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

Method and device for determining a recognition model

A technology for identifying models and determining methods. Applied in the field of human-machine identification, it can solve the problems of poor model effect and incomplete data, and achieve the effect of improving the recognition rate and generalization ability.

Active Publication Date: 2022-05-13
TONGDUN HLDG CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the above problems, the embodiment of the present application provides a method for determining a recognition model, which can solve the problem of incomplete data or poor model effect in human-machine recognition in the prior 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
  • Method and device for determining a recognition model
  • Method and device for determining a recognition model
  • Method and device for determining a recognition model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In order to make the above objects, features and advantages of the present application more obvious and comprehensible, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0027] refer to figure 1 , which shows a flow chart of the steps of an embodiment of a method for determining a recognition model of the present application, which may specifically include the following steps:

[0028] Step 101, acquire data to be trained and data to be tested.

[0029] Wherein, the data to be trained and the data to be tested both include C categories of data.

[0030] For example, the data to be trained and the data to be tested can be different data sets from the same data source. For a platform, according to the data source of the platform, it can be divided into PC and mobile; according to the product, the data source includes bio Features (fingerprint, iris, voiceprint, face, gai...

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 embodiment of the present application provides a method and device for determining a recognition model. The method includes: obtaining data to be trained and data to be tested, the data to be trained and the data to be tested both include C categories of data; according to N learning models and the data to be trained, using the Stacking model fusion strategy to predict the probability of the training data and the data to be tested to determine the feature data set; according to the feature data set, the Fisher discriminant model is trained to determine the C-1 dimensional discriminant function model; A target recognition model is output through the preset model evaluation index, and the target recognition model is a discriminant function model meeting the preset model evaluation conditions. It can solve the problem of man-machine recognition, improve the recognition rate and generalization ability of the recognition model.

Description

technical field [0001] The present application relates to the technical field of human-machine identification, in particular to a method and device for determining an identification model. Background technique [0002] In the field of Internet, with the development of machine learning technology, various rich and colorful experiences are provided for users, but network security problems are brought along with it. Therefore, human-machine identification technology is produced. In the existing technology, traditional The machine learning algorithm performs human-machine recognition, and it is a two-category recognition. The human-machine recognition models currently used are all for different platforms, such as training a single classifier for each e-commerce company for this platform, because each platform has its own characteristics, and the data generated by some platforms is incomplete For example, due to equipment, environment, personnel and other conditions, the data ob...

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): G06K9/62
CPCG06F18/285G06F18/214
Inventor 范芳芳
Owner TONGDUN HLDG CO LTD