Method and device for automatic generation of text summaries based on heuristic rules

An automatic generation and heuristic technology, applied in the direction of unstructured text data retrieval, text database browsing/visualization, natural language data processing, etc. , the effect of abstract diversification

Active Publication Date: 2021-04-09
NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT +1
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since this method automatically selects the more important sentences in the article, and then composes the summary according to the order of the importance of the sentences, it is not satisfactory in the reorganization of the semantic word order and the readability of the generated content.

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
  • Method and device for automatic generation of text summaries based on heuristic rules
  • Method and device for automatic generation of text summaries based on heuristic rules
  • Method and device for automatic generation of text summaries based on heuristic rules

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The present invention will be described in further detail below in conjunction with the embodiments and accompanying drawings, so that those skilled in the art can implement it with reference to the description.

[0027] Such as figure 1 As shown, the present invention provides a method for automatically generating text summaries based on heuristic rules, including:

[0028] S1. Using the paragraph and sentence order of the text as the heuristic word order, divide the news text into the beginning paragraph, the middle paragraph and the end paragraph, and heuristically segment each paragraph at the granularity of sentences and fragments;

[0029] S2. First, take the sentence as the granularity, extract the target sentences of each paragraph respectively, and obtain the sentence abstract set of each paragraph, and then use the fragments in the sentence abstract collection as the granularity, respectively extract the target fragments of each paragraph, and obtain the fragm...

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 method for automatically generating text summaries based on heuristic rules, including: S1, using the paragraphs and sentence sequences of the text as the heuristic word order, dividing the news text into the beginning paragraph, the middle paragraph and the end paragraph, and using sentences and fragments Carry out heuristic segmentation of each paragraph as the granularity; S2, first take the sentence as the granularity, extract the target sentence of each paragraph respectively, obtain the sentence summary set of each paragraph, and then take the fragments in the sentence summary set as the granularity, respectively extract each The target segment of a paragraph is obtained by obtaining a segment summary set of each paragraph; S3, removing redundant segments in the segment summary set, and combining the selected segments according to the sequence in which the segments appear to generate a text summary. And, a device for automatically generating text summaries based on heuristic rules. The sentence organization of the text summary generated by the method of the invention has good coherence and strong readability.

Description

technical field [0001] The invention relates to the field of natural language processing. More specifically, the present invention relates to a method and device for automatically generating text summaries based on heuristic rules. Background technique [0002] The process of automatic summarization is mainly to summarize the central meaning of the text document, and the purpose is to create a summary that contains the main content of the original document. It has significant application scenarios in news, finance, medical and other fields. Especially in the current Internet information age, information overload makes people eager to learn the most and most useful text information in the shortest time, and the automatic generation technology of text summarization makes this requirement come true. [0003] The automatic summarization technology takes the entire article as input, and generates a paragraph of refined words to express and summarize the core content of the inpu...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/34G06F40/211G06F40/289G06Q30/02G06Q30/06G06Q50/30
CPCG06Q30/0645G06Q50/30G06Q30/0239G06F40/211G06F40/289
Inventor 石瑾张翔宇张旭刘春阳李建欣毛乾任孙庆赟
Owner NAT COMP NETWORK & INFORMATION SECURITY MANAGEMENT CENT
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