Supercharge Your Innovation With Domain-Expert AI Agents!

Retrieval processing method

A processing method and document technology, applied in the field of retrieval, can solve problems such as query failure, slow query speed, and large amount of retrieved data, and achieve the effect of improving retrieval efficiency

Inactive Publication Date: 2020-03-06
INSPUR SOFTWARE CO LTD
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As the number of documents increases, for example, in massive documents such as product manuals and legal documents, the amount of retrieved data is huge, which often leads to slow query speed or even query failure

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
  • Retrieval processing method
  • Retrieval processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Such as figure 1 As shown, this embodiment provides a retrieval processing method, including:

[0046] 11. Obtain a question, and extract at least one keyword from the question.

[0047] 12. Determine a massive document library for retrieving answers corresponding to the questions.

[0048] 13. According to the degree of association with the at least one keyword, extract documents associated with the question from the massive document library to form an associated document set;

[0049] 14. Retrieve a result corresponding to the question from the associated document set.

[0050] In one embodiment, according to the degree of association with the at least one keyword, extracting documents associated with the question from the massive document library to form an associated document set includes:

[0051] Obtain the subject of each document in the massive document library, match each keyword in the at least one keyword with the subject of each document in the massive do...

Embodiment 2

[0086] This embodiment describes in detail the retrieval processing method of the embodiment of the present invention in combination with specific examples, such as figure 2 As shown, the method includes:

[0087] 21. Obtain a massive document library.

[0088] The massive document library used in this embodiment stores a large number of documents, and the documents contained in the massive document library are Doc1, Doc2, Doc3....

[0089] 22. Obtain questions and process them to get keywords.

[0090] For example, Doc1 is an article introducing chrysanthemum tea, and the input question is "what is the growth and change of chrysanthemum tea?" When preprocessing the question, the problem is analyzed and processed, including stop words (for example, of), Error correction (change), processing of word segmentation, deletion of non-keywords (words), and conversion of questions into keywords: chrysanthemum tea, growth environment.

[0091] 23. Perform topic matching and semanti...

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 embodiment of the invention discloses a retrieval processing method which can improve the retrieval efficiency of mass retrieval. The retrieval processing method comprises the steps: acquiring a question, and extracting at least one keyword from the question; determining a mass document library used for retrieving answers corresponding to the questions; according to the degree of association with the at least one keyword, extracting documents related to the question from the massive document library to form an associated document set; and retrieving answers corresponding to the questions from the associated document set. The retrieval processing method obtains a question, extracts at least one keyword from the question, determines a mass document library for retrieving an answer corresponding to the question, extracts related documents of the question from the mass document library according to the degree of association with the at least one keyword to form an associated document set, and retrieves the answer corresponding to the question from the associated document set. Therefore, the associated documents are selected from the massive document library according to the questions, and the retrieval answers are retrieved in the associated documents, so that the retrieval efficiency of massive retrieval is improved.

Description

technical field [0001] The invention relates to the retrieval field, in particular to a retrieval processing method. Background technique [0002] In the information age, information is growing explosively. Quickly retrieving answers to user questions from massive amounts of information has become one of the keys in the field of intelligent dialogue systems. As the number of documents increases, for example, in massive documents such as product manuals and legal documents, the amount of retrieved data is huge, which often leads to slow query speed or even query failure. Contents of the invention [0003] An embodiment of the present invention provides a retrieval processing method, which can improve retrieval efficiency of mass retrieval. [0004] The embodiment of the present invention adopts following technical scheme: [0005] A retrieval processing method, comprising: [0006] Obtaining questions, extracting at least one keyword from the questions; [0007] determi...

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): G06F16/332G06F16/33
CPCG06F16/3329G06F16/3346
Inventor 潘心冰李明明曾光张红若
Owner INSPUR SOFTWARE CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com