Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Intelligent digital newspaper automatic abstract and voice interaction news chat method and system thereof

A voice interaction and automatic summarization technology, applied in the field of voice interaction processing methods and systems, can solve the problems of lack of semantics, sparse data, and error accumulation, and achieve the effect of avoiding time-consuming, labor-intensive and error accumulation.

Pending Publication Date: 2021-03-26
浙江方正印务有限公司
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In-depth learning method, voice interaction, learning to obtain dense document quantification of news texts, processing doc2vec word vector representation, so as to solve the problems of high dimensionality, data sparseness, lack of semantics, sentence segmentation and other problems of traditional text representation, using news text word vectors as input, through The attention neural network automatically learns and extracts news text features, thereby avoiding the shortcomings of time-consuming, labor-intensive and error accumulation of traditional news text classification methods that manually participate in feature extraction

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
  • Intelligent digital newspaper automatic abstract and voice interaction news chat method and system thereof
  • Intelligent digital newspaper automatic abstract and voice interaction news chat method and system thereof
  • Intelligent digital newspaper automatic abstract and voice interaction news chat method and system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0069] In the practical application of this embodiment, the following description of at least one example is actually only illustrative, and is by no means any limitation to the present invention and its application or use.

[0070] Techniques, methods and devices known to those of ordinary skill in the related art may not be discussed in detail, but where applicable, the techniques and methods should be considered a part of the specification.

[0071] In all methods shown and discussed herein, any specific values ​​should be construed as exemplary only, and not as limitations. Therefore, other instances ...

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 relates to an intelligent digital newspaper automatic abstract and voice interaction news chat method and a system thereof, a neural network is built through a self-attention layer and used for a text intelligent abstract generation method, and the system comprises an algorithm technology, a scheduling technology, an awakening technology, a searching technology, a voice recognition technology, a synthesis technology and a news chat technology, and particularly relates to intelligent abstracts and chat news. The purpose of intelligently and efficiently extracting and summarizing texts from massive news is achieved, and the method is concise, easy to read, personalized in news recommendation and topic recognition and tracking. The real-time pickup, ultrasonic filtering and an attention neural network solve the problems of high dimension, data sparseness and lack of semantic methods of traditional texts, and in voice output, intelligent human-computer interaction experienceof selection, listening, speaking, understanding and answering is given.

Description

technical field [0001] The invention belongs to the field of automatic generation technology of intelligent news processing summaries, natural language processing technology and voice interactive chat news, and in particular relates to an automatic generation method of intelligent news summaries based on semantic correlation, a voice interaction processing method and a system. Background technique [0002] Newspapers are one of the oldest means in the field of communication. For thousands of years, newspapers have made outstanding contributions to the progress of human civilization. As an important channel for news readers to obtain social information resources, news information is an important means for people to obtain effective social information in the era of big data. How to quickly obtain the information we need from this huge ocean of information has become crucial. Intelligent news summary refers to one or a paragraph of sentences extracted and summarized from the so...

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): G10L15/22G10L15/26G10L15/18G10L15/16G10L15/06G10L25/54G10L25/30G10L13/04G10L13/047G10L13/08G06F16/332G06F16/34G06F40/289G06F40/30G06F40/211G06F40/216G06K9/62G06N3/04G06N3/08G06N5/04
CPCG10L15/22G10L15/1822G10L15/16G10L15/063G10L25/54G10L25/30G10L13/047G10L13/08G06F16/3329G06F16/345G06F40/289G06F40/30G06F40/216G06F40/211G06N3/049G06N3/08G06N5/041G10L2015/223G10L2015/0638G10L2015/0631G06N3/045G06F18/24Y02D10/00
Inventor 庄跃辉程雨夏
Owner 浙江方正印务有限公司
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
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