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

Identification method, device, electronic device and readable storage medium for multi-label information

A recognition method and multi-label technology, applied in the computer field, can solve the problem of poor self-consistency of recognition results, and achieve the effect of improving self-consistency

Active Publication Date: 2021-06-29
BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present disclosure is to provide a multi-tag information identification method, device, electronic equipment and readable storage medium, at least to a certain extent, to overcome the problem of poor self-consistency of multi-tag identification results in the related art

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
  • Identification method, device, electronic device and readable storage medium for multi-label information
  • Identification method, device, electronic device and readable storage medium for multi-label information
  • Identification method, device, electronic device and readable storage medium for multi-label information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0040] Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities ...

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 disclosure provides a multi-label information identification method, device, electronic equipment and readable storage medium, and relates to the technical field of computers. Wherein, the identification method of multi-label information includes: training the multi-label recognition model through training labels, the input end of the prediction branch of the multi-label identification model is introduced with a cyclic network, and the cyclic network is used to learn the relationship between multiple training labels; Construct a tag-restricted relationship set based on the branch prediction results of the multi-label recognition model. The tag-restricted relationship set includes label combinations that meet the preset label rules; obtain multi-label messages to be identified; and restrict the relationship set according to the trained multi-label recognition model and tags. , to determine the recognition result of the multi-label information. Through the technical proposal of the present disclosure, the accuracy, reliability and self-consistency of identifying multiple tags are improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a multi-label information identification method, device, electronic equipment and readable storage medium. Background technique [0002] Multi-label recognition is an important direction in the field of machine learning, and it also has broad application scenarios in real life. [0003] In related technologies, most of the multi-label recognition methods are based on the deep network model as the feature extractor. Taking the multi-label recognition method of the image as an example, the features are extracted through the convolutional neural network for recognition, and at least the following technical problems exist: [0004] (1) There is a problem of poor self-consistency in the recognition results for each label. [0005] (2) In the post-processing process of multiple tag recognition, it is introduced in the form of a matrix or a single layer of network, its g...

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 Patents(China)
IPC IPC(8): G06N20/00G06N3/08
CPCG06N3/08G06N20/00
Inventor 于伟王林芳梅涛
Owner BEIJING WODONG TIANJUN INFORMATION TECH CO LTD