Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Science and technology information text-oriented text abstract generation method and system

A text and technology technology, applied in the field of text abstract generation for scientific and technological information text, can solve the problems of poor abstract quality and achieve the effect of good quality

Pending Publication Date: 2021-01-12
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects or improvement needs of the prior art, the present invention provides a method and system for generating text summaries oriented to scientific and technological information texts, the purpose of which is to solve the technical problem of poor summaries existing in the prior art

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
  • Science and technology information text-oriented text abstract generation method and system
  • Science and technology information text-oriented text abstract generation method and system
  • Science and technology information text-oriented text abstract generation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] A text summary generation method for scientific and technological information texts, such as figure 1 shown, including the following steps:

[0041] S1. Perform entity recognition and relationship extraction on the scientific and technological information text to be processed to obtain entities and triples contained in the scientific and technological information text; it should be noted that entities are words or phrases with descriptive meaning in the scientific and technological information text; A triple is a tuple composed of the relationship between the extracted entities and the entity.

[0042] S2. Determine whether the scientific and technological information text is a long text, and if so, go to step S3; otherwise, fuse the scientific and technological information text with the above entities and triples to form model input information, and go to step S4;

[0043] Specifically, the length of the scientific and technological information text is compared with a...

Embodiment 2

[0075] A text summary generation system for scientific and technological information texts, including:

[0076] Text preprocessing module: used for entity recognition and relationship extraction of the scientific and technological information text to be processed, to obtain entities and triples contained in the scientific and technological information text, and output them and the scientific and technological information text to the long text judgment module;

[0077] Long text judging module: used to judge the length of the scientific and technological information text, if it is a long text, output the scientific and technological information text, the above entities and triples to the long text processing module; otherwise, combine the scientific and technological information text with the above entities and triplets are fused to form model input information, and output to the summary generation module;

[0078] Long text processing module: used to determine the influence of...

Embodiment 3

[0082] A computer-readable storage medium, the computer-readable storage medium includes a stored computer program, wherein, when the computer program is run by a processor, the device where the storage medium is located is controlled to execute a method provided in Embodiment 1 of the present invention. A text summarization method for scientific and technological information texts. The relevant technical solutions are the same as those in Embodiment 1, and will not be repeated here.

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 discloses a science and technology information text-oriented text abstract generation method and system, and the method comprises the following steps: S1, carrying out the entity recognition and relation extraction of a to-be-processed science and technology information text, and obtaining entities and triples contained in the science and technology information text; s2, judging whether the science and technology information text is a long text or not, and if so, turning to the step S3; otherwise, fusing the science and technology information text with the entity and the triad toform model input information, and going to the step S4; s3, determining the influence of each sentence in the science and technology information text based on the line text structure of the science and technology information text and in combination with the entity and the triad, obtaining K sentences with the highest influence from the science and technology information text to form a key sentence group, and fusing the key sentence group with the entity and the triad to form model input information; and S4, inputting the model input information into a pre-trained sequence to a sequence modelto obtain a text abstract. And the generated abstract is high in accuracy, strong in readability and good in quality.

Description

technical field [0001] The invention belongs to the technical field of text abstract generation, and more specifically relates to a text abstract generation method and system for scientific and technological information texts. Background technique [0002] In the era of information explosion, the total amount of scientific and technological information has increased exponentially, and scientific and technological information has been updated rapidly. This makes scientific and technological researchers have not obtained useful scientific and technological research information in time, and the scientific and technological research information may be outdated. At the same time, due to the huge amount of scientific and technological information and the existence of a large amount of repetitive information, it is difficult for scientific and technological researchers to obtain scientific and technological information efficiently and comprehensively, and then grasp the development...

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): G06F40/258G06F40/295G06F40/30
CPCG06F40/258G06F40/295G06F40/30
Inventor 李国徽潘鹏韩镓维袁凌
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com