In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shippi...In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.展开更多
This critical review looks at the assessment of the application of artificial intelligence in handling legal documents with specific reference to medical negligence cases with a view of identifying its transformative ...This critical review looks at the assessment of the application of artificial intelligence in handling legal documents with specific reference to medical negligence cases with a view of identifying its transformative potentialities, issues and ethical concerns. The review consolidates findings that show the impact of AI in improving the efficiency, accuracy and justice delivery in the legal profession. The studies show increased efficiency in speed of document review and enhancement of the accuracy of the reviewed documents, with time efficiency estimates of 60% reduction of time. However, the review also outlines some of the problems that continue to characterize AI, such as data quality problems, biased algorithms and the problem of the opaque decision-making system. This paper assesses ethical issues related to patient autonomy, justice and non-malignant suffering, with particular focus on patient privacy and fair process, and on potential unfairness to patients. This paper’s review of AI innovations finds that regulations lag behind AI developments, leading to unsettled issues regarding legal responsibility for AI and user control over AI-generated results and findings in legal proceedings. Some of the future avenues that are presented in the study are the future of XAI for legal purposes, utilizing federated learning for resolving privacy issues, and the need to foster adaptive regulation. Finally, the review advocates for Legal Subject Matter Experts to collaborate with legal informatics experts, ethicists, and policy makers to develop the best solutions to implement AI in medical negligence claims. It reasons that there is great potential for AI to have a deep impact on the practice of law but when done, it must do so in a way that respects justice and on the Rights of Individuals.展开更多
With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers ...With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers has become particularly urgent.Currently,detection methods based on document structure and behavioral features encounter challenges in feature engineering,these methods not only have limited accuracy,but also consume large resources,and usually can only detect documents in specific formats,which lacks versatility and adaptability.To address such problems,this paper proposes a novel malicious document detection method-visualizing documents as GGE images(Grayscale,Grayscale matrix,Entropy).The GGE method visualizes the original byte sequence of the malicious document as a grayscale image,the information entropy sequence of the document as an entropy image,and at the same time,the grayscale level co-occurrence matrix and the texture and spatial information stored in it are converted into grayscale matrix image,and fuses the three types of images to get the GGE color image.The Convolutional Block Attention Module-EfficientNet-B0(CBAM-EfficientNet-B0)model is then used for classification,combining transfer learning and applying the pre-trained model on the ImageNet dataset to the feature extraction process of GGE images.As shown in the experimental results,the GGE method has superior performance compared with other methods,which is suitable for detecting malicious documents in different formats,and achieves an accuracy of 99.44%and 97.39%on Portable Document Format(PDF)and office datasets,respectively,and consumes less time during the detection process,which can be effectively applied to the task of detecting malicious documents in real-time.展开更多
This video series is the first experimental psychology documentary made in China.It focuses on analyzing professional theories to raise people’s general understanding of basic psychology.By combining innovative audio...This video series is the first experimental psychology documentary made in China.It focuses on analyzing professional theories to raise people’s general understanding of basic psychology.By combining innovative audiovisual narrative with psychological experiments,it zooms in on real human nature through discussing social hotspots from the perspectives of social psychology,cognitive psychology,and personality psychology,in order to help people find answers for their current psychological difficulties.展开更多
What Are You Up To Today?Chief Director:Wu Zijuan Length:12 Episodes Producer:bilibili Broadcasting Platform:bilibili Produced by China’s YouTube-like video sharing platform bilibili,the film is a series of short doc...What Are You Up To Today?Chief Director:Wu Zijuan Length:12 Episodes Producer:bilibili Broadcasting Platform:bilibili Produced by China’s YouTube-like video sharing platform bilibili,the film is a series of short documentaries presenting people's daily life in different jobs.It follows 12 individuals in their respective jobs and trades that keep society functioning.By focusing on their daily lives,the documentary films capture the hustle and bustle of the days that make up a hopeful life.展开更多
This paper highlights the critical role of medical device design and development documents within the quality system,including their compliance with regulatory standards,their function as a traceable record,their supp...This paper highlights the critical role of medical device design and development documents within the quality system,including their compliance with regulatory standards,their function as a traceable record,their support for all stages,and their use in risk and change management.It also covers document template creation,review record association,information management,adverse event traceability,and the reconciliation of differences in international declarations.展开更多
In nursing practice,electronic nursing records(ENRs)are an important component of patient care documents,but they also significantly increase administrative burdens.With the development of artificial intelligence tech...In nursing practice,electronic nursing records(ENRs)are an important component of patient care documents,but they also significantly increase administrative burdens.With the development of artificial intelligence technology,it has become possible to use large text models to assist in generating nursing documents.This article explores the application of generative AI in nursing documentation.Research has shown that the application of generative AI in nursing documents demonstrates significant potential,but also faces challenges in terms of quality and implementation.In terms of efficiency,AI assisted document tools can significantly reduce the administrative burden on nurses by reallocating time to direct patient care.Studies have shown that they can reduce document time by 21-30%.However,there are variables in the quality of AI generated records,and the content is often described as'textbook style',lacking patient specific details and appropriate medical terminology.Successful implementation relies on a specialized framework that includes strong stakeholder engagement and adaptation to nursing specific workflows and regulatory standards.The conclusion points out that current AI systems are most suitable for assisting in drafting nursing documents,and clinical validation remains crucial for patient safety and document integrity.展开更多
The rapid advancement of Large Language Models(LLMs)has enabled their application in diverse professional domains,including law.However,research on automatic judicial document generation remains limited,particularly f...The rapid advancement of Large Language Models(LLMs)has enabled their application in diverse professional domains,including law.However,research on automatic judicial document generation remains limited,particularly for taiwan region of China courts.This study proposes a keyword-guided training framework that enhances LLMs’ability to generate structured and semantically coherent judicial decisions in Chinese.The proposed method first employs LLMs to extract representative legal keywords from absolute court judgments.Then it integrates these keywords into Supervised Fine-Tuning(SFT)and Reinforcement Learning withHuman Feedback using Proximal Policy Optimization(RLHF-PPO).Experimental evaluations using models such as Chinese Alpaca 7B and TAIDE-LX-7B demonstrate that keyword-guided training significantly improves generation quality,achieving ROUGE-1,ROUGE-2,and ROUGE-L score gains of up to 17%,16%,and 20%,respectively.The results confirm that the proposed framework effectively aligns generated judgments with human-written legal logic and structural conventions.This research advances domainadaptive LLM fine-tuning strategies and establishes a technical foundation forAI-assisted judicial document generation in the taiwan region of China legal context.This research provides empirical evidence that domain-adaptive LLM fine-tuning strategies can significantly improve performance in complex,structured legal text generation.展开更多
In the process of building a new power system dominated by new energy sources,power storage is a key supporting technology that ensures the safe and stable operation of the power grid,enables the flexible regulation o...In the process of building a new power system dominated by new energy sources,power storage is a key supporting technology that ensures the safe and stable operation of the power grid,enables the flexible regulation of the system,and raises the level of new energy consumption.It is also key to achieving carbon peak and neutrality as well as energy transformation.展开更多
文摘In the international shipping industry, digital intelligence transformation has become essential, with both governments and enterprises actively working to integrate diverse datasets. The domain of maritime and shipping is characterized by a vast array of document types, filled with complex, large-scale, and often chaotic knowledge and relationships. Effectively managing these documents is crucial for developing a Large Language Model (LLM) in the maritime domain, enabling practitioners to access and leverage valuable information. A Knowledge Graph (KG) offers a state-of-the-art solution for enhancing knowledge retrieval, providing more accurate responses and enabling context-aware reasoning. This paper presents a framework for utilizing maritime and shipping documents to construct a knowledge graph using GraphRAG, a hybrid tool combining graph-based retrieval and generation capabilities. The extraction of entities and relationships from these documents and the KG construction process are detailed. Furthermore, the KG is integrated with an LLM to develop a Q&A system, demonstrating that the system significantly improves answer accuracy compared to traditional LLMs. Additionally, the KG construction process is up to 50% faster than conventional LLM-based approaches, underscoring the efficiency of our method. This study provides a promising approach to digital intelligence in shipping, advancing knowledge accessibility and decision-making.
文摘This critical review looks at the assessment of the application of artificial intelligence in handling legal documents with specific reference to medical negligence cases with a view of identifying its transformative potentialities, issues and ethical concerns. The review consolidates findings that show the impact of AI in improving the efficiency, accuracy and justice delivery in the legal profession. The studies show increased efficiency in speed of document review and enhancement of the accuracy of the reviewed documents, with time efficiency estimates of 60% reduction of time. However, the review also outlines some of the problems that continue to characterize AI, such as data quality problems, biased algorithms and the problem of the opaque decision-making system. This paper assesses ethical issues related to patient autonomy, justice and non-malignant suffering, with particular focus on patient privacy and fair process, and on potential unfairness to patients. This paper’s review of AI innovations finds that regulations lag behind AI developments, leading to unsettled issues regarding legal responsibility for AI and user control over AI-generated results and findings in legal proceedings. Some of the future avenues that are presented in the study are the future of XAI for legal purposes, utilizing federated learning for resolving privacy issues, and the need to foster adaptive regulation. Finally, the review advocates for Legal Subject Matter Experts to collaborate with legal informatics experts, ethicists, and policy makers to develop the best solutions to implement AI in medical negligence claims. It reasons that there is great potential for AI to have a deep impact on the practice of law but when done, it must do so in a way that respects justice and on the Rights of Individuals.
基金supported by the Natural Science Foundation of Henan Province(Grant No.242300420297)awarded to Yi Sun.
文摘With the development of anti-virus technology,malicious documents have gradually become the main pathway of Advanced Persistent Threat(APT)attacks,therefore,the development of effective malicious document classifiers has become particularly urgent.Currently,detection methods based on document structure and behavioral features encounter challenges in feature engineering,these methods not only have limited accuracy,but also consume large resources,and usually can only detect documents in specific formats,which lacks versatility and adaptability.To address such problems,this paper proposes a novel malicious document detection method-visualizing documents as GGE images(Grayscale,Grayscale matrix,Entropy).The GGE method visualizes the original byte sequence of the malicious document as a grayscale image,the information entropy sequence of the document as an entropy image,and at the same time,the grayscale level co-occurrence matrix and the texture and spatial information stored in it are converted into grayscale matrix image,and fuses the three types of images to get the GGE color image.The Convolutional Block Attention Module-EfficientNet-B0(CBAM-EfficientNet-B0)model is then used for classification,combining transfer learning and applying the pre-trained model on the ImageNet dataset to the feature extraction process of GGE images.As shown in the experimental results,the GGE method has superior performance compared with other methods,which is suitable for detecting malicious documents in different formats,and achieves an accuracy of 99.44%and 97.39%on Portable Document Format(PDF)and office datasets,respectively,and consumes less time during the detection process,which can be effectively applied to the task of detecting malicious documents in real-time.
文摘This video series is the first experimental psychology documentary made in China.It focuses on analyzing professional theories to raise people’s general understanding of basic psychology.By combining innovative audiovisual narrative with psychological experiments,it zooms in on real human nature through discussing social hotspots from the perspectives of social psychology,cognitive psychology,and personality psychology,in order to help people find answers for their current psychological difficulties.
文摘What Are You Up To Today?Chief Director:Wu Zijuan Length:12 Episodes Producer:bilibili Broadcasting Platform:bilibili Produced by China’s YouTube-like video sharing platform bilibili,the film is a series of short documentaries presenting people's daily life in different jobs.It follows 12 individuals in their respective jobs and trades that keep society functioning.By focusing on their daily lives,the documentary films capture the hustle and bustle of the days that make up a hopeful life.
文摘This paper highlights the critical role of medical device design and development documents within the quality system,including their compliance with regulatory standards,their function as a traceable record,their support for all stages,and their use in risk and change management.It also covers document template creation,review record association,information management,adverse event traceability,and the reconciliation of differences in international declarations.
基金supported by the Tightly Integrated Health Consortium Research Project(Grant ynlglht202412)。
文摘In nursing practice,electronic nursing records(ENRs)are an important component of patient care documents,but they also significantly increase administrative burdens.With the development of artificial intelligence technology,it has become possible to use large text models to assist in generating nursing documents.This article explores the application of generative AI in nursing documentation.Research has shown that the application of generative AI in nursing documents demonstrates significant potential,but also faces challenges in terms of quality and implementation.In terms of efficiency,AI assisted document tools can significantly reduce the administrative burden on nurses by reallocating time to direct patient care.Studies have shown that they can reduce document time by 21-30%.However,there are variables in the quality of AI generated records,and the content is often described as'textbook style',lacking patient specific details and appropriate medical terminology.Successful implementation relies on a specialized framework that includes strong stakeholder engagement and adaptation to nursing specific workflows and regulatory standards.The conclusion points out that current AI systems are most suitable for assisting in drafting nursing documents,and clinical validation remains crucial for patient safety and document integrity.
文摘The rapid advancement of Large Language Models(LLMs)has enabled their application in diverse professional domains,including law.However,research on automatic judicial document generation remains limited,particularly for taiwan region of China courts.This study proposes a keyword-guided training framework that enhances LLMs’ability to generate structured and semantically coherent judicial decisions in Chinese.The proposed method first employs LLMs to extract representative legal keywords from absolute court judgments.Then it integrates these keywords into Supervised Fine-Tuning(SFT)and Reinforcement Learning withHuman Feedback using Proximal Policy Optimization(RLHF-PPO).Experimental evaluations using models such as Chinese Alpaca 7B and TAIDE-LX-7B demonstrate that keyword-guided training significantly improves generation quality,achieving ROUGE-1,ROUGE-2,and ROUGE-L score gains of up to 17%,16%,and 20%,respectively.The results confirm that the proposed framework effectively aligns generated judgments with human-written legal logic and structural conventions.This research advances domainadaptive LLM fine-tuning strategies and establishes a technical foundation forAI-assisted judicial document generation in the taiwan region of China legal context.This research provides empirical evidence that domain-adaptive LLM fine-tuning strategies can significantly improve performance in complex,structured legal text generation.
文摘In the process of building a new power system dominated by new energy sources,power storage is a key supporting technology that ensures the safe and stable operation of the power grid,enables the flexible regulation of the system,and raises the level of new energy consumption.It is also key to achieving carbon peak and neutrality as well as energy transformation.
