基于用户本体模型的文本信息过滤方法研究

ON METHOD OF TEXT INFORMATION FILTERING BASED ON USER ONTOLOGY MODEL

随着互联网信息的快速剧增,文本过滤技术成为互联网内容处理的关键技术,对海量信息处理具有很重要的意义。目前研究热点是基于语义的过滤方法,但是这些方法一般都需要大量规则和领域知识的支持,可用性不是很好。为了使机器更好地理解用户需求和文本内容,使过滤结果更能反映用户的真正需求,提高文本过滤的准确率和召回率,提出了基于用户本体模型UOM的文本信息过滤方法。该方法主要包括UOM构建、文本结构分析、文本概念提取和语义相关度计算等。基于UOM(User Ontology Model)的过滤方法,不仅可以表示复杂的用户需求,而且还避免了领域本体的构建,因而其有效性和实用性得到了很大的提高。通过在网络教学资源的智能按需服务系统中的实际运用,表明此方法能更有效地为用户提供过滤服务。

With dramatic increase of information on Internet, text filtering becomes a key technology in Internet content processing and is of important in huge information processing. Now the filtering methods based on semantics are researchers＇ focus, however the usability of these methods is not good, because they must be supported by plentiful rules and domain knowledge. To improve filtering precision and recall rates, in this paper it presents a novel method for text information filtering based on User Ontology Model （ UOM）, so that the machines could understand better the user＇ s requirements and text content to some extent, and the filtering results could reflect users＇ requirements more. The method includes UOM model building, text structure analysis, text conception extracting and semantic correlation computing, and so on. The filtering method based on UOM can express the complex requirements and also avoids building domain ontology, so its effectiveness and practicality have had a great promotion. This method is applied to the system of intelligent on-demand services for interact teaching resource and is shown that it can provide filtering services to users effectively.