Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic patent classification method based on patent network representation learning

A network representation and automatic classification technology, applied in neural learning methods, biological neural network models, text database clustering/classification, etc., can solve the problem that the effect of patent classification needs to be improved, and achieve the effect of improving the accuracy rate

Pending Publication Date: 2021-10-01
UNIV OF SCI & TECH OF CHINA
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

All in all, there is a large amount of interactive information between patents and inventors and patentees in patent data. Existing methods ignore these cross-view interconnected knowledge. Therefore, the effect of patent classification needs to be improved.

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
  • Automatic patent classification method based on patent network representation learning
  • Automatic patent classification method based on patent network representation learning
  • Automatic patent classification method based on patent network representation learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0021] The embodiment of the present invention provides a patent automatic classification method based on patent network representation learning, such as figure 1 As shown, it mainly includes:

[0022] Step 1. Obtain the patent text information including the text content of the patent, inventor information and patentee information.

[0023] Step 2. Use the text content of the patent, the inventor information and the patentee information to construct t...

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 an automatic patent classification method based on patent network representation learning. The method classifies patents by introducing methods in two fields of multi-view learning and network representation learning, and can more effectively utilize information of different view sources to improve patent prediction accuracy. Meanwhile, by using various methods including an attention mechanism, complete interpretability analysis can be carried out on contribution of various views to patent classification prediction, and final patent characterization can be visualized, so that the effect of achieving two purposes by one stone is achieved.

Description

technical field [0001] The present invention relates to the technical field of patent classification, in particular to a patent automatic classification method based on patent network representation learning. Background technique [0002] Patent automatic classification is of great significance for improving the efficiency of large-scale patent management and service. Typically, a patent examiner manually classifies each patent into multiple categories based on the domain knowledge he or she possesses. However, the number of patent applications has increased rapidly in recent years, and the traditional manual operation is laborious and time-consuming, which can hardly meet the demand. Therefore, there is an urgent need for automatic patent classification tools to support related services. [0003] Traditionally, related technologies regard patent classification as a text classification problem, that is, given a patent problem, determine the category it belongs to. However...

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): G06F16/33G06F16/35G06F40/284G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F16/35G06F16/3344G06F40/284G06F40/30G06N3/08G06N3/048G06N3/044G06F18/241
Inventor 徐童陈恩红方林涛张乐武晗周丁
Owner UNIV OF SCI & TECH OF CHINA