SBIR Phase I: Research Agents and Inferential Retrieval

SBIR 第一阶段：研究代理和推理检索

• 批准号: 9861411
• 负责人: Marvin Cohen
• 金额: $ 10万
• 依托单位: COGNITIVE TECHNOLOGIES INC
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1999
• 资助国家: 美国
• 起止时间: 1999-01-01 至 1999-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9861411&HistoricalAwards=false
• 关键词: SBIR; Phase; Research; Agents; Inferential

9861411 The tremendous growth in access to information can create a "fire hose" effect, in which information is useless without effective methods for distinguishing what is relevant from what is not. This Small Business Innovation Research Phase I from Cognitive Technologies, Inc. addresses the problem of search, especially Internet search, from a unique perspective as research agents that mediate between, and on behalf of, the user and more traditional information retrieval systems. The innovative features of the approach are as follows: it provides direct support for users in constructing and elaborating mental models of the research context that motivates the search behavior; leverages such context with fast, parallel inferential search that filters and organizes search results from traditional search engines; supports critical thinking as it bears on the research issues under investigation; and envisions research as a collaborative process in which the fruits of each researcher's labors may be published electronically as active knowledge structures that can inform and organize subsequent searches, and which can form the basis of improved understanding of the domain. Direct commercial applications of the proposed integration of intelligent agent (IA) technology with a technology for explicitly representing a user's mental model of a domain include information access and management on the Internet and in vertical markets; namely, preparing briefs for case or patent law; market analysis for traders and brokers; intelligence analysis; primary and continuing education; university-based research; and conducting and managing national research interests.

9861411 获取信息的巨大增长可能产生“消防水管”效应，如果没有有效的方法来区分什么是相关的，什么是不相关的，那么信息就毫无用处。 这个小企业创新研究第一阶段从认知技术公司。从一个独特的角度来解决搜索问题，特别是互联网搜索，作为研究代理人，在用户和更传统的信息检索系统之间进行调解，并代表用户和更传统的信息检索系统。 该方法的创新之处在于：它为用户提供了直接的支持，帮助用户构建和阐述激发搜索行为的研究背景的心理模型;利用这种背景进行快速、并行的推理搜索，过滤和组织传统搜索引擎的搜索结果;支持批判性思维，因为它与所调查的研究问题有关;并设想研究作为一个合作的过程中，每个研究人员的劳动成果可能会以电子形式发布，作为积极的知识结构，可以通知和组织随后的搜索，并可以形成基础，提高对该领域的理解。 将智能代理人技术与明确表示用户对某一领域的心理模型的技术结合起来的建议的直接商业应用包括：在互联网上和在垂直市场上获取和管理信息;即为案例或专利法编写案情摘要;为交易商和经纪人进行市场分析;情报分析;初级教育和继续教育;大学研究;以及开展和管理国家研究兴趣。