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

Multi-mode fusion commodity classification system

A classification system and multi-modal technology, applied in character and pattern recognition, sales/lease transactions, instruments, etc., can solve the problems of slow classification speed and low classification accuracy, and achieve the goal of fast and accurate product classification Effect

Inactive Publication Date: 2017-06-30
SHENZHEN MINGCHUANG AUTOMATIC CONTROL TECH CO LTD
View PDF1 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing product classification methods only study the image of the product and ignore the text information of the product. On the other hand, the existing product classification methods have problems such as low classification accuracy and slow classification 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
  • Multi-mode fusion commodity classification system
  • Multi-mode fusion commodity classification system
  • Multi-mode fusion commodity classification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The present invention is further described in conjunction with the following examples.

[0012] see figure 1 , a multi-modal fusion commodity classification system in this embodiment includes an image-based commodity classification module 1, a text-based commodity classification module 2, and an image-text fusion classification module 3, and the image-based commodity classification module 1 uses To obtain the classification result of commodity images; the text-based commodity classification module 2 is used to obtain the classification results of commodity text; the graphic-text fusion classification module 3 is used to fuse the classification results based on commodity images and the classification results based on text images , get and output the commodity category.

[0013] This embodiment can realize more accurate and rapid commodity classification.

[0014] Preferably, the image-based commodity classification module 1 is used to obtain the classification results ...

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 provides a multi-mode fusion commodity classification system, and the system comprises a commodity classification module based on an image, a commodity classification module based a text, and an image-text fusion classification module. The commodity classification module based on the image is used for obtaining a classification result of a commodity image. The commodity classification module based the text is used for obtaining the classification result of a commodity text. The image-text fusion classification module is used for the fusion of the classification result based on the commodity image and the classification result based on the commodity text, and obtains and outputs a commodity class. The beneficial effects of the invention: the method can achieve the more precise and quicker classification of the commodity.

Description

technical field [0001] The invention relates to the technical field of commodity classification, in particular to a multimodal fusion commodity classification system. Background technique [0002] Product classification provides strong support for product retrieval, product placement strategy formulation, and intelligent recommendation. As the main information carrier of commodities, image-based commodity classification technology research has become a research hotspot in the fields of image processing, computer vision and pattern recognition. However, the existing product classification methods only study the images of the products and ignore the text information of the products. On the other hand, the existing product classification methods have problems such as low classification accuracy and slow classification speed. Contents of the invention [0003] In view of the above problems, the present invention aims to provide a multi-modal fusion commodity classification sy...

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): G06K9/62G06Q30/06
CPCG06Q30/0601G06F18/2431
Inventor 不公告发明人
Owner SHENZHEN MINGCHUANG AUTOMATIC CONTROL TECH CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com