A method and system for automatically generating document templates based on a recursive neural network language model

A recursive neural network and document template technology, applied in the software field, can solve the problems of low efficiency of document template generation and achieve the effect of improving generation efficiency

Active Publication Date: 2022-05-24
正孚信安(北京)技术有限公司
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Therefore, it is necessary to provide a method and system for automatically generating document templates based on a recursive neural network language model to solve the problem of low efficiency of existing document template generation

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
  • A method and system for automatically generating document templates based on a recursive neural network language model
  • A method and system for automatically generating document templates based on a recursive neural network language model
  • A method and system for automatically generating document templates based on a recursive neural network language model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to describe in detail the technical content, structural features, achieved objectives and effects of the technical solution, the following detailed description is given in conjunction with specific embodiments and accompanying drawings.

[0026] see Figure 1 to Figure 6 The present embodiment provides a method and system for automatically generating a document template based on a recurrent neural network language model. The present invention can be used to generate document templates in different fields. The following describes the power document template. When the template of the document is generated, the information of the original document is extracted through the information extraction step. The following is a detailed description of the information extraction steps:

[0027] Information extraction is to structure the information contained in the text and turn it into a table-like organizational form. The input information extraction system is the origi...

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 document template automatic generation method and system based on a recursive neural network language model. The method includes the following steps: corpus building step: extracting corpus from a preset corpus document and establishing a corpus; performing information extraction on a plurality of documents of the same type according to the corpus, extracting structured text information related to the document, Structured text information contains strings; step of deep text analysis: call deep representation model unit, perform dependency syntax analysis and discourse-level rhetorical relationship analysis on structured text information, and obtain the syntax tree and discourse relationship of structured text information; document Template generation step: input structured text information, syntax tree and discourse relationship into a language model based on recurrent neural network to generate a document template. The above technical solution realizes automatic generation of document templates based on deep learning and information extraction technology, thereby improving generation efficiency.

Description

technical field [0001] The invention relates to the technical field of software, in particular to a method and system for automatically generating a document template based on a recurrent neural network language model. Background technique [0002] The document template contains all the necessary components of a standard document, such as the report document contains the title, the chapters of the report, the main content of the report, the object of the report and the time and date. Through such a template, a standard-compliant document can be quickly produced. The current document templates are mainly produced manually. For many existing documents without document templates, it is necessary to manually check the documents, find out the components of the documents, and then produce the document templates, which is inefficient. SUMMARY OF THE INVENTION [0003] Therefore, it is necessary to provide a method and system for automatically generating document templates based ...

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): G06F40/186G06F40/216G06F40/295G06F40/211G06N3/04
CPCG06F40/186G06F40/216G06F40/295G06F40/211G06N3/049G06N3/045
Inventor 倪时龙
Owner 正孚信安(北京)技术有限公司
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
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