Model data processing method

A data processing and model technology, applied in the field of data processing, can solve problems such as poor model performance evaluation, and achieve the effect of good feature data

Inactive Publication Date: 2020-01-07
创新奇智(南京)科技有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the defect that the existing feature screening rules have poor performance evaluation of the model, the present invention provides a data processing method for the model

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
  • Model data processing method
  • Model data processing method
  • Model data processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and implementation examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0044] see figure 1 , the present invention provides a kind of data processing method of model, and it comprises the steps:

[0045] P1. Provide a master model X;

[0046] P2. Using the feature data to test the main model X to obtain test results;

[0047] P3. Select the feature data that needs to be further expanded or constructed according to the distribution feedback of the test results in the value of the feature data;

[0048] P4. Construct the selected feature data that needs to be further expanded or constructed to obtain new feature data;

[0049] P5. Use the newly cons...

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 relates to the technical field of data processing, in particular to a model data processing method which comprises the following steps: providing a main model X; p2, testing the main model X by utilizing the characteristic data to obtain a test result; p3, selecting feature data needing to be further expanded or constructed according to effect distribution feedback of thetest resultin the feature data value; p4, constructing the selected feature data needing to be further expanded or constructed to obtain new feature data; p5, retraining the main model X by using the newly constructed new feature data to obtain a model X1, and screening the constructed new feature data; p6, updating the feature data set by utilizing the screened new feature data to obtain an updated featuredata set; and returning to the step P2 again until the model Xn meets the preset stop condition. According to the effect distribution feedback of the test result in the feature data value, the featuredata needing to be further expanded or constructed is selected, so that the screened feature data has a better improvement space for the main model.

Description

【Technical field】 [0001] The invention relates to the technical field of data processing, in particular to a method for processing model data. 【Background technique】 [0002] Existing feature engineering methods usually design features based on the developer's business experience and visualization phenomena, construct new features randomly, through heuristic combinations, or transformation operators, and then filter through the test results of the training model. These methods often cannot fully combine the attributes of the feature data, and the performance of the model cannot be better optimized, or the training time of the model is long or the complexity is high. 【Content of invention】 [0003] Aiming at the defect that the existing feature screening rules have poor performance evaluation of the model, the present invention provides a data processing method for the model. [0004] In order to solve the above-mentioned technical problems, the present invention provides ...

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): G06F16/215G06F16/26
Inventor 刘俊龙周鹏程张发恩
Owner 创新奇智(南京)科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap