Text abstract generation method

A text and abstract technology, applied in the field of text abstract generation, can solve the problems of information redundancy, low fluency, and poor identification of key information, and achieve the effect of avoiding information redundancy, improving fluency, and accurate identification.

Active Publication Date: 2019-04-23
IFLYTEK CO LTD
View PDF6 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a text abstract generation method to overcome the current defects of poor identification of key information, low fluency, and redundant information, and at the same time overcome the inability to accurately generate business processes due to failure to incorporate domain-related business information summary question

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
  • Text abstract generation method
  • Text abstract generation method
  • Text abstract generation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0035] In one embodiment of the present application, in general, as figure 1 As shown, the method of the present application is based on an encoder-decoder structure in automatic text summarization, combined with a copy (copy) mechanism, extraction (retrieval) mechanism and / or coverage (coverage) mechanism, to generate key words in the dialogue text information, generating summary information.

[0036] In another embodiment of the present application, in general, the method of the present application is based on the encoder-decoder structure in automatic summarization, combined with the business information of the corresponding domain database of the business domain, and ...

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 text abstract generation method, which comprises the following steps of obtaining the probability of commonly generating words and field words on the basis of contents of aninput text and business information of a field corresponding to the input text; and generating abstract information corresponding to the input text based on the probabilities of the common generated words and the field words and the corresponding vocabularies. The invention also discloses a text abstract generation method, which comprises the following steps of obtaining the probabilities of the common generated word, the duplicated word and the field word corresponding to the input text in real time based on the coded input text, and obtaining abstract information based on the probabilities of the common generated word, the duplicated word and the field word and the corresponding vocabulary. According to the method provided by the invention, the abstract words can be extracted based on the related service information of the corresponding domain library incorporated into the domain in combination with the related service domain, so that the abstract information of the related service process can be summarized more accurately, at the same time, the key information can be accurately identified by integrating multiple mechanisms, the fluency is improved, and the information redundancyis avoided.

Description

technical field [0001] The invention relates to the technical fields of natural language processing and human-computer mutual assistance, in particular to a method for generating text summaries. Background technique [0002] With the rapid development of artificial intelligence, it is increasingly necessary for machines to assist humans to complete tasks. All walks of life need to record past information and form a summary, so article summary technology is particularly necessary. Among them, understanding the intent of the article and obtaining key information are the most critical. [0003] Represented by the public service industry. For example, operators, people will consult various telecommunications issues, and the staff will form a record of the questions answered every day, and will fill in the work order and submit it if it cannot be resolved in time. This technology will assist staff to complete work orders and reduce their workload. [0004] Also for example, i...

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): G06F16/34G06F16/332
Inventor 陈翰卿宋时德胡加学
Owner IFLYTEK 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