Modeling of Knowledge with Imprecision in Linked Data Environment

关联数据环境中不精确知识建模

• 批准号: RGPIN-2015-06169
• 负责人: Reformat, Marek
• 金额: $ 1.31万
• 依托单位: University of Alberta
• 依托单位国家: 加拿大
• 项目类别: Discovery Grants Program - Individual
• 财政年份: 2016
• 资助国家: 加拿大
• 起止时间: 2016-01-01 至 2017-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=614490
• 关键词: Modeling; Knowledge; Imprecision; Linked; Data

The web becomes an enormous repository of data and information. Its constant growth creates a lot of opportunities as well as challenges for the users: How to embrace large amounts of data? How to find new pieces of information? How to deal with imprecision and missing data? How to convert data into information and then into knowledge? Fortunately, we are at the onset of significant and far-reaching changes in the way data are represented and stored on the web. One of the most fundamental aspects of the Semantic Web – Resource Description Framework – is generating a lot of attention. The application of Resource Description Framework induces a truly distributed and highly interconnected network of data. This creates an environment suitable for addressing the questions stated above.   The proposed research project puts a special emphasis on processes of constructing, updating and utilizing knowledge models built based on data and information obtained on the web. A key innovation of this project is a fusion of Computational Intelligence techniques with web technologies to fully explore data, including temporal data, and to take advantage of Resource Description Framework’s intrinsic interconnectivity. These activities will lead to establishing coherent rudiments of knowledge creation processes and systems. In a nutshell, the proposed methodology focuses on forming knowledge models using 1) a hierarchical clustering of Resource Description Framework data; 2) an automatic generalization of the constructed clusters; maintaining the models with incremental updates using aggregation and data assimilation techniques that take into account imprecision and confidence levels in different pieces of data, as well as temporal information about data; and visual and query-based exploration of knowledge models leading to multi-facet processing of data and knowledge.  The proposed project exhibits a direct and essential impact on the current and future research in the area of intelligent web systems. It is expected that the project will lead to significant contributions in methodologies focused on building new generation of systems that support the users in their activities related to collecting data from the web, and processing it towards creation of knowledge. This could lead to personal knowledge repositories that will help users with their activities of utilizing information available on the web.   The project would provide not only immediate results in the form of creation of intellectual property (new technologies, patents), but also in preparation of future generation of engineers and researchers equipped with highly competitive skills. These aspects of the project would support Canada’s pursuit to become one of the top technologically advanced countries. The project will contribute to the generation of employment and development of advanced technologies.

网络成为一个巨大的数据和信息仓库。它的不断增长为用户带来了很多机会和挑战：如何拥抱大量数据？如何找到新的信息？如何处理不精确和缺失的数据？如何将数据转化为信息，再转化为知识？幸运的是，我们正处于数据在网络上的表示和存储方式发生重大而深远变化的开端。语义Web最基本的方面之一-资源描述框架-正在引起人们的广泛关注。资源描述框架的应用，导致一个真正的分布式和高度互连的数据网络。这就创造了一个适合解决上述问题的环境。  拟议的研究项目提出了一个特别强调的过程中构建，更新和利用知识模型建立的基础上获得的数据和信息在网络上。该项目的一个关键创新是将计算智能技术与网络技术相结合，以充分探索数据，包括时态数据，并利用资源描述框架的内在互联性。这些活动将导致建立连贯的知识创造过程和系统的雏形。简而言之，所提出的方法集中于形成知识模型，使用1）资源描述框架数据的分层聚类; 2）所构建的聚类的自动泛化;使用聚合和数据同化技术来保持模型的增量更新，该技术考虑到不同数据片段中的不精确性和置信水平，以及关于数据的时间信息;以及知识模型的可视化和基于查询的探索，从而导致数据和知识的多方面处理。 该项目对智能Web系统领域当前和未来的研究具有直接和重要的影响。预计该项目将对侧重于建立新一代系统的方法学作出重大贡献，这些系统支持用户从网上收集数据并对其进行处理以创造知识。这可能导致个人知识库，将有助于用户利用网络上的信息的活动。  该项目不仅将以创造知识产权（新技术、专利）的形式提供直接成果，而且还将为未来一代工程师和研究人员提供具有高度竞争力的技能。该项目的这些方面将支持加拿大努力成为技术最先进的国家之一。该项目将有助于创造就业机会和发展先进技术。