Retrieval ordering method and system

Abstract

The invention discloses a retrieval ordering method. The method comprises the following steps of: receiving query phrases, and retrieving; returning retrieval results; extracting the low-dimensional features of all documents in a document library; acquiring relevancy feedback information of a plurality of documents in the retrieval results; generating a relevancy judgment model; calculating the relevancy scores of all documents in the retrieval results; and returning again retrieval results which are ordered from high to low according to the relevancy scores. The invention also discloses a retrieval ordering system, which comprises a retrieval module, a feature extraction module, a relevancy feedback module, an ordering module and a storage module. By the retrieval ordering method and the retrieval ordering system, high-efficiency and accurate retrieval results can be provided.

Description

technical field [0001] The invention relates to the technical field of information retrieval, in particular to a retrieval and sorting method and system. Background technique [0002] In recent years, with the popularization of the Internet and the diversification of information-generating media, the total amount of information resources has continued to grow at an exponential rate. A statistical study of the total number of Internet pages from 2000 to 2007 shows that, refer to the attached figure 1 , the growth rate of the number of web pages is also increasing. At the same time, it is generally stored on the node in an unstructured form. For users, how to effectively obtain information urgently needs corresponding theories and methods to solve. Therefore, a new upsurge of research on information retrieval has been set off in academia and industry, and it has become a research hotspot in the field of information processing. [0003] At present, some retrieval models have...

AI Technical Summary

Problems solved by technology

The main problem is that the algorithm cannot select parameters adaptively, and the model parameters need to be adjusted manually during operation. For this reason, a retrieval algorithm based on machine learning is called sorting learning, that is, the system automatically judges the data in the repository based on the query phrases submitted by users. The degree of relevance between the document and the query, and a sorted list is given, the higher the position, the more relevant the returned result is to the query

[0004] At the same time, the retrieval system faces the following problem: when the user has difficulty constructing a good query, the retrieval results are often unsatisfactory, but it is relatively easy for the user to judge the relevance of the document to the query, so it is considered to directly provide the document through user interaction. Introduce the retrieval system to judge the relevance of documents to improve the accuracy of retrieval results. This is the information retrieval method based on user-related feedback.

[0005] Judging from the research results of information retrieval methods based on machine learning and information retrieval methods based on user-related feedback, the two types of algorithms are not well integrated at present, and often each has a certain range of application. How to combine machine learning methods with user-related More effective retrieval and sorting of information by feedback mechanism is a technical issue of great concern to those skilled in the art

Images