基于交互感知的探索式搜索中资源的推荐方法

发布时间：2018-09-11 15:04

【摘要】：基于关键词匹配的信息搜索技术日渐成熟,人们期待搜索引擎更加智能,能够根据模糊需求启发用户找到正确的信息,探索式搜索由此出现。已有依据关键词之间的语义关联进行搜索推荐的探索式搜索方式,能够启发用户找到与当前查询相关的其他信息。然而,这种随机式的推荐方式仅适用于用户对不熟悉的领域进行初步了解的应用场景。针对有特定搜索意图的用户,如何有效利用用户提供的信息,让信息推荐以符合认知规律的方式进行,并且能够使计算机智能地理解用户的下一步信息需求的意图是研究的关键。提出一种基于交互感知的信息推荐方法,设定交互的基本规则,便于系统尽快确定模糊用户需求的搜索意图。示例展示这种方式能够对有效交互进行定量分析,并能有效减少用户与系统之间交互的步数。
[Abstract]:The information search technology based on keyword matching is maturing day by day. People expect the search engine to be more intelligent and can inspire users to find the correct information according to the fuzzy requirements. An exploratory search method based on semantic association between keywords can inspire users to find other information related to the current query. However, this random recommendation is only suitable for applications where users have a preliminary understanding of unfamiliar areas. How to make effective use of the information provided by the user and how to make the information recommendation in accordance with the rules of cognition for the users with a specific search intention? And it is the key of the research that the computer can intelligently understand the intention of the user's next information requirement. An information recommendation method based on interaction perception is proposed to set the basic rules of interaction so as to facilitate the system to determine the search intention of fuzzy user requirements as soon as possible. Examples show that this method can quantitatively analyze the effective interaction and reduce the number of steps between the user and the system.
【作者单位】：中国人民公安大学信息技术与网络安全学院;中国人民公安大学安全防范与风险评估公安部重点实验室;
【基金】：国家高技术研究发展计划(863计划)(2015AA016009) 中国人民公安大学基本科研业务费项目(2016JKF01316)资助
【分类号】：TP391.3

【相似文献】