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

Label completion method and device based on cross validation, terminal and storage medium

A cross-validation and labeling technology, applied in the field of machine learning, can solve problems such as inaccurate labeling and local discriminant model paranoia, and achieve the effect of ensuring security, improving performance and

Pending Publication Date: 2019-10-15
WEBANK (CHINA)
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The main purpose of the present invention is to provide a label completion method, system, device and storage medium based on cross-validation, aiming to solve the problem that the labels added by the local discriminant model in the existing label complement have a strong influence on the local discriminant model. Technical issues with paranoia and inaccurate labeling

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
  • Label completion method and device based on cross validation, terminal and storage medium
  • Label completion method and device based on cross validation, terminal and storage medium
  • Label completion method and device based on cross validation, terminal and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0040] Such as figure 1 as shown, figure 1 It is a schematic structural diagram of a terminal in the hardware operating environment involved in the solution of the embodiment of the present invention.

[0041] Such as figure 1 As shown, the terminal may include: a processor 1001 such as a CPU, a network interface 1004 , a client interface 1003 , a memory 1005 , and a communication bus 1002 . Wherein, the communication bus 1002 is used to realize connection and communication between these components. The customer interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional customer interface 1003 may also include a standard wired interface and a wireless interface. Optionally, the network interface 1004 may include a standard wired interface and a wireless int...

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 label completion method based on cross validation. The method comprises the following steps of generating a to-be-calibrated label by a first terminal corresponding to a second sample based on a first sample, a first label corresponding to the first sample and the second sample, and then determining a target label by the first terminal corresponding to the second sample based on the second sample, the to-be-calibrated label and a cross validation algorithm. The invention further discloses a device, a terminal and a storage medium. According to the invention, the biasof the label to the local discrimination model is solved, the performance of the machine model and the accuracy of label completion are improved, and the security of the data of each terminal is ensured at the same time.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a cross-validation-based label completion method, terminal, device and storage medium. Background technique [0002] Machine learning algorithms based on supervised learning require sufficient labeled samples to train the model in order to achieve the desired effect. In real application scenarios, the labels of some (or even most) training samples are missing, and samples without labels will not be used for model training. We usually have to give up these samples, which will not only cause waste of sample data, but also The sample data used to train the machine learning model is insufficient, thus reducing the generalization ability of the training model. [0003] At present, the existing technical solutions are to collect more labeled samples or label unlabeled samples. However, manual collection of labeled samples or sample labeling often requires professiona...

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): G06N20/00
CPCG06N20/00
Inventor 康焱刘洋陈天健杨强
Owner WEBANK (CHINA)