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 study aims at developing a Knowledge Management Implementation Framework for adoption by firms in the Ghanaian construction industry. Recent developments in the field of Knowledge management in the construction s...This study aims at developing a Knowledge Management Implementation Framework for adoption by firms in the Ghanaian construction industry. Recent developments in the field of Knowledge management in the construction sector have led to a renewed competition in driving organizational performance. However, the construction industry in Ghana lacks a knowledge management implementation framework that addresses the needs of the Ghanaian construction supply chain while a comprehensive approach to managing knowledge remains nebulous. The study adopted an extensive literature review of existing knowledge management models to provide the basis for the development of the proposed framework for Ghana. The proposed knowledge management implementation framework was subjected to testing and validation by project managers drawn from nineteen indigenous construction firms in Ghana. The technology acceptance model (TAM) was used as the criteria to validate the proposed knowledge management implementation framework. The proposed Guribie & Tengan knowledge management implementation framework was perceived to be useful, and easy to use and the intention to adopt and use was high among indigenous Ghanaian construction firms. The study recommends further validation using wider population to enhance the efficacy of the framework for wider industry acceptance to enhance organizational competitiveness and performance delivery.展开更多
Knowledge Management(KM)has become a dynamic concept for inquiry in research.The management of knowledge from multiple sources requires a systematic approach that can facilitate capturing all important aspects related...Knowledge Management(KM)has become a dynamic concept for inquiry in research.The management of knowledge from multiple sources requires a systematic approach that can facilitate capturing all important aspects related to a particular discipline,several KM frameworks have been designed to serve this purpose.This research aims to propose a Collaborative Knowledge Management(CKM)Framework that bridges gaps and overcomes weaknesses in existing frameworks.The paper also validates the framework by evaluating its effectiveness for the agriculture sector of Pakistan.A software LCWU aKMS was developed which serves as a practical implementation of the concepts behind the proposed CKMF framework.LCWU aKMS served as an effective system for rice leaf disease detection and identification.It aimed to enhance CKM through knowledge sharing,lessons learned,feedback on problem resolutions,help from co-workers,collaboration,and helping communities.Data were collected from 300 rice crop farmers by questionnaires based on hypotheses.Jennex Olfman model was used to estimate the effectiveness of CKMF.Various tests were performed including frequency measures of variables,Cronbach’s alpha reliability,and Pearson’s correlation.The research provided a KMS depicting KM and collaborative features.The disease detection module was evaluated using the precision and recall method and found to be 94.16%accurate.The system could replace the work of extension agents,making it a cost and time-effective initiative for farmer betterment.展开更多
The key activity to build semantic web is to build ontologies. But today, the theory and methodology of ontology construction is still far from ready. This paper proposed a theoretical framework for massive knowledge ...The key activity to build semantic web is to build ontologies. But today, the theory and methodology of ontology construction is still far from ready. This paper proposed a theoretical framework for massive knowledge management- the knowledge domain framework （KDF）, and introduces an integrated development environment （IDE） named large-scale ontology development environment （LODE）, which implements the proposed theoretical framework. We also compared LODE with other popular ontology development environments in this paper. The practice of using LODE on management and development of agriculture ontologies shows that knowledge domain framework can handle the development activities of large scale ontologies. Application studies based on the described briefly. principle of knowledge domain framework and LODE was展开更多
近年来,大语言模型(Large language model,LLM)在自然语言处理中取得重大进展.在模型足够大时,大语言模型涌现出传统的预训练语言模型(Pre-trained language model,PLM)不具备的推理能力.为了探究如何将大语言模型的涌现能力应用于中文...近年来,大语言模型(Large language model,LLM)在自然语言处理中取得重大进展.在模型足够大时,大语言模型涌现出传统的预训练语言模型(Pre-trained language model,PLM)不具备的推理能力.为了探究如何将大语言模型的涌现能力应用于中文实体链接任务,适配了以下四种方法:知识增强、适配器微调、提示学习和语境学习(In-context learning,ICL).在Hansel和CLEEK数据集上的实证研究表明,基于Qwen-7B/ChatGLM3-6B的监督学习方法超过基于小模型的方法,在Hansel-FS数据集上提升3.9%~11.8%,在Hansel-ZS数据集上提升0.7%~4.1%,在CLEEK数据集上提升0.6%~3.7%.而当模型参数量达到720亿时,Qwen-72B的无监督方法实现与监督微调Qwen-7B相近的结果(-2.4%~+1.4%).此外,大语言模型Qwen在长尾实体场景下有明显的优势(11.8%),且随着参数量的增加,优势会更加明显(13.2%).对错误案例进行分析(以下简称错误分析)发现,实体粒度和实体类别相关错误占比较高,分别为36%和25%.这表明在实体链接任务中,准确划分实体边界以及正确判断实体类别是提高系统性能的关键.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 study aims at developing a Knowledge Management Implementation Framework for adoption by firms in the Ghanaian construction industry. Recent developments in the field of Knowledge management in the construction sector have led to a renewed competition in driving organizational performance. However, the construction industry in Ghana lacks a knowledge management implementation framework that addresses the needs of the Ghanaian construction supply chain while a comprehensive approach to managing knowledge remains nebulous. The study adopted an extensive literature review of existing knowledge management models to provide the basis for the development of the proposed framework for Ghana. The proposed knowledge management implementation framework was subjected to testing and validation by project managers drawn from nineteen indigenous construction firms in Ghana. The technology acceptance model (TAM) was used as the criteria to validate the proposed knowledge management implementation framework. The proposed Guribie & Tengan knowledge management implementation framework was perceived to be useful, and easy to use and the intention to adopt and use was high among indigenous Ghanaian construction firms. The study recommends further validation using wider population to enhance the efficacy of the framework for wider industry acceptance to enhance organizational competitiveness and performance delivery.
文摘Knowledge Management(KM)has become a dynamic concept for inquiry in research.The management of knowledge from multiple sources requires a systematic approach that can facilitate capturing all important aspects related to a particular discipline,several KM frameworks have been designed to serve this purpose.This research aims to propose a Collaborative Knowledge Management(CKM)Framework that bridges gaps and overcomes weaknesses in existing frameworks.The paper also validates the framework by evaluating its effectiveness for the agriculture sector of Pakistan.A software LCWU aKMS was developed which serves as a practical implementation of the concepts behind the proposed CKMF framework.LCWU aKMS served as an effective system for rice leaf disease detection and identification.It aimed to enhance CKM through knowledge sharing,lessons learned,feedback on problem resolutions,help from co-workers,collaboration,and helping communities.Data were collected from 300 rice crop farmers by questionnaires based on hypotheses.Jennex Olfman model was used to estimate the effectiveness of CKMF.Various tests were performed including frequency measures of variables,Cronbach’s alpha reliability,and Pearson’s correlation.The research provided a KMS depicting KM and collaborative features.The disease detection module was evaluated using the precision and recall method and found to be 94.16%accurate.The system could replace the work of extension agents,making it a cost and time-effective initiative for farmer betterment.
基金supported by the Key Technology R&D Program of China during the 12th Five-Year Plan period:Super-Class Scientific and Technical Thesaurus and Ontology Construction Faced the Foreign Scientific and Technical Literature (2011BAH10B01)
文摘The key activity to build semantic web is to build ontologies. But today, the theory and methodology of ontology construction is still far from ready. This paper proposed a theoretical framework for massive knowledge management- the knowledge domain framework （KDF）, and introduces an integrated development environment （IDE） named large-scale ontology development environment （LODE）, which implements the proposed theoretical framework. We also compared LODE with other popular ontology development environments in this paper. The practice of using LODE on management and development of agriculture ontologies shows that knowledge domain framework can handle the development activities of large scale ontologies. Application studies based on the described briefly. principle of knowledge domain framework and LODE was
文摘近年来,大语言模型(Large language model,LLM)在自然语言处理中取得重大进展.在模型足够大时,大语言模型涌现出传统的预训练语言模型(Pre-trained language model,PLM)不具备的推理能力.为了探究如何将大语言模型的涌现能力应用于中文实体链接任务,适配了以下四种方法:知识增强、适配器微调、提示学习和语境学习(In-context learning,ICL).在Hansel和CLEEK数据集上的实证研究表明,基于Qwen-7B/ChatGLM3-6B的监督学习方法超过基于小模型的方法,在Hansel-FS数据集上提升3.9%~11.8%,在Hansel-ZS数据集上提升0.7%~4.1%,在CLEEK数据集上提升0.6%~3.7%.而当模型参数量达到720亿时,Qwen-72B的无监督方法实现与监督微调Qwen-7B相近的结果(-2.4%~+1.4%).此外,大语言模型Qwen在长尾实体场景下有明显的优势(11.8%),且随着参数量的增加,优势会更加明显(13.2%).对错误案例进行分析(以下简称错误分析)发现,实体粒度和实体类别相关错误占比较高,分别为36%和25%.这表明在实体链接任务中,准确划分实体边界以及正确判断实体类别是提高系统性能的关键.
