ITR: Analogy, Knowledge Integration, and Task Modeling Tools for Intelligence Analysts

ITR：情报分析师的类比、知识整合和任务建模工具

• 批准号: 0325315
• 负责人: Kenneth Forbus
• 金额: $ 95万
• 依托单位: Northwestern University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2003
• 资助国家: 美国
• 起止时间: 2003-09-15 至 2008-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0325315&HistoricalAwards=false
• 关键词: ITR; Analogy; Knowledge; Integration; Task

Intelligence analysts must sift through massive amounts of information, using perspective gained from history and experience to pull together from disparate sources the best coherent picture of what is happening. Today's world has grown far more complex, but human cognitive abilities have remained unchanged. This project is tackling this problem by exploring how to tightly combine three kinds of AI techniques: deductive reasoning over a large common sense knowledge base, analogical reasoning, and intelligent information retrieval, to create new power tools for intelligence analysts. The hypothesis being explored is that these techniques can be combined synergistically, each overcoming limitations of the others. The team has access to detailed data about how analysts work and opportunities for feedback about prototypes through Cycorp's participation in ARDA/NIMD's Glass Box Analysis Environment, which records the information streams analysts use while working on unclassified but representative problems. This work could have a significant positive impact on homeland security.

情报分析人员必须对大量信息进行筛选，利用从历史和经验中获得的观点，从不同的来源中得出关于正在发生的事情的最佳连贯画面。 今天的世界已经变得更加复杂，但人类的认知能力却没有改变。 该项目通过探索如何将联合收割机三种人工智能技术紧密结合来解决这个问题：大常识知识库上的演绎推理，类比推理和智能信息检索，为情报分析人员创造新的动力工具。 正在探索的假设是，这些技术可以协同组合，每一个克服其他的限制。 通过Cycorp参与ARDA/NIMD的玻璃盒分析环境，该团队可以获得有关分析师如何工作的详细数据，并有机会获得有关原型的反馈，该环境记录了分析师在处理未分类但具有代表性的问题时使用的信息流。这项工作可能会对国土安全产生重大积极影响。