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

Method and system for recommending commodities according to commodity images based on image recognition

An image recognition and commodity image technology, applied in the computer field, can solve the problems of different sizes and time consumption, and achieve the effect of quality improvement, easy and accurate analysis process

Pending Publication Date: 2022-06-07
丁伟
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] There are still some deficiencies in the existing system. For some secondary retail merchants, it is necessary to identify a large amount of product information every day and find similar products. However, there are many types of products and different sizes, making each identification process difficult It is necessary to adjust the recognition equipment to ensure the shooting angle and shooting focal length, resulting in a lot of time consumption

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
  • Method and system for recommending commodities according to commodity images based on image recognition
  • Method and system for recommending commodities according to commodity images based on image recognition
  • Method and system for recommending commodities according to commodity images based on image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] like figure 1 As shown, an image recognition-based system for recommending commodities according to commodity images according to an embodiment of the present invention includes a receiving module, an analysis module, and a recommendation module;

[0040] Receiving module: the receiving module includes a photographing unit and a tracking unit; the photographing unit is used for photographing the image information of the product and transmits the information to the analysis module; the tracking unit is used for interacting with the photographing unit and controlling the images captured by the photographing unit Adjustment of angle and focal length;

[0041] Analysis module: The analysis module is used to receive the information transmitted by the receiving module, compare other product information through the network, and finally transmit all the product information with high contrast to the recommendation module;

[0042] Recommendation module: The recommendation modul...

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 computers, and particularly relates to a method and system for recommending commodities according to commodity images based on image recognition, and the system comprises a receiving module, an analysis module and a recommendation module. The receiving module comprises a shooting unit and a tracking unit; the shooting unit is used for shooting image information of a product and transmitting the information to the analysis module; the tracking unit is used for interacting with the shooting unit and controlling the shooting angle and focal length adjustment of the shooting unit; the tracking unit is added in the receiving module, so that the receiving module can accurately track the position and the distance of a product needing to be identified, the focal length and the angle of the receiving module are adjusted, the shooting quality is improved, meanwhile, the influence of the surrounding environment on product shooting is reduced, and the subsequent analysis process is easier and more accurate.

Description

technical field [0001] The invention belongs to the field of computers, in particular to a method and system for recommending commodities according to commodity images based on image recognition. Background technique [0002] With the development of science and technology, people gradually begin to change from offline shopping to online shopping. In order to meet the needs of each customer, the platform can recommend similar products with high similarity based on the image information of the products. [0003] A Chinese patent with publication number CN110992141A discloses a method, device and electronic device for recommending commodities based on recognizing commodity images. By combining the commodity images browsed by the user, the constructed commodity category recognition model is used to automatically estimate the number of commodity images browsed by the user. The category information of the product, according to the estimated product category information, recommends...

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): G06Q30/06G06V20/00G06V10/147B08B1/00
CPCG06Q30/0631B08B1/00
Inventor 丁伟
Owner 丁伟