Big Data: Digitisation, Semantic Analysis, Topic Modelling, Visualisation and Exploration.

大数据：数字化、语义分析、主题建模、可视化和探索。

• 批准号: 101779
• 金额: $ 45.42万
• 依托单位: MICROPORTS.NET LIMITED
• 依托单位国家: 英国
• 项目类别: Collaborative R&D
• 财政年份: 2014
• 资助国家: 英国
• 起止时间: 2014 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=101779
• 关键词: Big; Data; Digitisation; Semantic; Analysis

There is significant need across health, care & education for a new, cost effective means by which unstructured data can be presented to professional users. Specifically, to more instantly and easily derive meaning in context from within the content of paper records and digital documents. There is also a critical need for better access to ‘joined-up’ relevant information across the medical and social care divide. (e.g. early warning signs for children at risk, early onset risk diagnosis of long term debilitation like dementia). The problem is that much of the information is hidden within the content of documents (unstructured data) rather than in the structured data input to and held within database driven systems. This project will unlock the hidden meaning from within document collections and provide innovative user experiences to support evidence-based decisions.

在健康，护理和教育中，有一种新的，具有成本效益的方式的需求，可以将非结构化数据呈现给专业用户。具体而言，从纸质记录和数字文档的内容中的上下文中更加立即，更容易地在上下文中得出含义。在整个医疗和社会护理鸿沟中，还需要更好地访问“加入”相关信息。 （例如，有风险的儿童的预警信号，长期衰减（如痴呆）的早期发作风险诊断）。问题在于，许多信息都隐藏在文档内容（非结构化数据）中，而不是在数据库驱动系统中的结构化数据输入中。该项目将从文档收集中解锁隐藏的含义，并提供创新的用户体验以支持基于证据的决策。