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

Automatic updating method and device, computer equipment and storage medium

An automatic update and computer program technology, applied in the field of machine learning, can solve problems such as continuous deployment and restart of models that cannot be automatically updated, and achieve the effect of automatic deployment

Pending Publication Date: 2019-08-27
PINGAN PUHUI ENTERPRISE MANAGEMENT CO LTD
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above method requires a lot of human resources for monitoring and deployment, and the system needs to be restarted when the machine learning model is updated, and the continuous deployment of the updated model cannot be automated

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
  • Automatic updating method and device, computer equipment and storage medium
  • Automatic updating method and device, computer equipment and storage medium
  • Automatic updating method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] see figure 1 , in the automatic updating method of a kind of machine training model of the present embodiment, comprise the following steps:

[0043] S1: Monitor the model training cycle in the configuration file, and trigger an update task when the model training cycle is reached.

[0044] The present invention saves various parameters involved in the machine model training process in the configuration file, and the specific configuration file is composed of multiple configuration tables, such as the basic configuration table for recording basic configuration information such as various server addresses and paths, and the basic configuration table for recording machine training. The core configuration table of core configuration parameters such as the name, address, and training cycle of the model, and the task record table that records parameters such as the task completion status of machine learning model training. The automatic update task in the present invention ...

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 automatic updating method and device for a machine training model, computer equipment and a storage medium, and the method comprises the steps: monitoring a model training period in a configuration file, and triggering an updating task when the model training period is reached; performing training of a first machine learning model according to the updating task; when monitoring that training is completed, downloading the trained first machine learning model to a local directory; and updating the original machine learning model into the first machine learning model. Through the scheme of the invention, the machine training model generated by the model training end can be automatically provided for the client to call. Task information loaded by the model is set through an instruction and a configuration mode, a model training end is connected through a file server and a message queue mode, monitoring is achieved in the system, processing, packaging and reheatingdeployment are conducted after a new model is received, and therefore automatic deployment of the machine training model can be achieved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to an automatic update method, system, computer equipment and storage medium with time management function. Background technique [0002] At present, the machine learning model is separated from each other in the training stage and the application stage, that is, in the training stage, a large amount of data calculation is used to train the required model, and in the application stage, the model is manually built into an executable program, and the method and interface are encapsulated transfer. The above method requires a lot of human resources for monitoring and deployment, and the system needs to be restarted when the machine learning model is updated, and the continuous deployment of the updated model cannot be realized automatically. Contents of the invention [0003] The object of the present invention is to provide an automatic update method, system, compu...

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): G06N20/00H04L29/08
CPCG06N20/00H04L67/06
Inventor 黄晓龙
Owner PINGAN PUHUI ENTERPRISE MANAGEMENT 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