基于中文自然语言查询的多媒体数据库检索系统-教育技术学专业论文.docxVIP

层次确定重要性后，计算总相似度。按照总相似度的大小，将最相似的20个结 层次确定重要性后，计算总相似度。按照总相似度的大小，将最相似的20个结 果反馈给用户。 论文在I：述1：作的基础上设计了基于中文自然语言‘查询的多媒体数据库检 索系统。用户注册登录后在界面上输入中文自然语言查询文本，进行文件格式、 文件大小、媒体类型的选择。系统自动提取主题内容、内容特征、计算相似度， 将符合条件的记录数据按照相似度的大小反馈给用户，反馈的内容还包括文件大 小、相似度大小、媒体所在网址等相关信息。初步实验结果表明，该系统对结构 比较简单的、嵌套较少的查询文本能比较准确的进行分词，提取主题内容、主题 词和主体属性词。对数据库中内容特征标注准确、详实的记录，检索结果准确度 较高，证明依据内容特征检索的方法是可行的。论文最后总结了本文的工作，并 提出了下一步的研究方向。 【关键字】自然语言查询，多媒体数据库，检索，内容特征，相似度 【分类号】G434 II Research Research Oil Multi—media Database RetrievaI Basing on the Chinese Natural Language ABSTRACT The informationization of education has brought forward new reqnirements for teachers．As the supervisor of the learning TC$ODECCS，teachers are to fix the media resources that are needed，and provide the query clues for students．Although there are abundant multi—media resources in the Interact，the existent searching retrievals mainly based the keywords，which searching accuracy is not so high．Teachers of middle and primary schools busy doing their routine jobs，and they various in applying the technology of computer network．Therefore，they need a convenient and fast system to search the multimedia resources． Natural language query means that the users describe the query object in the retrieval system，which extracts the query requirement and the key fcatures．Then the retrieval system feedback the query results according to fixed rules and algorithm． The Chinese natural language based multimedia retrieval mainly include three procedures：extracting the key features of the object media from its Chinese query words；searching records in the multimedia database which meet the query requirement and have the hiigher conformity；providing the records to the users according to its conformity． In this thesis，WC research into the features of the Chinese language understanding and general ways of word division，found a word division system for own use， divide the query texts and label its parts of speech．After omitting the function words and the default words from