Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Rule training method, device and equipment and storage medium

A training method and training algorithm technology, applied in the direction of knowledge expression, etc., can solve problems such as singleness, inaccurate rule analysis, and impact on scalability

Pending Publication Date: 2020-01-03
PING AN TECH (SHENZHEN) CO LTD
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide a rule training method, device, equipment and computer-readable storage medium, aiming to solve the technical problem that the existing data rule analysis is too single, which leads to inaccurate rule analysis and affects its scalability

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
  • Rule training method, device and equipment and storage medium
  • Rule training method, device and equipment and storage medium
  • Rule training method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0063] In the present invention, it provides a rule training method, which is mainly aimed at the method of verifying the extensibility of the analyzed data change law when the data processing equipment analyzes and processes the big data. Divide into multiple subsets, and then deduce and analyze the verification rules of the subsets according to some algorithms (such as the greedy algorithm), obtain the commonality of the verification rules between the subsets, and calculate the continuity level of the verification rules, so as to realize the rule Optimization to improve the verification accuracy of the final data.

[0064] Specifically, it is a regular rolling verification mechanism based on the combination of batch size and greedy algorithm. Through this mechanism, in the massive data verification set, the batch si...

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 big data processing, and discloses a rule training method. The rule training method includes: obtaining a corresponding data sample set according to analgorithm scene of a current data system for data processing; repeatedly extracting a model training sample and a model verification sample from the data sample set by adopting a small-batch extraction algorithm; realizing data rule training based on the two samples and the selected corresponding rule training algorithm to obtain a rule extension model, performing evaluation verification on the rule extension model, and selecting a model with the most ductility as a rule verification module in combination with a greedy algorithm. The invention further discloses a rule training device and equipment and a storage medium, rule optimization is realized, a final rule verification module in the data is obtained, the ductility of the analyzed data rule is further improved, and the verification correctness of the final data is also improved.

Description

technical field [0001] The present invention relates to the technical field of big data processing, in particular to a rule training method, device, equipment and computer-readable storage medium. Background technique [0002] At present, the accuracy of the final conclusions drawn from the classification and verification of data through big data classification and regression models is still relatively low, and the correct prediction of data classification is also relatively low, and the continuity and effectiveness of the law There is no good implementation in the current implementation method, especially when the data volume is more than tens of millions, due to the shortage of office resources such as servers in some small and medium-sized enterprises, it is impossible to support map- reduce, or the overall efficiency becomes very slow, unable to quickly support real-time requirements, thus limiting the mining and verification of some important laws, resulting in the diff...

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): G06N5/02
CPCG06N5/025
Inventor 陈娴娴阮晓雯徐亮
Owner PING AN TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com