Full-text retrieval system based on two-level semantic analysis

A semantic analysis and retrieval system technology, applied in the field of information retrieval, can solve problems such as lack of semantic analysis capabilities of documents, inability to accurately retrieve semantics, and affect retrieval accuracy, etc., to achieve precise retrieval services, accurate query expansion sentences, and improve precision Effect

Inactive Publication Date: 2013-06-05
HUAZHONG NORMAL UNIV
View PDF7 Cites 54 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because it has not yet adopted deep semantic analysis technology, many highly relevant retrieval results are lost
On the other hand, because information retrieval cannot "understand" the semantics of document chapter level, but simply considers a document as a collection of words, this also c

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Full-text retrieval system based on two-level semantic analysis
  • Full-text retrieval system based on two-level semantic analysis
  • Full-text retrieval system based on two-level semantic analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0029] Such as figure 1 As shown, the full-text retrieval system based on double-layer semantic analysis provided by the present invention includes a query information receiving module 100, a sentence summary level semantic processing module 200, a retrieval module 300, an index library 400, an index module 500, a chapter level semantic processing module 600, A result set processing module 700 and a data server 800 .

[0030] The query information receiving module 100 is used to receive the query information input by the user, and submit the query information to the sentence summary level semantic processing module 200 for summary level semantic processing of the query sentence according to the user's selection, or directly request the retrieval module 300 for retrieval services.

[0031] Such as image 3 As shown, the processing flow of the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of information retrieval, and provides a full-text retrieval system based on two-level semantic analysis. The system comprises a query information receiving module, a sentence summary level semantic processing module, a retrieval module, an index library, an index module, a text level semantic processing module, a result set processing module and a data server. The system performs summary processing and repeat processing for a query statement to repeat the query statement submitted by a user from sentence summary level semanteme, and latent semantic information and thematic information are extracted in the text level to eliminate retrieval result documents not conforming to text level semanteme, so that the full-text retrieval system achieves two-level semantic analysis in the 'sentence summary level' and the 'text level'. By improving semantic processing capacity of query statements and text sets, the full-text retrieval system is more human-friendly and intelligent, and provides more convenient and accurate services for users.

Description

technical field [0001] The invention belongs to information retrieval technology, in particular to a full-text retrieval system based on double-layer semantic analysis. technical background [0002] With the continuous exponential growth of Internet information, people have entered an era of information explosion. How to accurately and efficiently find the data users need in massive amounts of data is a huge challenge. The birth of search engines has solved the above problems to a certain extent. Search engines use specific computer programs to collect information from the Internet according to certain strategies, organize and process the information, provide users with retrieval services, and display the relevant information retrieved by users to the user's system. The vast majority of search engines use information retrieval technology to establish document inverted index databases, query keywords or query statements submitted by users, and return relevant document resul...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F17/30
Inventor 张茂元邹春燕黄梵王立刘强贺凡黎陈水银张红
Owner HUAZHONG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap