Analysis method and system for quantifying influence of characteristic indexes on labels, medium and terminal

A technology for quantifying features and analysis methods, applied in the computer field, it can solve problems such as narrow application, inapplicable influence, and inability to label influence, and achieve the effect of accurate prediction results, close connection with reality, and universality.

Pending Publication Date: 2021-10-29
中冶赛迪信息技术(重庆)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing analysis methods, when faced with the analysis of the impact of multiple eigenvalues, the existing methods cannot directly quantify the influence of eigenvalues ​​on label values, and are not even suitable for th

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
  • Analysis method and system for quantifying influence of characteristic indexes on labels, medium and terminal
  • Analysis method and system for quantifying influence of characteristic indexes on labels, medium and terminal
  • Analysis method and system for quantifying influence of characteristic indexes on labels, medium and terminal

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0077] Example 1

[0078] The following is quantified by rolling the fuel consumption parameters of the rolling steel to quantify the fuel consumption as a specific application scenario, and the analysis is analyzed by the first quantization impact model.

[0079] S1101. First, obtain the process of rolling process parameters history data.

[0080] In the present embodiment, the method of acquiring the rolling process parameter history data can be directly called from the rolling process database, and the data in the rolling process database can obtain accumulated, operator autonomous setting, and the system automatically periodically adds accumulated Real-time data, etc. For example, the specific call parameters are: * # * Heating segment residual value * # *, * # * all-hot section residual value * # *, * # * preheating section residual oxygen content * # *, * # * heating section Almost air-fuel ratio * # *, * # * Heating section air-fuel ratio * # *, * # * all over the rolling m...

Example Embodiment

[0093] Example 2

[0094] The following is quantified by rolling the fuel consumption parameters of rolling steel as a specific application scenario, and analyzes by the second quantization impact model.

[0095] S1201. Get the process of the rolling process parameters history data.

[0096] In the present embodiment, the method of acquiring the rolling process parameter history data is directly called from the rolling process database, and the data in the rolling process database can obtain accumulated, the operator is independently set, and the system automatically periodically adds accumulated real-time. Data, etc. The specific call parameters are: * # * Heating segment residual value * # *, * # * Swong segment residual value * # *, * # * warm-up section residual oxygen content * # *, * # * Heating section Burning * # *, * # * Heating section air-fuel ratio * # *, * # * all-hot section air-fuel * # *, * # * all-hot section rolling side air-fuel ratio * # *, *, * The heat-fuel r...

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 provides an analysis method and system for quantifying influence of characteristic indexes on labels, medium and terminal and the method comprises the steps: obtaining sample data, calibrating the sample data, building a quantitative influence model according to the calibrated sample data, and training the quantitative influence model; wherein the quantitative influence model comprises a first quantitative influence model used for carrying out regression prediction on label influence according to the quantitative characteristic indexes and a second quantitative influence model used for data matching analysis; selecting a first quantitative influence model or a second quantitative influence model according to a sample data volume and a service demand, obtaining an influence quantitative value, and completing analysis of the influence of the quantitative characteristic index on the label; By expansion selection of multiple basic models and construction of a comprehensive scoring system, a prediction result can be more accurate, through data matching analysis, an analysis result is more visual and is more closely related to reality, and the invention is not limited to abnormal quantitative analysis, has universality and is beneficial to helping a user to optimize regulation and control.

Description

technical field [0001] The present invention relates to the field of computer technology, and in particular to an analysis method, system, medium and terminal for quantifying the impact of characteristic indicators on labels. Background technique [0002] With the development of computer technology, network data is growing rapidly. In the context of the era of big data, the demand for big data and the pursuit of the meaning represented by data make the mining and analysis of data very important. At present, there are many methods for analyzing data. By inputting the corresponding algorithm into the computer and then substituting the data, the relationship between the data can be obtained. When actual needs arise, new data processing methods can be obtained through the combination and optimization of algorithms. Therefore, the algorithm is not static, and new optimizations can be made according to specific needs. [0003] At present, in a production project, mining and anal...

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
IPC IPC(8): G06K9/62
CPCG06F18/21
Inventor 张涛汤槟余鹏毛尚伟吴润宇
Owner 中冶赛迪信息技术(重庆)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