Full-text database accurate and efficient retrieval method for perfecting subject terms

Abstract

The invention provides a full-text database accurate and efficient retrieval method for perfecting subject terms. The method comprises the steps of firstly, creating a long-tail subject term lexicon,designing a long-tail subject term selection algorithm, selecting a user to optimize a search expression, and clearing the search intention; designing a subject term synonymy expansion algorithm basedon the word forest expansion version, and expanding the subject term into a synonymy set of the subject term; and designing an improved synonym similarity calculation method based on the Known synonym tree, and calculating the similarity between the expanded subject term set and the original subject term by adopting an improved algorithm; setting an appropriate similarity threshold value throughmultiple groups of experimental statistical analysis, and simplifying the subject term set according to the similarity critical value to obtain an improved subject term set; and finally, improving a retrieval result sorting algorithm. The recall ratio, the precision ratio and the retrieval efficiency of the method are greatly improved, and good performance is shown.

Description

technical field [0001] The invention relates to a full-text database retrieval method for perfecting subject terms, in particular to an accurate and efficient full-text database retrieval method for perfecting subject terms, belonging to the technical field of full-text database retrieval. Background technique [0002] With the continuous development of digitization and informatization, search engines have become extremely important information acquisition tools in all walks of life and fields, and various new technologies for information retrieval emerge in an endless stream. [0003] After the continuous development and popularization of the Internet, information from all walks of life is accumulated in the network day by day, with various types and quantities, involving life, society, education, technology, entertainment and other aspects. It is necessary to search for valuable information in such a huge network information database. information is becoming increasingly d...

AI Technical Summary

Problems solved by technology

[0009] The 3rd, the words included in the extended version of Cilin of the prior art are too comprehensive, and a subject word can be expanded into a collection of more than a dozen related words, and the collection of related words is used for retrieval, which will increase the workload of the information retrieval stage and the result processing stage, Reduce the efficiency of system retrieval

Moreover, classical Chinese words have been used very little in modern Chinese, and some words have low semantic correlation with modern Chinese, and in some cases there are even ambiguities.

The noise data in the related word set interferes with the search results and reduces the retrieval accuracy

[0010] The fourth is that the existing technology optimizes the keyword set to contain a lot of related words. There is a certain difference between the related words and the keyword, and the impact on the search results is also different. The default sorting algorithm of Lucene performs the same processing on all the keywords. It is obviously unreasonable to not distinguish the correlation between subject words

The sorting of the search results cannot satisfy the user's search habits, and the documents with high relevance to the subject words cannot be ranked in front of the search results.

Images