The Research About The Education Resources Search Engine Based On The Content

In this paper, we explore a special plan about a Chinese personalization education resources search engine facing the need property of high-elementary education. With the increasing development of the users and the teaching resources database, it will become very important about how to understand the query need of the user considerately and return the results which can reflect the connotation and the extension of the query need, how to construct the high efficient index database , how to compress the index, and how to construct the general knowledge database about the high-elementary education and the regularity database reflecting the experience of the teaching. This paper mainly finished the intelligent search and the automatic push of the education resources by web mining and semantic web technologies; Secondly, at the aspect of the construction about the education resources database, it firstly puts forward the idea that the concise abstract should be added to the education resources and use the Chinese text categorization technology to automatically put the education resources into the database., At the same time, we extract the keyword from the text summarization as the automatic index, considering the economization of the store space, we do the research about the index compression and the latent semantic index based on the content and analyzes the hypothesis of constructing the classification dictionary and the feasibility of education semantic web. At last, it formulates the system characteristics and the potential problems. Firstly, at the aspect of the finishing the intelligent search and dynamic push, this paper mainly explore the query expansion of using the artificial and the dynamic resources, and put forward the teaching resources association link, that is to say ,use the mind map to improve the performance of the query expansion. Secondly, at the aspect of the dynamic index and the index compression, this paper analyzes the feasibility of the compression and the superiority brought about by the compression, and formulates the application of the latent semantic index in the teaching resources research based on the content. Thirdly, at the aspect of the automatic construction of the education resources database, this paper puts forward the idea that the concise abstract should be added to the education resources and use the Chinese text categorization technology to automatically put the education resources into the database. At last, this paper analyzes the hypothesis of constructing the classification dictionary and the feasibility of education semantic web and formulates the characteristic of the system , some latent problems and the work needed to do in the future. The task of the Google is to organize the information and provide the best service accessible to the people, while the task of the DSJet is to high efficiently organize the teaching resources and provide the best service in order to force the development of the high-elementary education.