Model training method and system and electronic equipment

A model training and training model technology, applied in the field of model training, can solve problems such as inaccurate association between fields and data elements, and inability to obtain data elements

Pending Publication Date: 2022-02-08
ZHEJIANG DAHUA TECH CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, in order to associate the fields of enterprise original data as standard data, the existing models are trained according to the semantic similarity between fields and data elements. Fields are the names of data in enterprise original data. Due to the variety of field naming methods, fields Contains underscores, spaces, mixed Chinese and English, etc., resulting in inaccurate associations between fields and data elements obtained through the trained model, or the data elements corresponding to the input fields cannot be obtained through 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 training method and system and electronic equipment
  • Model training method and system and electronic equipment
  • Model training method and system and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0118] refer to figure 1 , the present application provides a method for model training, which can obtain a prediction model, through which the accuracy of field association results can be improved and the problem that the field cannot match the corresponding data element can be avoided. The implementation process is as follows:

[0119] Step S1: Obtain standard data and original data, establish a first association relationship between the standard data and the original data, and obtain training samples.

[0120] The specific process of obtaining standard data in the embodiment of this application: Since the national standard organization has formulated the standard files of relevant data elements and each enterprise has a professional database related to data processing, read the standard files formulated by the national standard organization and the data of each enterprise. Professional database, extract standard tables, standard fields and data elements specified by nation...

Embodiment 2

[0149] refer to figure 2 , the application provides a data processing method, which can process the original data of the enterprise, thereby improving the accuracy of field association results and avoiding the problem that the field cannot match the corresponding data element. The implementation process of the method as follows:

[0150] Step S21: receiving the data input by the user and classifying the data.

[0151] To receive the data entered by the user, in order to distinguish the field from the actual table, it is necessary to classify the data entered by the user. The specific method of classification is as follows:

[0152] Method 1: Determine the type of data according to the file format of the data.

[0153] After receiving the data input by the user, judge the file format of the data. If the format of the data is the format corresponding to the document, such as TXT format, DOC format, then use the data input by the user as a field, such as the format of the data...

Embodiment 3

[0168] refer to image 3 , this application provides a method for data matching, which can mark fields as data elements, avoiding the problem that the fields cannot match the corresponding data elements. The implementation process of this method is as follows:

[0169] Step S31: when receiving the data input by the user, input the data into the predictive model.

[0170] When the data input by the user is received, since the data has already been classified into fields and actual tables, and the actual table has also been transformed into multiple fields, it is only necessary to input the data into the prediction model.

[0171] Step S32: Input the data into the prediction model and output the training result as a data element.

[0172] After data processing, the user inputs the data that needs to be associated with data elements into the prediction model, and the data will be matched with each data element in the prediction model to obtain the existence probability value cor...

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 model training method and system and electronic equipment, and the method comprises the steps: obtaining standard data and original data, building a first incidence relation between the standard data and the original data, obtaining a training sample, building a second incidence relation between the standard data and the reality data according to the semantic similarity between the standard data and the reality data, according to the first incidence relation and the second incidence relation, obtaining initial atlas data, putting the training sample into the initial atlas data, putting the initial atlas data into an atlas neural network model for N times of training, and obtaining N loss values, and taking the training model corresponding to the minimum loss value in the N loss values as the prediction model. Learning training is carried out on the initial map data through the method to obtain the prediction model, and the data element corresponding to the maximum loss value is screened out through the prediction model when the input fields are matched, so that the accuracy of a field association result is improved.

Description

technical field [0001] The present application relates to the field of model training, in particular to a method, system and electronic equipment for model training. Background technique [0002] With the advent of the era of big data, data has become an important asset of enterprises. When the same type of data is analyzed in different enterprises, due to the nature of the enterprise and the different needs of the enterprise, the evaluation criteria for the same batch of data are different, resulting in The same type of data corresponds to different evaluation criteria. For example, for the same type of live broadcast delivery data, the evaluation standard for media companies is whether the ratio of the number of fans who consume in the live broadcast room to the number of fans in the live broadcast room reaches the expected ratio. The judging criterion for a company of a financial nature is whether the turnover of the live broadcast reaches the expected turnover. [0003]...

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): G06N3/08G06N3/04G06F16/36G06F16/35G06F16/33G06F16/335
CPCG06N3/08G06N3/04G06F16/367G06F16/35G06F16/337G06F16/3344G06F16/3346
Inventor 李先飞王龙陈立力周明伟
Owner ZHEJIANG DAHUA TECH CO LTD
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