A trademark pattern approximation query system and method

A query system and query method technology, applied in the direction of still image data retrieval, still image data indexing, special data processing applications, etc., can solve the problems of inaccurate manual labeling, poor retrieval efficiency, low recognition rate, etc., and achieve accurate attributes, Increased efficiency and reliability, targeted results

Inactive Publication Date: 2019-05-28
北京博鳌纵横网络科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention proposes a trademark pattern approximate query system and method, which solves the limitations of the existing technology in the recognition of trademark images with relatively complex images, the recognition rate is low, the retrieval efficiency is poor, and additional manual labeling is required. Labeling imprecise and unobjective problems

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 trademark pattern approximation query system and method
  • A trademark pattern approximation query system and method
  • A trademark pattern approximation query system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0047] Such as figure 1 As shown, the present invention proposes a similar trademark pattern query system, including a trademark pattern feature library generation subsystem, a convolutional neural network, a trademark pattern feature library, and a trademark pattern query subsystem; the trademark pattern feature library generation subsystem is convolution The neural network provides the initial training set, and the convolutional neural network trains the machine ...

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 trademark pattern approximate query system and method. The trademark pattern approximate query system comprises a trademark pattern feature library generation subsystem, a convolutional neural network, a trademark pattern feature library and a trademark pattern query subsystem. The trademark pattern feature library generation subsystem provides an initial training set forthe convolutional neural network; the convolutional neural network is used for training a machine learning model for automatically processing trademark patterns; the trademark pattern features and the related index information are stored into a trademark pattern feature library; and when the query object trademark pattern is input, the trademark pattern feature library query subsystem performs feature matching on the query object trademark pattern and the trademark pattern stored in the trademark pattern feature library, and feeds back a matching result to the convolutional neural network tocomplete correction of the machine learning model. The trademark pattern serves as input, the intelligent algorithm based on the convolutional neural network is adopted to learn the features of the pattern in the feature library, manual marking is not needed, and the precision and efficiency of trademark pattern approximate query are improved.

Description

technical field [0001] The invention relates to a trademark pattern approximate query system and method. Background technique [0002] A trademark is a mark used by a company, product or service to distinguish an operator's brand or service from other operators' goods or services. It is integrated with the company's product quality, service quality, and management, and plays an important role in the industrial and commercial society The important role is an important attribute of the company and its products, and it is unique. In order for a trademark to be legally protected, it must be formally registered with the Trademark Office. With the development of my country's economy and the acceleration of globalization, the number of trademarks is increasing year by year. Preventing duplicate registration or registration of similar trademarks is the core issue of trademark management. In order to protect the legitimate rights and interests of registered trademarks and crack do...

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): G06F16/583G06F16/51
Inventor 杨昕邢海峰程凯悦
Owner 北京博鳌纵横网络科技有限公司
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