The digital health field's pursuit of massive, personalized healthcare continuously faces constraints from doctors' resources and capacity limitations. Recently, the emergence of large language models (LLMs), with their remarkable comprehension and processing abilities, has revolutionized digital health and enhanced massive, personalized healthcare. Although these LLMs have achieved significant advancements, they have also introduced inevitable hallucinations, which impact patient safety when used in massive applications. To address these challenges, this study proposes a digital hospital for a massive, personalized, reliable healthcare service named the Chat Chain-Brain-based Doctor (CHATCBD). In addition, this study transforms the LLM-based diagnostic process into a digital hospital architecture, designs a controllable AI agents framework, and develops a self-audit mechanism to enhance their reliability. The proposed CHATCBD uses blockchain technology to decentralize external regulation of the LLMs' personalized diagnoses. It introduces a blockchain-based personalized routing management mechanism to improve patient-centered decision-making and designs a blockchain-based audit framework based on a proposed mathematical model that ensures both the professionalism and honesty of audits, serving as a safety net for addressing LLM hallucinations. The results of extensive experiments conducted on 13 datasets from multiple perspectives demonstrate that the proposed CHATCBD system can significantly enhance the capabilities of LLMs in personalized healthcare. The code used in this study can be found at https://github.com/LDDLQ/ChatCBD.

Genetic algorithms are machine learning algorithms inspired by the theory of natural evolution. By mimicking the process of natural selection and reproduction, genetic algorithms can provide high-quality solutions to a wide range of problems involving search, optimization, and learning. It can overcome some of the obstacles encountered by traditional search and optimization algorithms, especially for problems with many parameters and complex mathematical representations. To extend its application, this paper applies it to more subjective judging sessions. Firstly, after in-depth analysis, collation, and classification of judging data from several innovation competitions, genetic algorithms are subsequently used to optimize the allocation of works and judging experts, and the current standard score judging scheme is improved by non-linear correction of parameters. The results of the final data experiment show that the model greatly improves the concentration of scores and judging power and provides a reference for similar subjective scenario modelling optimization.

Many traditional ceramic techniques are inscribed on UNESCO’s Intangible Cultural Heritage lists; yet, expert scarcity, long training cycles, and stylistic homogenization impede intergenerational transmission and innovation. Although large language models offer new opportunities, research tailored to ceramics remains limited. To address this gap, we first construct EvalCera, the first open-source domain large language model evaluation dataset for ceramic knowledge, image analysis, and generation, and conduct large-scale assessments of existing general large language models on ceramic tasks, revealing their limitations. We then release the first ceramics-focused training corpus for large language models and, using it, develop CeramicGPT, the first domain-specific large language model for ceramics. Finally, we built ChatCAS, a workflow multi-agent system built on CeramicGPT and GPT-4o. Experiments show that our model and agents achieve the best performance on EvalCera (A) and (B) text tasks as well as (C) image generation. The code is publicly available.

Ceramics, as an intangible cultural heritage of humanity, carry rich historical legacy, cultural significance, and unique craftsmanship. However, the study and transmission of ceramic knowledge face significant barriers, including high learning thresholds and a lack of professional practitioners, which limits the dissemination of related knowledge. This severely restricts the popularization and innovative development of ceramic techniques. In recent years, large language models such as ChatGPT have gained widespread attention for their impressive knowledge reasoning and expressive capabilities, potentially aiding in the transmission of ceramic knowledge. This paper presents an empirical study to explore the application of ChatGPT in the field of ancient Chinese ceramics. Our findings show that, despite ChatGPT's strong generative abilities, it exhibits significant deficiencies in foundational professional knowledge within the ceramics field. Furthermore, ChatGPT's performance varies when addressing different types of ceramic-related questions, with the strongest performance in questions related to Yaozhou kiln ceramics and the weakest in those related to Ge kiln ceramics. Overall, our research provides valuable insights into the strengths and limitations of large language models, particularly ChatGPT, in the field of ceramics.