基于XML和ANN的Web文本智能检索研究

Research of web text information retrieval based on XML and ANN

传统的网络信息检索技术如搜索引擎存在一些不足,一方面它只是将信息搜寻出来,不能发现隐藏在数据背后的知识;另一方面其采集软件在采集数据时缺乏人工干预,智能性不强,导致信息利用率不高。针对传统的Web搜索引擎存在的上述问题,结合Web文本挖掘、XML、BP神经网络在数据处理方面的长处,提出了一个具有一定智能的Web文本信息检索模型,以使其具有较高的信息利用率。

There are some shortages to the traditional technical of web information retrieval such as search engine. On one hand, when it works, all that it does is only responsible for searching the information in the Web, and then shows all the results to users in some order without some necessary work of filter, so it can＇t find the hidden knowledge behind the data; on the other hand, due to a lack of necessary manual intervention, its module of gathering data is with poor intelligence. Hence on this condition the utilization ratio of information is not high. To the above questions that the traditional web search engine exists, the advantages of web text mining, XML, BP neural networks in processing data are combined to propose a model of web text information retrieval and through it, a higher utilization ratio of information is achieved.