摘要: 目的/ 意义 知识图谱作为人工智能时代的重要基石，为知识提供了一种新型组织与表示形式，而如何高效构建并 合理地管理知识图谱成为当前图谱研究人员的迫切需求。研究聚焦于已有的知识图谱构建管理系统，以期对多款已有系统做 全面深入的比较后，总结出当前知识图谱构建管理系统的建设新思路，并为更加通用、实用、好用的知识图谱构建管理系统 研发提供参考。 方法/ 过程 目前大量学者针对知识图谱核心构建流程提出了先进的算法与技术，众多知识图谱相关机构也 研发了多种类型的知识图谱构建管理系统，文中选择具有代表性的6 款国内外主流知识图谱构建管理系统进行调研，分析各 系统在业务流程中的系统特色，在系统的构建流程支持、技术选型及可用性等方面进行总结对比，并围绕当前用户对于知识 图谱构建管理系统的最新需求总结已有系统存在的局限。 结果/ 结论 在深入对比分析的基础上，文中研究了一体化知识图 谱协同构建管理系统的建设模式，总结并提出分布式协同构建、多图谱并行管理、多路径知识抽取、多类图存储引擎以及跨 媒体与多模态知识图谱等知识图谱构建管理系统建设的优化构想。
Abstract: Purpose/Significance Knowledge Graph has become a major research hotspot in the era of artificial intelligence due to its ability to provide a new means of organization and representation of knowledge. As the field continues to evolve, numerous scholars have proposed advanced algorithms and technologies for each core stage of constructing a knowledge graph, and many large domestic and foreign enterprises have also developed their independent knowledge graph management systems. However, the majority of these graph tools developed are designed for commercial use and are often too expensive and difficult to deploy locally for small and medium-sized research teams. This presents a challenge for information organizations such as research libraries with massive resources, which require a more adaptable, universal, and efficient tool to build and manage knowledge graphs. To meet this need, it is important to develop an open-source, user-friendly, and customizable knowledge graph management system that can be easily deployed by small and medium-sized research teams. Method/Process In summary, this article offers a thorough and informative analysis of six mainstream knowledge graph management systems, both domestically and internationally. It delves into the unique characteristics of each system within the business process and provides an in-depth comparative analysis based on several important factors, including system functionality, technology selection, open-source availability, and application domains. The article refers to the standard construction process of knowledge graphs and highlights the platform characteristics of each system during the construction process while also examining their limitations based on current data characteristics. In response to practical needs, the article focuses on multi-path, multi-engine, distributed, and collaborative construction, integrating advanced graph algorithms and considering a well-developed underlying graph storage strategy. Results/Conclusions As a result袁the article presents an in-depth analysis of the construction model for a collaborative development and management system of an integrated knowledge graph. It not only investigates the current state of knowledge graph management systems but also proposes novel optimization ideas. These ideas include distributed collaborative construction, which allows for simultaneous contributions from multiple sources, and parallel management of multiple graphs, enabling efficient organization and retrieval. Additionally, some suggestions are put forward: developing multi-path knowledge extraction techniques to enhance the knowledge acquisition process, and using specialized multi-graph storage engines for optimized storage and retrieval. Last, the article emphasizes the importance of incorporating cross-media and multimodal knowledge into the graph for a comprehensive representation of information.
|6. 基于知识图谱的黄河流域非遗资源 智能问答研究||2023-11-07|
|7. 基于文本挖掘与复杂网络的我国绿色消费领域 研究主题挖掘||2023-11-07|