Dunhuang murals are an important part of human cultural heritage with extraordinary literary and historical value. However, with the influences of time and the environment, many murals have suffered large defects and require complete reconstructions of their historical information, which is difficult. Moreover, the manual restoration of murals is complicated and slow. We attempted to use deep learning techniques to restore two types of damaged murals, including central regular defects and random irregular defects. First, we created a dataset of 26,240 Dunhuang murals for model training. Second, we built an image restoration model based on U-net to automatically restore murals. We show that mapping global information to defective areas can effectively restore murals with random irregular defects. Compared to manual restoration, the proposed model significantly reduces the time and cost of restoration work. In addition, we propose a method for constructing and preserving the contour maps of mural images and present the model’s training process. Using the deep learning model, professional restorers can provide visual feedback on the restoration process to directly compare the restoration patterns of different rounds. This method implements observations of the filling-in process in the defective areas. Finally, we built a Dunhuang mural restoration system for professional restorers to restore, select, and share murals on an online platform.

High-altitude environments characterized by low air pressure, hypoxia, and strong solar radiation have a significant impact on human thermal comfort; however, existing thermal comfort theories and evaluation models are primarily developed under low-altitude climatic conditions, and their applicability in plateau regions remains limited. With the acceleration of urbanization and the increase in residential, tourism, and occupational activities in high-altitude areas, systematically reviewing the research progress on thermal comfort in such environments is of great practical significance. This study combines systematic literature retrieval and bibliometric analysis, based on the Web of Science Core Collection and China National Knowledge Infrastructure (CNKI) databases, to analyze relevant studies published since 2001. Using CiteSpace, research hotspots, collaboration networks, and evolutionary trends are visualized. The results indicate that current research hotspots mainly focus on physiological responses and thermal adaptation mechanisms under low-pressure and hypoxic conditions, thermal comfort regulation strategies for high-altitude buildings and environments, and the applicability and modification of conventional thermal comfort models. Emerging trends include multi-environmental factor coupling analysis, adaptive model development, region-specific building design approaches, and health-oriented comprehensive evaluation frameworks. The findings provide valuable references for building thermal environment design, regional revision of thermal comfort evaluation standards, and policy-making in high-altitude regions.

As technologies become increasingly diverse and complex, Intelligent Massage Systems (IMS) are evolving from traditional mechanically executed modes toward personalized and predictive health interventions. However, the field still lacks a unified grading standard for intelligence, making it difficult to quantitatively assess a system’s overall intelligence level. To address this gap, this paper proposes a task-driven six-level (L0–L5) classification framework and constructs a Massage-Driven Task (MDT) model that decomposes the massage process into six subtasks (S1–S6). Building on this, we design a three-dimensional evaluation scheme comprising a Functional Delegation Structure (FDS), an Anomaly Perception Mechanism (APM), and a Human–Machine Interaction Boundary (HMIB), and we select eight key performance indicators to quantify IMS intelligence across the perception–decision–actuation–feedback closed loop. We then determine indicator weights via the Delphi method and the Analytic Hierarchy Process (AHP), and obtain dimension-level scores and a composite intelligence score S0 using normalization and weighted aggregation. Threshold intervals for L0–L5 are defined through equal-interval partitioning combined with expert calibration, and sensitivity is verified on representative samples using ±10% data perturbations. Results show that, within typical error ranges, the proposed grading framework yields stable classification decisions and exhibits strong robustness. The framework not only provides the first reusable quantitative basis for grading IMS intelligence but also supports product design optimization, regulatory certification, and user selection.