Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Semantic-Based Cross-Language Patent Innovation Prediction Analysis Method

An analysis method and cross-language technology, applied in semantic analysis, semantic tool creation, text database query, etc., can solve problems such as inability to find translations, and achieve the effect of narrowing the scope of manual retrieval

Active Publication Date: 2020-04-21
江苏交科能源科技发展有限公司
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The first category may have the problem that some words cannot be found in the translation, and the second category needs to choose a suitable method to construct the transformation space

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 Semantic-Based Cross-Language Patent Innovation Prediction Analysis Method
  • A Semantic-Based Cross-Language Patent Innovation Prediction Analysis Method
  • A Semantic-Based Cross-Language Patent Innovation Prediction Analysis Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further described in detail below in conjunction with the accompanying drawings, so that those skilled in the art can implement it with reference to the description.

[0045] It should be understood that terms such as "having", "comprising" and "including" as used herein do not entail the presence or addition of one or more other elements or combinations thereof.

[0046] Such as figure 1 , 2 , 9, a novel semantic-based cross-language patent prediction analysis method, including:

[0047] Step 1. Read the classification information of Wikipedia, and obtain at least one related word of the entry by extracting phrases on the keyword interface, disambiguation page or redirection page, and establish a mapping relationship between categories, articles, and keyword lists , to build a Chinese semantic network structure; Wikipedia (Wikipedia) has become one of the largest and most widely used free encyclopedias on the Internet. It has millions o...

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 present invention discloses a semantics-based cross-language patent novelty predetermining analysis method. The method comprises the steps of reading classified information of Wikipedia, extracting keywords, synonyms and related words of an article title, a disambiguation page and a redirection page, and building a cross-language semantic network structure; extracting Chinese keywords from a to-be-examined Chinese patent, reading related words of the Chinese patent from a cross-language knowledge bank, combining and expanding the multiple Chinese keywords and the related words, so as to form multiple groups of Chinese inquire words, translating the Chinese inquire words into corresponding English inquire words for retrieving, so as to obtain multiple similar English files; and extracting English keywords, performing similarity calculation, predetermining the novelty, building a tree map through hierarchical clustering, and outputting the most similar English files. Through adoption of the method, a cross-language comparison policy is made, patent writing and examination efficiency can be improved greatly, patent declaration and approval time is shortened, patent declaration and examination efficiency is improved, and the method has high promotion value.

Description

technical field [0001] The invention relates to the field of natural language processing in the computer field. More specifically, the present invention relates to a semantically-based cross-lingual patent innovative predictive analysis method. Background technique [0002] At present, the writing and review of invention patents in my country is still carried out manually, and the huge number of applications has brought a huge workload to the patent writing and review personnel. Especially in the substantive examination stage, examiners are required to search for all published materials such as patent documents and papers that are the same as or similar to the patent to be examined and whose publication date is before the patent application date, and compare them. This makes a judgment on whether it is novel and inventive, and then decides whether to grant authorization. This process first requires searching for similar patents and documents, and then performing content co...

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): G06F16/31G06F16/33G06F16/36G06F40/30
CPCG06F16/313G06F16/3347G06F16/36G06F40/30
Inventor 梁颖红
Owner 江苏交科能源科技发展有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products