Complexity-based patent document machine translation method and system

A patent document and machine translation technology, applied in the field of machine translation, can solve the problems of difficult translation, slow translation speed, and low accuracy, and achieve the effects of high translation efficiency, improved translation accuracy, and fast translation speed

Pending Publication Date: 2022-04-15
苏州远卓科技信息有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Patent documents are highly specialized technical documents, which contain a large number of professional vocabulary and terminology. Therefore, whether it is human translation or machine translation, there are problems of difficult translation, low accuracy and slow translation speed.

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
  • Complexity-based patent document machine translation method and system
  • Complexity-based patent document machine translation method and system
  • Complexity-based patent document machine translation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] refer to figure 2 , this embodiment provides a method for machine translation of patent documents based on complexity, which specifically includes the following steps:

[0041] S11: Divide patent documents into first-level regions according to content characteristics, and divide them into description abstract, claims, description, and appendix Figure four parts.

[0042] S12: Allocation of computing power to each partition after division according to the degree of complexity, specifically, including distribution of computing power according to the memory size and word count of each partition.

[0043] S13: Sorting the complexity of each sentence in the division and performing secondary distribution of computing power, specifically, including judging according to the character length of the proper noun in the patent document, when the length of the proper noun character in the patent document is longer , the more computing power is allocated. For example, when the n...

Embodiment 2

[0048] refer to image 3 , this embodiment provides a method for machine translation of patent documents based on complexity, which specifically includes the following steps:

[0049] S21: Divide patent documents into first-level regions according to content characteristics, and divide them into description abstract, claims, description, and attachments to the description. Figure four parts.

[0050]S22: Divide the divided specification into two levels, and divide it into five parts: technical field, background technology, content of the invention, description of drawings, and specific implementation methods.

[0051] S23: Divide the divided specific implementation manner into three levels, and divide it into several embodiments.

[0052] S24: Prioritize the divisions of the divided patent documents; specifically, prioritize according to the complexity and / or importance of the content in each division of the patent documents; for example, prioritize according to the complex...

Embodiment 3

[0060] refer to Figure 4 , a complexity-based machine translation system for patent documents, including:

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 belongs to the field of machine translation, and discloses a patent document machine translation method based on complexity, which comprises the following steps of: performing regional division on patent documents to form a plurality of divided regions; performing synchronous machine translation on the divided regions; wherein the synchronous machine translation comprises the steps of carrying out computing power distribution according to the complexity degree of contents in a division area and synchronously translating according to the computing power; the calculation power distribution according to the content complexity in the division area comprises counting the percentage of the character number in the division area in the total character number of the patent literature and then distributing the calculation power of the corresponding percentage for translation. In addition, the invention also discloses a patent document machine translation system based on complexity. According to the method, the machine translation speed can be effectively increased by adopting a mode of firstly partitioning and then performing synchronous machine translation, so that the patent document machine translation efficiency is improved.

Description

technical field [0001] The invention relates to the field of machine translation, in particular to a method and system for machine translation of patent documents based on complexity. Background technique [0002] Machine translation, that is, translating text in one language into another by computer, has become one of the important methods to solve the multilingual barrier at present. As early as 2013, Google Translate provided more than one billion translation services every day, which is equivalent to the annual human translation volume in the world, and the number of words processed is equivalent to one million books. [0003] Patent documents are highly specialized technical documents, which contain a large number of professional vocabulary and terminology. Therefore, whether it is human translation or machine translation, there are problems of difficult translation, low accuracy and slow translation speed. Therefore, improving the translation rate of patent documents ...

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): G06F40/58G06F40/131
Inventor 王艳慧
Owner 苏州远卓科技信息有限公司
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