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

Annotation information verification method and device and category determination method and device

A technology for labeling information and categories, applied in the field of labeling information verification, can solve problems such as labeling errors, low data accuracy, and high similarity of SKU pictures

Active Publication Date: 2020-04-24
TENCENT CLOUD COMPUTING BEIJING CO LTD
View PDF14 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the number of SKU pictures is large, and the similarity of SKU pictures is high, which is prone to labeling errors, resulting in low accuracy of data stored in the SKU retrieval database

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
  • Annotation information verification method and device and category determination method and device
  • Annotation information verification method and device and category determination method and device
  • Annotation information verification method and device and category determination method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0104] The embodiment of the present application provides a method for verifying labeling information, a method and a device for determining a category, which are used to determine the corresponding intra-class similarity and inter-class similarity for images in the SKU search database, based on the intra-class similarity and The similarity between classes generates the verification result of the annotation information corresponding to the image, so that the image can be removed or modified according to the verification result, thereby improving the accuracy of the SKU retrieval data in the database.

[0105] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the embodime...

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 annotation information verification method and device and a category determination method and device. Corresponding intra-class similarity and inter-class similarity are determined for images in an SKU retrieval database. Based on the intra-class similarity and the inter-class similarity, the verification result of the annotation information corresponding to the image isgenerated, so that operations such as elimination or modification can be performed on the image according to the verification result, and the accuracy of retrieving the data in the database by the SKU is improved. The method comprises the steps of obtaining a to-be-verified image, a first image set and a second image set; determining the similarity in the target class according to the to-be-verified image and the first image set; determining target inter-class similarity according to the to-be-verified image and the second image set; and determining a verification result of the target annotation information according to the target intra-class similarity and the target inter-class similarity.

Description

technical field [0001] The present application relates to the field of artificial intelligence, in particular to a method for verifying marked information, a method and a device for determining a category. Background technique [0002] Due to the high damage rate of unmanned shelves and the high cost of vending machines, smart containers have gradually become a new trend in the field of unmanned retail. Smart containers generally adopt cashless transactions and ordinary currency transactions. For example: self-service orange machine, self-service coffee machine, self-service ice cream machine and unmanned self-service vending machine, etc. Due to the unmanned vending characteristics of smart cabinets, replenishment personnel are required to regularly check for replenishment, so that smart cabinets can meet the needs of users at any time. [0003] At present, there is a shooting device inside the smart container, which regularly takes pictures of the Stock Keeping Unit (SKU...

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): G06F16/53G06F16/58G06K9/62
CPCG06F16/5866G06F16/53G06F18/23213G06F18/214
Inventor 卓炜刘强沈小勇刘文龙戴宇荣
Owner TENCENT CLOUD COMPUTING BEIJING CO LTD