In the context of power generation companies, vast amounts of specialized data and expert knowledge have been accumulated. However, challenges such as data silos and fragmented knowledge hinder the effective utilizati...In the context of power generation companies, vast amounts of specialized data and expert knowledge have been accumulated. However, challenges such as data silos and fragmented knowledge hinder the effective utilization of this information. This study proposes a novel framework for intelligent Question-and-Answer (Q&A) systems based on Retrieval-Augmented Generation (RAG) to address these issues. The system efficiently acquires domain-specific knowledge by leveraging external databases, including Relational Databases (RDBs) and graph databases, without additional fine-tuning for Large Language Models (LLMs). Crucially, the framework integrates a Dynamic Knowledge Base Updating Mechanism (DKBUM) and a Weighted Context-Aware Similarity (WCAS) method to enhance retrieval accuracy and mitigate inherent limitations of LLMs, such as hallucinations and lack of specialization. Additionally, the proposed DKBUM dynamically adjusts knowledge weights within the database, ensuring that the most recent and relevant information is utilized, while WCAS refines the alignment between queries and knowledge items by enhanced context understanding. Experimental validation demonstrates that the system can generate timely, accurate, and context-sensitive responses, making it a robust solution for managing complex business logic in specialized industries.展开更多
Objective:This study aimed to develop a Nursing Retrieval-Augmented Generation(NurRAG)system based on large language models(LLMs)and to evaluate its accuracy and clinical applicability in nursing question answering.Me...Objective:This study aimed to develop a Nursing Retrieval-Augmented Generation(NurRAG)system based on large language models(LLMs)and to evaluate its accuracy and clinical applicability in nursing question answering.Methods:A multidisciplinary team consisting of nursing experts,artificial intelligence researchers,and information engineers collaboratively designed the NurRAG framework following the principles of retrieval-augmented generation.The system included four functional modules:1)construction of a nursing knowledge base through document normalization,embedding,and vector indexing;2)nursing question filtering using a supervised classifier;3)semantic retrieval and re-ranking for evidence selection;and 4)evidence-conditioned language model generation to produce citation-based nursing answers.The system was securely deployed on hospital intranet servers using Docker containers.Performance evaluation was conducted with 1,000 expert-verified nursing question–answer pairs.Semantic fidelity was assessed using Recall Oriented Understudy for Gisting Evaluation–Longest Common Subsequence(ROUGE-L),and clinical correctness was measured using Accuracy.Results:The NurRAG system achieved significant improvements in both semantic fidelity and answer accuracy compared with conventional large language models.For ChatGLM2-6B,ROUGE-L increased from(30.73±1.48)%to(64.27±0.27)%,and accuracy increased from(49.08±0.92)%to(75.83±0.35)%.For LLaMA2-7B,ROUGE-L increased from(28.76±0.89)%to(60.33±0.21)%,and accuracy increased from(43.27±0.83)%to(73.29±0.33)%.All differences were statistically significant(P<0.001).A quantitative case analysis further demonstrated that NurRAG effectively reduced hallucinated outputs and generated evidence-based,guideline-concordant nursing responses.Conclusion:The NurRAG system integrates domain-specific retrieval with LLMs generation to provide accurate,reliable,and traceable evidence-based nursing answers.The findings demonstrate the system’s feasibility and potential to improve the accuracy of clinical knowledge access,support evidence-based nursing decision-making,and promote the safe application of artificial intelligence in nursing practice.展开更多
This article examines the implementation of a virtual health assistant powered by Retrieval-Augmented Generation (RAG) and GPT-4, aimed at enhancing clinical support through personalized, real-time interactions with p...This article examines the implementation of a virtual health assistant powered by Retrieval-Augmented Generation (RAG) and GPT-4, aimed at enhancing clinical support through personalized, real-time interactions with patients. The system is hypothesized to improve healthcare accessibility, operational efficiency, and patient outcomes by automating routine tasks and delivering accurate health information. The assistant leverages natural language processing and real-time data retrieval models to respond to patient inquiries, schedule appointments, provide medication reminders, assist with symptom triage, and answer insurance-related questions. By integrating RAG-based virtual care, the system reduces the burden on healthcare specialists and helps mitigate healthcare disparities, particularly in rural areas where traditional care is limited. Although the initial scope of testing did not validate all potential benefits, the results demonstrated high patient satisfaction and strong response accuracy, both critical for systems of this nature. These findings underscore the transformative potential of AI-driven virtual health assistants in enhancing patient engagement, streamlining operational workflows, and improving healthcare accessibility, ultimately contributing to better outcomes and more cost-effective care delivery.展开更多
The global energy crisis and electricity shortage pose unprecedented challenges.Bio-based solar-driven ionic power generation devices with flexibility,photothermal self-healing and scalability hold great promise for s...The global energy crisis and electricity shortage pose unprecedented challenges.Bio-based solar-driven ionic power generation devices with flexibility,photothermal self-healing and scalability hold great promise for sustainable electricity and alleviating energy crisis.Here,inspired by plant transpiration,a multifunctional bio-based ion conductive elastomer with solar power generation capability was designed by engineered synergy among epoxy natural rubber,cellulose nanofibrils,lithium bis(trifluoromethane)sulfonimide and eumelanin.The film exhibits an outstanding stretchability(1072%)and toughness(22.7 MJ m^(-3)).The favorable synergy of low thermal conductivity,high hygroscopicity and photothermal conversion performance endowed the film with a large thermal gradient under light illumination,driving efficient water transpiration.Furthermore,the excellent interfacial compatibility between eumelanin and matrix facilitates the formation of space charge regions,which further enhances Li^(+)transport.The film demonstrates excellent evaporation rate(2.83 kg m^(-2)h^(-1)),output voltage(0.47 V)and conductivity(5.11×10^(-2)S m^(-1)).Notably,the film exhibits remarkable photothermal self-healing performance even in saline environment,achieving 99.6%healing efficiency of output voltage.Therefore,the film demonstrates significant prospects for applications in photo-thermoelectric generation and solar-driven ionic power generation.展开更多
The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location re...The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location reidentification and correlation attacks.To address these challenges,privacy-preserving trajectory generation methods are critical for applications relying on sensitive location data.This paper introduces DPIL-Traj,an advanced framework designed to generate synthetic trajectories while achieving a superior balance between data utility and privacy preservation.Firstly,the framework incorporates Differential Privacy Clustering,which anonymizes trajectory data by applying differential privacy techniques that add noise,ensuring the protection of sensitive user information.Secondly,Imitation Learning is used to replicate decision-making behaviors observed in real-world trajectories.By learning from expert trajectories,this component generates synthetic data that closely mimics real-world decision-making processes while optimizing the quality of the generated trajectories.Finally,Markov-based Trajectory Generation is employed to capture and maintain the inherent temporal dynamics of movement patterns.Extensive experiments conducted on the GeoLife trajectory dataset show that DPIL-Traj improves utility performance by an average of 19.85%,and in terms of privacy performance by an average of 12.51%,compared to state-of-the-art approaches.Ablation studies further reveal that DP clustering effectively safeguards privacy,imitation learning enhances utility under noise,and the Markov module strengthens temporal coherence.展开更多
With their intricate vectorial structures in space,optical skyrmions have significantly expanded the landscape of topological optics and light-matter interactions.We theoretically investigate high harmonic generation ...With their intricate vectorial structures in space,optical skyrmions have significantly expanded the landscape of topological optics and light-matter interactions.We theoretically investigate high harmonic generation in crystals driven by optical skyrmions.We find that although the skyrmion number is not conserved,the resulting high-order harmonics can exhibit a distinctive multi-vortex structure,whose features are shaped by both the topology of the optical skyrmions and the rotational symmetry of the crystal.The position of the vortex centers can be effectively tuned by employing different types of optical skyrmions.To elucidate the underlying physics,we develop a multi-absorption channel model based on the conservation laws of spin and orbital angular momentum.Our work explores the role of optical topology in extreme nonlinear light-matter interactions,offering new opportunities for the formation and manipulation of optical vortices and novel structured light fields in the visible and ultraviolet regimes.展开更多
With the rapid development of image-generative AI (artificial intelligence) technology, its application in undergraduate Landscape Architecture education has demonstrated significant potential. Based on this, the pres...With the rapid development of image-generative AI (artificial intelligence) technology, its application in undergraduate Landscape Architecture education has demonstrated significant potential. Based on this, the present study explores the implications of integrating image-generative AI into Landscape Architecture courses from three perspectives: stimulating students creative design potential, expanding approaches to form and concept generation, and enhancing the visualization of spatial scenes. Furthermore, it discusses application strategies from three dimensions: AI-assisted conceptual generation, human-machine collaboration for design refinement, and optimization of scheme presentation and evaluation. This paper aims to provide relevant educators with insights and references.展开更多
With the rise of AI-assisted education,many instructors and engineers seek to deliver high-quality programming courses online.However,crafting effective programming lectures remains a challenge,particularly for instru...With the rise of AI-assisted education,many instructors and engineers seek to deliver high-quality programming courses online.However,crafting effective programming lectures remains a challenge,particularly for instructors lacking pedagogical training or multilingual fluency.We present CourseAgent,a prompt-driven framework that leverages large language models(LLMs)to automatically generate Python tutorials,structured lecture scripts,and accompanying audio narrations.CourseAgent accepts raw code as input and transforms it into segmented,well-commented code blocks,adapting content to different difficulty levels and languages via prompt customization.Our system supports multilingual instruction(e.g.,Chinese,English),fine-grained control of pedagogical depth,and auto-generation of lecture videos.We evaluate the output generated by CourseAgent using real student feedback and feedback from in-service teachers,alongside automated assessments from LLMs.These evaluations demonstrate that the materials produced by CourseAgent are coherent,pedagogically sound,and comparable in quality to those created by experienced instructors.CourseAgent lowers the barrier to quality programming education and shows promise for scalable,personalized,and language-adaptive content generation.展开更多
Small datasets are often challenging due to their limited sample size.This research introduces a novel solution to these problems:average linkage virtual sample generation(ALVSG).ALVSG leverages the underlying data st...Small datasets are often challenging due to their limited sample size.This research introduces a novel solution to these problems:average linkage virtual sample generation(ALVSG).ALVSG leverages the underlying data structure to create virtual samples,which can be used to augment the original dataset.The ALVSG process consists of two steps.First,an average-linkage clustering technique is applied to the dataset to create a dendrogram.The dendrogram represents the hierarchical structure of the dataset,with each merging operation regarded as a linkage.Next,the linkages are combined into an average-based dataset,which serves as a new representation of the dataset.The second step in the ALVSG process involves generating virtual samples using the average-based dataset.The research project generates a set of 100 virtual samples by uniformly distributing them within the provided boundary.These virtual samples are then added to the original dataset,creating a more extensive dataset with improved generalization performance.The efficacy of the ALVSG approach is validated through resampling experiments and t-tests conducted on two small real-world datasets.The experiments are conducted on three forecasting models:the support vector machine for regression(SVR),the deep learning model(DL),and XGBoost.The results show that the ALVSG approach outperforms the baseline methods in terms of mean square error(MSE),root mean square error(RMSE),and mean absolute error(MAE).展开更多
High-precision optical frequency measurement serves as a cornerstone of modern science and technology,enabling advancements in fields ranging from fundamental physics to quantum information technologies.Obtaining prec...High-precision optical frequency measurement serves as a cornerstone of modern science and technology,enabling advancements in fields ranging from fundamental physics to quantum information technologies.Obtaining precise photon frequencies,especially in the ultraviolet or even extreme ultraviolet regimes,is a key goal in both light–matter interaction experiments and engineering applications.High-order harmonic generation(HHG)is an ideal light source for producing such photons.In this work,we propose an optical temporal interference model(OTIM)that establishes an analogy with multi-slit Fraunhofer diffraction(MSFD)to manipulate fine-frequency photon generation by exploiting the temporal coherence of HHG processes.Our model provides a unified physical framework for three distinct non-integer HHG generation schemes:single-pulse,shaped-pulse,and laser pulse train approaches,which correspond to single-MSFD-like,double-MSFD-like,and multi-MSFD-like processes,respectively.Arbitrary non-integer HHG photons can be obtained using our scheme.Our approach provides a new perspective for accurately measuring and controlling photon frequencies in fields such as frequency comb technology,interferometry,and atomic clocks.展开更多
Over the past decade,large-scale pre-trained autoregressive and diffusion models rejuvenated the field of text-guided image generation.However,these models require enormous datasets and parameters,and their multi-step...Over the past decade,large-scale pre-trained autoregressive and diffusion models rejuvenated the field of text-guided image generation.However,these models require enormous datasets and parameters,and their multi-step generation processes are often inefficient and difficult to control.To address these challenges,we propose CAFE-GAN,a CLIP-Projected GAN with Attention-Aware Generation and Multi-Scale Discrimination,which incorporates a pretrained CLIP model along with several key architectural innovations.First,we embed a coordinate attention mechanism into the generator to capture long-range dependencies and enhance feature representation.Second,we introduce a trainable linear projection layer after the CLIP text encoder,which aligns textual embeddings with the generator’s semantic space.Third,we design a multi-scale discriminator that leverages pre-trained visual features and integrates a feature regularization strategy,thereby improving training stability and discrimination performance.Experiments on the CUB and COCO datasets demonstrate that CAFE-GAN outperforms existing text-to-image generation methods,achieving lower Fréchet Inception Distance(FID)scores and generating images with superior visual quality and semantic fidelity,with FID scores of 9.84 and 5.62 on the CUB and COCO datasets,respectively,surpassing current state-of-the-art text-to-image models by varying degrees.These findings offer valuable insights for future research on efficient,controllable text-to-image synthesis.展开更多
The occurrence of severe thalassemia,an inherited blood disorder that is either blood-transfusiondependent or fatal,can be mitigated through carrier screening.Here,we aim to evaluate the effectiveness and outcomes of ...The occurrence of severe thalassemia,an inherited blood disorder that is either blood-transfusiondependent or fatal,can be mitigated through carrier screening.Here,we aim to evaluate the effectiveness and outcomes of pre-conceptional and early pregnancy screening initiatives for severe thalassemia prevention in a diverse population of 28,043 women.Using next-generation sequencing(NGS),we identify 4,226(15.07%)thalassemia carriers across 29 ethnic groups and categorize them into high-(0.75%),low-(25.86%),and unknown-risk(69.19%)groups based on their spouses'screening results.Post-screening follow-up reveals 59 fetuses with severe thalassemia exclusively in high-risk couples,underscoring the efficacy of risk classification.Among 25,053 live births over 6 months of age,two severe thalassemia infants were born to unknown-risk couples,which was attributed to incomplete screening and late NGS-based testing for a rare variant.Notably,64 rare variants are identified in 287 individuals,highlighting the genetic heterogeneity of thalassemia.We also observe that migrant flow significantly impacts carrier rates,with 93.90%of migrants to Chenzhou originating from high-prevalence regions in southern China.Our study demonstrates that NGS-based screening during pre-conception and early pregnancy is effective for severe thalassemia prevention,emphasizing the need for continuous screening efforts in areas with high and underestimated prevalence.展开更多
Thermomagnetic generation(TMG),a heat-to-electricity conversion technology based on the thermomagnetic effect,offers high reliability and broad adaptability to diverse heat sources.By exploiting the temperature-depend...Thermomagnetic generation(TMG),a heat-to-electricity conversion technology based on the thermomagnetic effect,offers high reliability and broad adaptability to diverse heat sources.By exploiting the temperature-dependent magnetization of thermomagnetic materials,TMG converts thermal energy into electrical energy through cyclic changes in magnetic flux based on Faraday's law.The performance of TMG systems is largely governed by the intrinsic properties of the working materials and the design of device architecture.Ideal TMG materials exhibit sharp and reversible magnetization transitions near the operating temperature,low thermal hysteresis,and high thermal conductivity.Device configurations can be broadly categorized into active and passive systems:active TMG devices rely on controlled thermal cycling and optimized magnetic circuits for enhanced output,whereas passive devices utilize self-actuated mechanical motion to generate electricity.In this topical review,we provide a comprehensive overview of recent advances in TMG materials and device configurations.Furthermore,we discuss future development trends and offer perspectives on experimental strategies to advance this field.展开更多
It remains difficult to automate the creation and validation of Unified Modeling Language(UML)dia-grams due to unstructured requirements,limited automated pipelines,and the lack of reliable evaluation methods.This stu...It remains difficult to automate the creation and validation of Unified Modeling Language(UML)dia-grams due to unstructured requirements,limited automated pipelines,and the lack of reliable evaluation methods.This study introduces a cohesive architecture that amalgamates requirement development,UML synthesis,and multimodal validation.First,LLaMA-3.2-1B-Instruct was utilized to generate user-focused requirements.Then,DeepSeek-R1-Distill-Qwen-32B applies its reasoning skills to transform these requirements into PlantUML code.Using this dual-LLM pipeline,we constructed a synthetic dataset of 11,997 UML diagrams spanning six major diagram families.Rendering analysis showed that 89.5%of the generated diagrams compile correctly,while invalid cases were detected automatically.To assess quality,we employed a multimodal scoring method that combines Qwen2.5-VL-3B,LLaMA-3.2-11B-Vision-Instruct and Aya-Vision-8B,with weights based on MMMU performance.A study with 94 experts revealed strong alignment between automatic and manual evaluations,yielding a Pearson correlation of r=0.82 and a Fleiss’Kappa of 0.78.This indicates a high degree of concordance between automated metrics and human judgment.Overall,the results demonstrated that our scoring system is effective and that the proposed generation pipeline produces UML diagrams that are both syntactically correct and semantically coherent.More broadly,the system provides a scalable and reproducible foundation for future work in AI-driven software modeling and multimodal verification.展开更多
Wing design is a critical factor in the aerodynamic performance of flapping-wing(FW)robots.Inspired by the natural wing structures of insects,bats,and birds,we explored how bio-mimetic wing vein morphologies,combined ...Wing design is a critical factor in the aerodynamic performance of flapping-wing(FW)robots.Inspired by the natural wing structures of insects,bats,and birds,we explored how bio-mimetic wing vein morphologies,combined with a bio-inspired double wing clap-and-fling mechanism,affect thrust generation.This study focused on increasing vertical force and payload capacity.Through systematic experimentation with various vein configurations and structural designs,we developed innovative wings optimized for thrust production.Comprehensive tests were conducted to measure aerodynamic forces,power consumption,and wing kinematics across a range of flapping frequencies.Additionally,wings with different aspect ratios,a key factor in wing design,were fabricated and extensively evaluated.The study also examined the role of bio-inspired vein layouts on wing flexibility,a critical component in improving flight efficiency.Our findings demonstrate that the newly developed wing design led to a 20%increase in thrust,achieving up to 30 g-force(gf).This research sheds light on the clap-and-fling effect and establishes a promising framework for bio-inspired wing design,offering significant improvements in both performance and payload capacity for FW robots.展开更多
Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural ...Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural artifacts online.As an effective medium,posters serve to attract public attention and facilitate broader engagement with cultural artifacts.However,existing poster generation methods mainly rely on fixed templates and manual design,which limits their scalability and adaptability to the diverse visual and semantic features of the artifacts.Therefore,we propose CAPGen,an automated aesthetic Cultural Artifacts Poster Generation framework built on a Multimodal Large Language Model(MLLM)with integrated iterative optimization.During our research,we collaborated with designers to define principles of graphic design for cultural artifact posters,to guide the MLLM in generating layout parameters.Later,we generated these parameters into posters.Finally,we refined the posters using an MLLM integrated with a multi-round iterative optimization mechanism.Qualitative results show that CAPGen consistently outperforms baseline methods in both visual quality and aesthetic performance.Furthermore,ablation studies indicate that the prompt,iterative optimization mechanism,and design principles significantly enhance the effectiveness of poster generation.展开更多
We are sorry for the mistakes of Affiliation,"a State Key Laboratory of Advanced Fiber Materials,Center for Advanced Low-Dimension Materials,Donghua University,Shanghai 201620,China"should be replaced by&quo...We are sorry for the mistakes of Affiliation,"a State Key Laboratory of Advanced Fiber Materials,Center for Advanced Low-Dimension Materials,Donghua University,Shanghai 201620,China"should be replaced by"a State Key Laboratory of Advanced Fiber Materials,Center for Advanced Low-Dimension Materials,College of Materials Science and Engineering,Donghua University,Shanghai 201620,China".We apologized for the inconvenience caused by this error.展开更多
In Human–Robot Interaction(HRI),generating robot trajectories that accurately reflect user intentions while ensuring physical realism remains challenging,especially in unstructured environments.In this study,we devel...In Human–Robot Interaction(HRI),generating robot trajectories that accurately reflect user intentions while ensuring physical realism remains challenging,especially in unstructured environments.In this study,we develop a multimodal framework that integrates symbolic task reasoning with continuous trajectory generation.The approach employs transformer models and adversarial training to map high-level intent to robotic motion.Information from multiple data sources,such as voice traits,hand and body keypoints,visual observations,and recorded paths,is integrated simultaneously.These signals are mapped into a shared representation that supports interpretable reasoning while enabling smooth and realistic motion generation.Based on this design,two different learning strategies are investigated.In the first step,grammar-constrained Linear Temporal Logic(LTL)expressions are created from multimodal human inputs.These expressions are subsequently decoded into robot trajectories.The second method generates trajectories directly from symbolic intent and linguistic data,bypassing an intermediate logical representation.Transformer encoders combine multiple types of information,and autoregressive transformer decoders generate motion sequences.Adding smoothness and speed limits during training increases the likelihood of physical feasibility.To improve the realism and stability of the generated trajectories during training,an adversarial discriminator is also included to guide them toward the distribution of actual robot motion.Tests on the NATSGLD dataset indicate that the complete system exhibits stable training behaviour and performance.In normalised coordinates,the logic-based pipeline has an Average Displacement Error(ADE)of 0.040 and a Final Displacement Error(FDE)of 0.036.The adversarial generator makes substantially more progress,reducing ADE to 0.021 and FDE to 0.018.Visual examination confirms that the generated trajectories closely align with observed motion patterns while preserving smooth temporal dynamics.展开更多
Objective To develop a clinical decision and prescription generation system(CDPGS)specifically for diarrhea in traditional Chinese medicine(TCM),utilizing a specialized large language model(LLM),Qwen-TCM-Dia,to standa...Objective To develop a clinical decision and prescription generation system(CDPGS)specifically for diarrhea in traditional Chinese medicine(TCM),utilizing a specialized large language model(LLM),Qwen-TCM-Dia,to standardize diagnostic processes and prescription generation.Methods Two primary datasets were constructed:an evaluation benchmark and a fine-tuning dataset consisting of fundamental diarrhea knowledge,medical records,and chain-ofthought(CoT)reasoning datasets.After an initial evaluation of 16 open-source LLMs across inference time,accuracy,and output quality,Qwen2.5 was selected as the base model due to its superior overall performance.We then employed a two-stage low-rank adaptation(LoRA)fine-tuning strategy,integrating continued pre-training on domain-specific knowledge with instruction fine-tuning using CoT-enriched medical records.This approach was designed to embed the clinical logic(symptoms→pathogenesis→therapeutic principles→prescriptions)into the model’s reasoning capabilities.The resulting fine-tuned model,specialized for TCM diarrhea,was designated as Qwen-TCM-Dia.Model performance was evaluated for disease diagnosis and syndrome type differentiation using accuracy,precision,recall,and F1-score.Furthermore,the quality of the generated prescriptions was compared with that of established open-source TCM LLMs.Results Qwen-TCM-Dia achieved peak performance compared to both the base Qwen2.5 model and five other open-source TCM LLMs.It achieved 97.05%accuracy and 91.48%F1-score in disease diagnosis,and 74.54%accuracy and 74.21%F1-score in syndrome type differentiation.Compared with existing open-source TCM LLMs(BianCang,HuangDi,LingDan,TCMLLM-PR,and ZhongJing),Qwen-TCM-Dia exhibited higher fidelity in reconstructing the“symptoms→pathogenesis→therapeutic principles→prescriptions”logic chain.It provided complete prescriptions,whereas other models often omitted dosages or generated mismatched prescriptions.Conclusion By integrating continued pre-training,CoT reasoning,and a two-stage fine-tuning strategy,this study establishes a CDPGS for diarrhea in TCM.The results demonstrate the synergistic effect of strengthening domain representation through pre-training and activating logical reasoning via CoT.This research not only provides critical technical support for the standardized diagnosis and treatment of diarrhea but also offers a scalable paradigm for the digital inheritance of expert TCM experience and the intelligent transformation of TCM.展开更多
Standards are the common language that consolidates global consensus and builds the most solid foundation for international partnerships.They are the cornerstone for global sustainable and high-quality development.You...Standards are the common language that consolidates global consensus and builds the most solid foundation for international partnerships.They are the cornerstone for global sustainable and high-quality development.Young students,with their active and vibrant minds,represent the future and hope of standardization.展开更多
文摘In the context of power generation companies, vast amounts of specialized data and expert knowledge have been accumulated. However, challenges such as data silos and fragmented knowledge hinder the effective utilization of this information. This study proposes a novel framework for intelligent Question-and-Answer (Q&A) systems based on Retrieval-Augmented Generation (RAG) to address these issues. The system efficiently acquires domain-specific knowledge by leveraging external databases, including Relational Databases (RDBs) and graph databases, without additional fine-tuning for Large Language Models (LLMs). Crucially, the framework integrates a Dynamic Knowledge Base Updating Mechanism (DKBUM) and a Weighted Context-Aware Similarity (WCAS) method to enhance retrieval accuracy and mitigate inherent limitations of LLMs, such as hallucinations and lack of specialization. Additionally, the proposed DKBUM dynamically adjusts knowledge weights within the database, ensuring that the most recent and relevant information is utilized, while WCAS refines the alignment between queries and knowledge items by enhanced context understanding. Experimental validation demonstrates that the system can generate timely, accurate, and context-sensitive responses, making it a robust solution for managing complex business logic in specialized industries.
基金supported by the Young and Middle-aged Research Fund Project of Shenzhen People's Hospital(Grant No.SYHL2024-N0010)the Shenzhen Basic Research Program(General Program,Grant No.JCYJ20240813104409013)。
文摘Objective:This study aimed to develop a Nursing Retrieval-Augmented Generation(NurRAG)system based on large language models(LLMs)and to evaluate its accuracy and clinical applicability in nursing question answering.Methods:A multidisciplinary team consisting of nursing experts,artificial intelligence researchers,and information engineers collaboratively designed the NurRAG framework following the principles of retrieval-augmented generation.The system included four functional modules:1)construction of a nursing knowledge base through document normalization,embedding,and vector indexing;2)nursing question filtering using a supervised classifier;3)semantic retrieval and re-ranking for evidence selection;and 4)evidence-conditioned language model generation to produce citation-based nursing answers.The system was securely deployed on hospital intranet servers using Docker containers.Performance evaluation was conducted with 1,000 expert-verified nursing question–answer pairs.Semantic fidelity was assessed using Recall Oriented Understudy for Gisting Evaluation–Longest Common Subsequence(ROUGE-L),and clinical correctness was measured using Accuracy.Results:The NurRAG system achieved significant improvements in both semantic fidelity and answer accuracy compared with conventional large language models.For ChatGLM2-6B,ROUGE-L increased from(30.73±1.48)%to(64.27±0.27)%,and accuracy increased from(49.08±0.92)%to(75.83±0.35)%.For LLaMA2-7B,ROUGE-L increased from(28.76±0.89)%to(60.33±0.21)%,and accuracy increased from(43.27±0.83)%to(73.29±0.33)%.All differences were statistically significant(P<0.001).A quantitative case analysis further demonstrated that NurRAG effectively reduced hallucinated outputs and generated evidence-based,guideline-concordant nursing responses.Conclusion:The NurRAG system integrates domain-specific retrieval with LLMs generation to provide accurate,reliable,and traceable evidence-based nursing answers.The findings demonstrate the system’s feasibility and potential to improve the accuracy of clinical knowledge access,support evidence-based nursing decision-making,and promote the safe application of artificial intelligence in nursing practice.
文摘This article examines the implementation of a virtual health assistant powered by Retrieval-Augmented Generation (RAG) and GPT-4, aimed at enhancing clinical support through personalized, real-time interactions with patients. The system is hypothesized to improve healthcare accessibility, operational efficiency, and patient outcomes by automating routine tasks and delivering accurate health information. The assistant leverages natural language processing and real-time data retrieval models to respond to patient inquiries, schedule appointments, provide medication reminders, assist with symptom triage, and answer insurance-related questions. By integrating RAG-based virtual care, the system reduces the burden on healthcare specialists and helps mitigate healthcare disparities, particularly in rural areas where traditional care is limited. Although the initial scope of testing did not validate all potential benefits, the results demonstrated high patient satisfaction and strong response accuracy, both critical for systems of this nature. These findings underscore the transformative potential of AI-driven virtual health assistants in enhancing patient engagement, streamlining operational workflows, and improving healthcare accessibility, ultimately contributing to better outcomes and more cost-effective care delivery.
基金financially supported by the National Natural Science Foundation of China(22175044)the Guangxi Natural Science Foundation(2023GXNSFDA026049)the Guangxi Major Talents Program(GXR-1BGQ2424023)。
文摘The global energy crisis and electricity shortage pose unprecedented challenges.Bio-based solar-driven ionic power generation devices with flexibility,photothermal self-healing and scalability hold great promise for sustainable electricity and alleviating energy crisis.Here,inspired by plant transpiration,a multifunctional bio-based ion conductive elastomer with solar power generation capability was designed by engineered synergy among epoxy natural rubber,cellulose nanofibrils,lithium bis(trifluoromethane)sulfonimide and eumelanin.The film exhibits an outstanding stretchability(1072%)and toughness(22.7 MJ m^(-3)).The favorable synergy of low thermal conductivity,high hygroscopicity and photothermal conversion performance endowed the film with a large thermal gradient under light illumination,driving efficient water transpiration.Furthermore,the excellent interfacial compatibility between eumelanin and matrix facilitates the formation of space charge regions,which further enhances Li^(+)transport.The film demonstrates excellent evaporation rate(2.83 kg m^(-2)h^(-1)),output voltage(0.47 V)and conductivity(5.11×10^(-2)S m^(-1)).Notably,the film exhibits remarkable photothermal self-healing performance even in saline environment,achieving 99.6%healing efficiency of output voltage.Therefore,the film demonstrates significant prospects for applications in photo-thermoelectric generation and solar-driven ionic power generation.
基金supported by the Natural Science Foundation of Fujian Province of China(2025J01380)National Natural Science Foundation of China(No.62471139)+3 种基金the Major Health Research Project of Fujian Province(2021ZD01001)Fujian Provincial Units Special Funds for Education and Research(2022639)Fujian University of Technology Research Start-up Fund(GY-S24002)Fujian Research and Training Grants for Young and Middle-aged Leaders in Healthcare(GY-H-24179).
文摘The generation of synthetic trajectories has become essential in various fields for analyzing complex movement patterns.However,the use of real-world trajectory data poses significant privacy risks,such as location reidentification and correlation attacks.To address these challenges,privacy-preserving trajectory generation methods are critical for applications relying on sensitive location data.This paper introduces DPIL-Traj,an advanced framework designed to generate synthetic trajectories while achieving a superior balance between data utility and privacy preservation.Firstly,the framework incorporates Differential Privacy Clustering,which anonymizes trajectory data by applying differential privacy techniques that add noise,ensuring the protection of sensitive user information.Secondly,Imitation Learning is used to replicate decision-making behaviors observed in real-world trajectories.By learning from expert trajectories,this component generates synthetic data that closely mimics real-world decision-making processes while optimizing the quality of the generated trajectories.Finally,Markov-based Trajectory Generation is employed to capture and maintain the inherent temporal dynamics of movement patterns.Extensive experiments conducted on the GeoLife trajectory dataset show that DPIL-Traj improves utility performance by an average of 19.85%,and in terms of privacy performance by an average of 12.51%,compared to state-of-the-art approaches.Ablation studies further reveal that DP clustering effectively safeguards privacy,imitation learning enhances utility under noise,and the Markov module strengthens temporal coherence.
基金supported by the National Natural Science Foundation of China (Grant Nos. 12234002, 92250303, 12474486, 12504301, and 12504396)the National Key Research and Development Program of China (Grant No. 2024YFA1612101)。
文摘With their intricate vectorial structures in space,optical skyrmions have significantly expanded the landscape of topological optics and light-matter interactions.We theoretically investigate high harmonic generation in crystals driven by optical skyrmions.We find that although the skyrmion number is not conserved,the resulting high-order harmonics can exhibit a distinctive multi-vortex structure,whose features are shaped by both the topology of the optical skyrmions and the rotational symmetry of the crystal.The position of the vortex centers can be effectively tuned by employing different types of optical skyrmions.To elucidate the underlying physics,we develop a multi-absorption channel model based on the conservation laws of spin and orbital angular momentum.Our work explores the role of optical topology in extreme nonlinear light-matter interactions,offering new opportunities for the formation and manipulation of optical vortices and novel structured light fields in the visible and ultraviolet regimes.
基金Supported by Applied Brand Course of Mianyang Teacher's College(Investigation and Monitoring of Natural Resources).
文摘With the rapid development of image-generative AI (artificial intelligence) technology, its application in undergraduate Landscape Architecture education has demonstrated significant potential. Based on this, the present study explores the implications of integrating image-generative AI into Landscape Architecture courses from three perspectives: stimulating students creative design potential, expanding approaches to form and concept generation, and enhancing the visualization of spatial scenes. Furthermore, it discusses application strategies from three dimensions: AI-assisted conceptual generation, human-machine collaboration for design refinement, and optimization of scheme presentation and evaluation. This paper aims to provide relevant educators with insights and references.
基金supported by the Zhejiang Province Leading Geese Plan(Grant No.2025C02025)the Guangdong Province Primary and Secondary School Teachers’Digital Literacy Enhancement Project 2025(Grant No.GDSZSYKT2025244).
文摘With the rise of AI-assisted education,many instructors and engineers seek to deliver high-quality programming courses online.However,crafting effective programming lectures remains a challenge,particularly for instructors lacking pedagogical training or multilingual fluency.We present CourseAgent,a prompt-driven framework that leverages large language models(LLMs)to automatically generate Python tutorials,structured lecture scripts,and accompanying audio narrations.CourseAgent accepts raw code as input and transforms it into segmented,well-commented code blocks,adapting content to different difficulty levels and languages via prompt customization.Our system supports multilingual instruction(e.g.,Chinese,English),fine-grained control of pedagogical depth,and auto-generation of lecture videos.We evaluate the output generated by CourseAgent using real student feedback and feedback from in-service teachers,alongside automated assessments from LLMs.These evaluations demonstrate that the materials produced by CourseAgent are coherent,pedagogically sound,and comparable in quality to those created by experienced instructors.CourseAgent lowers the barrier to quality programming education and shows promise for scalable,personalized,and language-adaptive content generation.
基金funding support from the National Science and Technology Council(NSTC),under Grant No.114-2410-H-011-026-MY3.
文摘Small datasets are often challenging due to their limited sample size.This research introduces a novel solution to these problems:average linkage virtual sample generation(ALVSG).ALVSG leverages the underlying data structure to create virtual samples,which can be used to augment the original dataset.The ALVSG process consists of two steps.First,an average-linkage clustering technique is applied to the dataset to create a dendrogram.The dendrogram represents the hierarchical structure of the dataset,with each merging operation regarded as a linkage.Next,the linkages are combined into an average-based dataset,which serves as a new representation of the dataset.The second step in the ALVSG process involves generating virtual samples using the average-based dataset.The research project generates a set of 100 virtual samples by uniformly distributing them within the provided boundary.These virtual samples are then added to the original dataset,creating a more extensive dataset with improved generalization performance.The efficacy of the ALVSG approach is validated through resampling experiments and t-tests conducted on two small real-world datasets.The experiments are conducted on three forecasting models:the support vector machine for regression(SVR),the deep learning model(DL),and XGBoost.The results show that the ALVSG approach outperforms the baseline methods in terms of mean square error(MSE),root mean square error(RMSE),and mean absolute error(MAE).
基金supported by the National Natural Science Foundation of China(Grant No.12304379)the Natural Science Foundation of Liaoning Province(Grant No.2024BS-269)the Guangdong Basic and Applied Basic Research Foundation(Grant No.025A1515011117)。
文摘High-precision optical frequency measurement serves as a cornerstone of modern science and technology,enabling advancements in fields ranging from fundamental physics to quantum information technologies.Obtaining precise photon frequencies,especially in the ultraviolet or even extreme ultraviolet regimes,is a key goal in both light–matter interaction experiments and engineering applications.High-order harmonic generation(HHG)is an ideal light source for producing such photons.In this work,we propose an optical temporal interference model(OTIM)that establishes an analogy with multi-slit Fraunhofer diffraction(MSFD)to manipulate fine-frequency photon generation by exploiting the temporal coherence of HHG processes.Our model provides a unified physical framework for three distinct non-integer HHG generation schemes:single-pulse,shaped-pulse,and laser pulse train approaches,which correspond to single-MSFD-like,double-MSFD-like,and multi-MSFD-like processes,respectively.Arbitrary non-integer HHG photons can be obtained using our scheme.Our approach provides a new perspective for accurately measuring and controlling photon frequencies in fields such as frequency comb technology,interferometry,and atomic clocks.
文摘Over the past decade,large-scale pre-trained autoregressive and diffusion models rejuvenated the field of text-guided image generation.However,these models require enormous datasets and parameters,and their multi-step generation processes are often inefficient and difficult to control.To address these challenges,we propose CAFE-GAN,a CLIP-Projected GAN with Attention-Aware Generation and Multi-Scale Discrimination,which incorporates a pretrained CLIP model along with several key architectural innovations.First,we embed a coordinate attention mechanism into the generator to capture long-range dependencies and enhance feature representation.Second,we introduce a trainable linear projection layer after the CLIP text encoder,which aligns textual embeddings with the generator’s semantic space.Third,we design a multi-scale discriminator that leverages pre-trained visual features and integrates a feature regularization strategy,thereby improving training stability and discrimination performance.Experiments on the CUB and COCO datasets demonstrate that CAFE-GAN outperforms existing text-to-image generation methods,achieving lower Fréchet Inception Distance(FID)scores and generating images with superior visual quality and semantic fidelity,with FID scores of 9.84 and 5.62 on the CUB and COCO datasets,respectively,surpassing current state-of-the-art text-to-image models by varying degrees.These findings offer valuable insights for future research on efficient,controllable text-to-image synthesis.
基金supported by the National Natural Science Foundation of China(81760037)Yunling Scholar Project of Yunnan Province(YNWR-YLXZ-2019-0005)+1 种基金Hunan Provincial Innovation Platform and Talent Program(2018SK4004)Hunan Provincial Natural Science Foundation(2019JJ80048).
文摘The occurrence of severe thalassemia,an inherited blood disorder that is either blood-transfusiondependent or fatal,can be mitigated through carrier screening.Here,we aim to evaluate the effectiveness and outcomes of pre-conceptional and early pregnancy screening initiatives for severe thalassemia prevention in a diverse population of 28,043 women.Using next-generation sequencing(NGS),we identify 4,226(15.07%)thalassemia carriers across 29 ethnic groups and categorize them into high-(0.75%),low-(25.86%),and unknown-risk(69.19%)groups based on their spouses'screening results.Post-screening follow-up reveals 59 fetuses with severe thalassemia exclusively in high-risk couples,underscoring the efficacy of risk classification.Among 25,053 live births over 6 months of age,two severe thalassemia infants were born to unknown-risk couples,which was attributed to incomplete screening and late NGS-based testing for a rare variant.Notably,64 rare variants are identified in 287 individuals,highlighting the genetic heterogeneity of thalassemia.We also observe that migrant flow significantly impacts carrier rates,with 93.90%of migrants to Chenzhou originating from high-prevalence regions in southern China.Our study demonstrates that NGS-based screening during pre-conception and early pregnancy is effective for severe thalassemia prevention,emphasizing the need for continuous screening efforts in areas with high and underestimated prevalence.
基金supported by the National Natural Science Foundation of China(Grant Nos.52171169 and 52101210)the National Key Research and Development Program of China(Grant No.2021YFB3501204)+3 种基金the State Key Laboratory for Advanced Metals and Materials(Grant No.2023-ZD01)USTB Concept Verification Funding Project(Grant No.GNYZ-2024-6)Fundamental Research Funds for the Central Universities(Grant No.FRF-TP-24-004A)USTB Research Center for International People-to-people Exchange in Science,Technology and Civilization(Grant Nos.2024KFZD001 and 2024KFYB004)。
文摘Thermomagnetic generation(TMG),a heat-to-electricity conversion technology based on the thermomagnetic effect,offers high reliability and broad adaptability to diverse heat sources.By exploiting the temperature-dependent magnetization of thermomagnetic materials,TMG converts thermal energy into electrical energy through cyclic changes in magnetic flux based on Faraday's law.The performance of TMG systems is largely governed by the intrinsic properties of the working materials and the design of device architecture.Ideal TMG materials exhibit sharp and reversible magnetization transitions near the operating temperature,low thermal hysteresis,and high thermal conductivity.Device configurations can be broadly categorized into active and passive systems:active TMG devices rely on controlled thermal cycling and optimized magnetic circuits for enhanced output,whereas passive devices utilize self-actuated mechanical motion to generate electricity.In this topical review,we provide a comprehensive overview of recent advances in TMG materials and device configurations.Furthermore,we discuss future development trends and offer perspectives on experimental strategies to advance this field.
基金supported by the DH2025-TN07-07 project conducted at the Thai Nguyen University of Information and Communication Technology,Thai Nguyen,Vietnam,with additional support from the AI in Software Engineering Lab.
文摘It remains difficult to automate the creation and validation of Unified Modeling Language(UML)dia-grams due to unstructured requirements,limited automated pipelines,and the lack of reliable evaluation methods.This study introduces a cohesive architecture that amalgamates requirement development,UML synthesis,and multimodal validation.First,LLaMA-3.2-1B-Instruct was utilized to generate user-focused requirements.Then,DeepSeek-R1-Distill-Qwen-32B applies its reasoning skills to transform these requirements into PlantUML code.Using this dual-LLM pipeline,we constructed a synthetic dataset of 11,997 UML diagrams spanning six major diagram families.Rendering analysis showed that 89.5%of the generated diagrams compile correctly,while invalid cases were detected automatically.To assess quality,we employed a multimodal scoring method that combines Qwen2.5-VL-3B,LLaMA-3.2-11B-Vision-Instruct and Aya-Vision-8B,with weights based on MMMU performance.A study with 94 experts revealed strong alignment between automatic and manual evaluations,yielding a Pearson correlation of r=0.82 and a Fleiss’Kappa of 0.78.This indicates a high degree of concordance between automated metrics and human judgment.Overall,the results demonstrated that our scoring system is effective and that the proposed generation pipeline produces UML diagrams that are both syntactically correct and semantically coherent.More broadly,the system provides a scalable and reproducible foundation for future work in AI-driven software modeling and multimodal verification.
基金Nguyen Tat Thanh University,Ho Chi Minh City,Vietnam for supporting this study。
文摘Wing design is a critical factor in the aerodynamic performance of flapping-wing(FW)robots.Inspired by the natural wing structures of insects,bats,and birds,we explored how bio-mimetic wing vein morphologies,combined with a bio-inspired double wing clap-and-fling mechanism,affect thrust generation.This study focused on increasing vertical force and payload capacity.Through systematic experimentation with various vein configurations and structural designs,we developed innovative wings optimized for thrust production.Comprehensive tests were conducted to measure aerodynamic forces,power consumption,and wing kinematics across a range of flapping frequencies.Additionally,wings with different aspect ratios,a key factor in wing design,were fabricated and extensively evaluated.The study also examined the role of bio-inspired vein layouts on wing flexibility,a critical component in improving flight efficiency.Our findings demonstrate that the newly developed wing design led to a 20%increase in thrust,achieving up to 30 g-force(gf).This research sheds light on the clap-and-fling effect and establishes a promising framework for bio-inspired wing design,offering significant improvements in both performance and payload capacity for FW robots.
基金supported by the National Key Research and Development Program of China(2023YFF0906502)the Postgraduate Research and Innovation Project of Hunan Province under Grant(CX20240473).
文摘Due to the digital transformation tendency among cultural institutions and the substantial influence of the social media platform,the demands of visual communication keep increasing for promoting traditional cultural artifacts online.As an effective medium,posters serve to attract public attention and facilitate broader engagement with cultural artifacts.However,existing poster generation methods mainly rely on fixed templates and manual design,which limits their scalability and adaptability to the diverse visual and semantic features of the artifacts.Therefore,we propose CAPGen,an automated aesthetic Cultural Artifacts Poster Generation framework built on a Multimodal Large Language Model(MLLM)with integrated iterative optimization.During our research,we collaborated with designers to define principles of graphic design for cultural artifact posters,to guide the MLLM in generating layout parameters.Later,we generated these parameters into posters.Finally,we refined the posters using an MLLM integrated with a multi-round iterative optimization mechanism.Qualitative results show that CAPGen consistently outperforms baseline methods in both visual quality and aesthetic performance.Furthermore,ablation studies indicate that the prompt,iterative optimization mechanism,and design principles significantly enhance the effectiveness of poster generation.
文摘We are sorry for the mistakes of Affiliation,"a State Key Laboratory of Advanced Fiber Materials,Center for Advanced Low-Dimension Materials,Donghua University,Shanghai 201620,China"should be replaced by"a State Key Laboratory of Advanced Fiber Materials,Center for Advanced Low-Dimension Materials,College of Materials Science and Engineering,Donghua University,Shanghai 201620,China".We apologized for the inconvenience caused by this error.
基金The authors extend their appreciation to Prince Sattam bin Abdulaziz University for funding this research work through the project number(PSAU/2024/01/32082).
文摘In Human–Robot Interaction(HRI),generating robot trajectories that accurately reflect user intentions while ensuring physical realism remains challenging,especially in unstructured environments.In this study,we develop a multimodal framework that integrates symbolic task reasoning with continuous trajectory generation.The approach employs transformer models and adversarial training to map high-level intent to robotic motion.Information from multiple data sources,such as voice traits,hand and body keypoints,visual observations,and recorded paths,is integrated simultaneously.These signals are mapped into a shared representation that supports interpretable reasoning while enabling smooth and realistic motion generation.Based on this design,two different learning strategies are investigated.In the first step,grammar-constrained Linear Temporal Logic(LTL)expressions are created from multimodal human inputs.These expressions are subsequently decoded into robot trajectories.The second method generates trajectories directly from symbolic intent and linguistic data,bypassing an intermediate logical representation.Transformer encoders combine multiple types of information,and autoregressive transformer decoders generate motion sequences.Adding smoothness and speed limits during training increases the likelihood of physical feasibility.To improve the realism and stability of the generated trajectories during training,an adversarial discriminator is also included to guide them toward the distribution of actual robot motion.Tests on the NATSGLD dataset indicate that the complete system exhibits stable training behaviour and performance.In normalised coordinates,the logic-based pipeline has an Average Displacement Error(ADE)of 0.040 and a Final Displacement Error(FDE)of 0.036.The adversarial generator makes substantially more progress,reducing ADE to 0.021 and FDE to 0.018.Visual examination confirms that the generated trajectories closely align with observed motion patterns while preserving smooth temporal dynamics.
基金National Key Research and Development Program of China(2024YFC3505400)Capital Clinical Project of Beijing Municipal Science&Technology Commission(Z221100007422092)Capital’s Funds for Health Improvement and Research(2024-1-2231).
文摘Objective To develop a clinical decision and prescription generation system(CDPGS)specifically for diarrhea in traditional Chinese medicine(TCM),utilizing a specialized large language model(LLM),Qwen-TCM-Dia,to standardize diagnostic processes and prescription generation.Methods Two primary datasets were constructed:an evaluation benchmark and a fine-tuning dataset consisting of fundamental diarrhea knowledge,medical records,and chain-ofthought(CoT)reasoning datasets.After an initial evaluation of 16 open-source LLMs across inference time,accuracy,and output quality,Qwen2.5 was selected as the base model due to its superior overall performance.We then employed a two-stage low-rank adaptation(LoRA)fine-tuning strategy,integrating continued pre-training on domain-specific knowledge with instruction fine-tuning using CoT-enriched medical records.This approach was designed to embed the clinical logic(symptoms→pathogenesis→therapeutic principles→prescriptions)into the model’s reasoning capabilities.The resulting fine-tuned model,specialized for TCM diarrhea,was designated as Qwen-TCM-Dia.Model performance was evaluated for disease diagnosis and syndrome type differentiation using accuracy,precision,recall,and F1-score.Furthermore,the quality of the generated prescriptions was compared with that of established open-source TCM LLMs.Results Qwen-TCM-Dia achieved peak performance compared to both the base Qwen2.5 model and five other open-source TCM LLMs.It achieved 97.05%accuracy and 91.48%F1-score in disease diagnosis,and 74.54%accuracy and 74.21%F1-score in syndrome type differentiation.Compared with existing open-source TCM LLMs(BianCang,HuangDi,LingDan,TCMLLM-PR,and ZhongJing),Qwen-TCM-Dia exhibited higher fidelity in reconstructing the“symptoms→pathogenesis→therapeutic principles→prescriptions”logic chain.It provided complete prescriptions,whereas other models often omitted dosages or generated mismatched prescriptions.Conclusion By integrating continued pre-training,CoT reasoning,and a two-stage fine-tuning strategy,this study establishes a CDPGS for diarrhea in TCM.The results demonstrate the synergistic effect of strengthening domain representation through pre-training and activating logical reasoning via CoT.This research not only provides critical technical support for the standardized diagnosis and treatment of diarrhea but also offers a scalable paradigm for the digital inheritance of expert TCM experience and the intelligent transformation of TCM.
文摘Standards are the common language that consolidates global consensus and builds the most solid foundation for international partnerships.They are the cornerstone for global sustainable and high-quality development.Young students,with their active and vibrant minds,represent the future and hope of standardization.
