Subject-based searching method and device

Abstract

The invention provides a subject-based searching method and device. The subject-based searching method comprises the steps of performing subject analysis on each document in a document library by using a subject analysis model to determine a subject distribution corresponding to each document; performing subject analysis on a query input by a user by using the subject analysis model to determine the subject distribution corresponding to the query; calculating the subject matching degree between the query and each document by using the subject distribution corresponding to the query and the subject distribution corresponding to each document; obtaining the matching degree between the query and each document by using the subject matching degree, and determining searching results according to the matching degree between the query and each document. According to the subject-based searching method and device, the subject matching mode instead of a keyword matching mode is adopted, the documents can still be recalled even the documents are not consistent with the query of the user or not matched with redundant terms, and the search results are matched with the query in subject to a maximum extent in the query in statement, so that the research recall and accuracy are improved.

Description

【Technical field】 [0001] The invention relates to the field of computer technology, in particular to a subject-based search method and device. 【Background technique】 [0002] With the continuous development of computer network technology, search engines have become an important means for people to obtain information. Users input search items (query) through search engines, and search engines search for documents related to query from the captured documents, and follow relevant sorted by degree. The widely used search model is the vector space model. Its basic idea is to represent the query and the document as word vectors respectively. The weight of the vector can be the frequency of word occurrence (TF) or word frequency-inverse document frequency (TF-IDF) , and then calculate the similarity between the word vector of the query and the word vector of the document as a measure of correlation. In practical applications, there are various variants, but essentially they all c...

AI Technical Summary

Problems solved by technology

[0004] First, when no or few identical keywords appear, even if the actual content reflects the requirements of the query, it is difficult to rank first, or even impossible to recall

For example, if a user enters the query "beautiful Lincoln", some documents contain "Lincoln with a streamlined design", "white, black or red Lincoln", etc. Although the appearance of Lincoln is also involved, the keyword "beautiful" does not appear. , may not be able to be recalled or ranked in the top position, but in fact these documents reflect that users want to search for documents about Lincoln's good looks

[0005] Second, some queries have redundant expressions, which will cause documents that do not match the redundant words in them to be unable to be recalled or ranked in the top position

For example, the user enters the query "what should I do if I still hate my ex-husband after divorce", because "divorce" is a redundant word, although some documents are about solutions to still hate my ex-husband, because they do not match the keyword "divorce" ” without being able to be recalled or ranked at the top

Images