Abstract extraction method and related equipment

An extraction method and abstract technology, which are applied in the field of abstract extraction methods and related equipment, can solve the problems of low abstract accuracy, insufficient use of sentence position information, low coverage of key content of documents, etc., and achieve the effect of improving accuracy.

Active Publication Date: 2018-05-18
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although in most documents, especially news documents, the summary of the important information of the document content will be concentrated at the beginning of the document, but if only the location information is taken as the only consideration for summarization, it will inevitably lead to the generation of summaries. coverage is too low
In the automatic summarization method that comprehensively considers the sentence position feature and other features that characterize the importance of the sentence, the deviation between the training data and the real data will lead to insufficient utilization of the sentence position information, resulting in the accuracy of the extracted summary. Low

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
  • Abstract extraction method and related equipment
  • Abstract extraction method and related equipment
  • Abstract extraction method and related equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them.

[0074] See figure 1 , figure 1 It is a schematic structural diagram of an abstract extraction system provided by an embodiment of the present invention. The abstract extraction system includes a text source 101, a server 102, a speech synthesis tool 103, a cloud 104, a voice assistant 105, and a user terminal 106, wherein the text source 101 can be are various news webpages, the server 102 can be an application program server, the speech synthesis tool 103 is used to convert text information into voice information in real time, the cloud 104 can be a software platform using application virtualization technology, and the voice assistant 105 can be an inte...

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

An embodiment of the invention discloses an abstract extraction method and related equipment. The method includes: extracting a first statement from a text to generate an initial abstract of the text;determining a confidence coefficient of each statement in the text; determining accuracy of the initial abstract according to the confidence coefficient of each statement; when the accuracy is largerthan a first threshold, determining the initial abstract as a target abstract of the text, and when the accuracy is not larger than the first threshold, selecting a second statement from the text toreplace the first statement in the initial abstract to obtain the target abstract of the text. By adoption of the abstract extraction method and the related equipment, abstract extraction accuracy canbe improved.

Description

technical field [0001] The invention relates to the field of electronic technology, in particular to an abstract extraction method and related equipment. Background technique [0002] At present, the single-document summary automatic extraction method is mainly based on heuristic rules or machine learning to evaluate and extract the sentences in the document. This method assigns a weight to each sentence in the text to reflect its importance, and then selects the largest A number of sentences form a summary. In this type of method, the positional features of the sentence are mixed with other important features representing the sentence, and the learning target is constructed based on the expected results, and then the importance of the sentence features is automatically discovered through the machine learning algorithm. Another type of method (for example: LEAD method) directly extracts the first few sentences of the document as a summary of the document, and this type of m...

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 Applications(China)
IPC IPC(8): G06F17/30G06F17/27
CPCG06F16/345G06F16/35G06F40/205
Inventor 曹云波万小军苏可
Owner TENCENT TECH (SHENZHEN) CO LTD
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