficult problems for plastic surgeons. The application of novel biomaterials may bring in hopeful solutions for these problems. Recently, some advanced biomaterials, such as regenerative biomaterials can effectively promote the repair of defective tissues, which have been proven to have good therapeutic as well as cosmetic effects in cosmetic surgery. Therefore, biomaterials with active compounds have drawn significant attention for the tissue regeneration of reconstructive and esthetic treatment. Some of these applications have achieved better clinical outcomes than traditional biological materials. This review summarized recent progress and clinical applications of advanced biomaterials in cosmetic surgery.

In response to the issues of poor content correlation and insufficient intelligent decision support in emergency plans for water conservancy projects, a method for intelligent generation of emergency plans based on knowledge graphs is proposed. Utilizing pre-trained language models (PTM) based on entity masking, the accuracy of entity recognition tasks is enhanced by uncovering contextual features surrounding the masked entities. By employing translations, rotations, and superpositions within the vector space, a multiview convolutional neural network (MCNN) is constructed to enhance the accuracy of relation extraction through complementary and integrated feature representation. Integrating PTM with MCNN enables the construction of an emergency entity relationship extraction method based on PTM-MCNN. Neo4j is utilized for storing entity relationship triplets to construct an emergency knowledge graph. Through the utilization of the mutual information criterion, knowledge retrieval and matching are performed to accomplish the intelligent generation of emergency plans. The results indicate that PTM-MCNN achieves high recognition accuracy (F1 score of 92.2%), ensuring the reliability of the generated emergency plans. Related studies can effectively improve the intelligence of emergency management of water conservancy projects.

The South-to-North Water Diversion Project consists of long-distance water delivery channels and a complicated geological environment along the way. To deal with the operation safety of the water conveyance channels in the middle route of the South-to-North Water Diversion Project, this study analyzes six failure modes: structural cracks, poor water delivery during ice periods, instability of canal slopes, material aging, abnormal leakage, and foundation defects. Based on FMEA, a multigranularity language evaluation method that can be converted into interval intuitionistic fuzzy numbers is used to evaluate the severity (S), occurrence (O), and detection difficulty (D) of the six failure modes. Interval intuitionistic fuzzy entropy is used to calculate the weights of the risk factors. Finally, a ranking model of each failure mode is built based on the TODIM method. The final ranking results show that the risk of abnormal leakage is the largest, and the risk of poor water delivery during ice periods is the smallest. The feasibility and validity of the calculation results are verified by comparing them with the ranking results of the traditional RPN and TOPSIS methods. The TODIM-FMEA risk assessment model offers a new solution to the problem of risk assessment for water transfer projects.

Using information technology to extract emergency decision-making knowledge from emergency plan documents is an essential means to enhance the efficiency and capacity of emergency management. To address the problems of numerous terminologies and complex relationships faced by emergency knowledge extraction of water diversion project, a multi-feature graph convolutional network (PTM-MFGCN) based on pre-trained model is proposed. Initially, through the utilization of random masking of domain-specific terminologies during pre-training, the model’s comprehension of the meaning and application of such terminologies within specific fields is enhanced, thereby augmenting the network’s proficiency in extracting professional terminologies. Furthermore, by introducing a multi-feature adjacency matrix to capture a broader range of neighboring node information, thereby enhancing the network’s ability to handle complex relationships. Lastly, we utilize the PTM-MFGCN to achieve the extraction of emergency entity relationships in water diversion project, thus constructing a knowledge graph for water diversion emergency management. The experimental results demonstrate that PTM-MFGCN exhibits improvements of 2.84% in accuracy, 4.87% in recall, and 5.18% in F1 score, compared to the baseline model. Relevant studies can effectively enhance the efficiency and capability of emergency management, mitigating the impact of unforeseen events on engineering safety.

Knowledge graph completion (KGC), the process of predicting missing knowledge through known triples, is a primary focus of research in the field of knowledge graphs. As an important graph representation technique in deep learning, graph neural networks (GNNs) perform well in knowledge graph completion, but most existing graph neural network-based knowledge graph completion methods tend to aggregate neighborhood information directly and individually, ignoring the rich hierarchical semantic structure of KGs. As a result, how to effectively deal with multi-level complex relations is still not well resolved. In this study, we present a hierarchical knowledge graph completion technique that combines both relation-level and entity-level attention and incorporates a weight matrix to enhance the significance of the embedded information under different semantic conditions. Furthermore, it updates neighborhood information to the central entity using a hierarchical aggregation approach. The proposed model enhances the capacity to capture hierarchical semantic feature information and is adaptable to various scoring functions as decoders, thus yielding robust results. We conducted experiments on a public benchmark dataset and compared it with several state-of-the-art models, and the experimental results indicate that our proposed model outperforms existing models in several aspects, proving its superior performance and validating the effectiveness of the model.

Knowledge graph embedding is a method to predict missing links in knowledge graphs by learning the interactions between embedded entities and relations in a continuous low-dimensional space. Current research on convolution-based models tends to provide sufficient interactions for extracting potential knowledge. However, sufficient interactions do not mean that they are reasonable. Our studies find that reasonable interactions can further stimulate knowledge extraction capability. Reasonable interactions need to ensure that the elements participating in interactions are disordered and in a reasonable number. To model reasonable interactions that cannot be specifically quantified, we propose a concise and effective model IntME to address this challenge. In detail, we utilize checked feature reshaping and disordered matrix multiplication to form two different types of feature maps to ensure the disorder of the interacting elements and control the number of elements before feature fusion by the shapes of the feature maps after channel scaling reshaping. In feature fusion, we employ large convolution filters and pointwise filters for the deep and shallow linear fusion of feature interactions, which can take into account both explicit and implicit knowledge extraction capability. The evaluations of four benchmark datasets show that IntME has a powerful performance in convolution-based models and a lower training cost, and also demonstrate that our proposed approaches based on reasonable interactions can effectively improve knowledge discovery capability.