Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic iterative operation and maintenance method and system for AI model, equipment and storage medium

An operation and maintenance system and model technology, applied in the field of artificial intelligence, can solve the problems of high manual operation and maintenance costs and difficulty in manual iterative training model operation and maintenance, and achieve the effects of reducing operation and maintenance costs, version transparency, and complex logic isolation.

Pending Publication Date: 2020-07-28
SHANGHAI CTRIP COMMERCE CO LTD
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide an automatic iterative operation and maintenance method, system, equipment and storage medium of an AI model in order to overcome the defects of difficulty in operation and maintenance of the manual iterative training model and high cost of manual operation and maintenance in the prior art

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 iterative operation and maintenance method and system for AI model, equipment and storage medium
  • Automatic iterative operation and maintenance method and system for AI model, equipment and storage medium
  • Automatic iterative operation and maintenance method and system for AI model, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] Such as figure 1 As shown, this embodiment provides an automatic iterative operation and maintenance method for an AI model, including the following steps:

[0070] Step 101, obtain the version number corresponding to the training set, the training method, the version name corresponding to the AI ​​model to be replaced, and the version name corresponding to the AI ​​model to be trained; wherein, the training method includes incremental training and full training; the training set is nearly a week The data can also be the data uploaded by yourself.

[0071] In this embodiment, the training method depends on the configuration of operation and maintenance personnel, and incremental training and / or full training can be selected.

[0072] Step 102: Use the training service to automatically download the training set, the AI ​​model to be replaced, and the AI ​​model to be trained from the file system according to the version number, the version name corresponding to the AI ​...

Embodiment 2

[0097] Such as figure 2 As shown, this embodiment provides an automatic iterative operation and maintenance system of an AI model, including a front end 1 , a management end 2 and a training server end 3 .

[0098] Front-end 1 is used to obtain the version number and training method corresponding to the training set. The training method includes incremental training and full training; the training set is the data of the past week.

[0099] The management terminal 2 is used to obtain the version name corresponding to the AI ​​model to be trained and the version name corresponding to the AI ​​model to be replaced.

[0100] Such as image 3 As shown, the training server 3 includes a download module 301 , a verification module 302 , a training module 303 , a model conversion module 304 , an evaluation module 305 , and a replacement module 306 .

[0101] The download module 301 is used to automatically download the training set, the AI ​​model to be trained and / or the AI ​​model...

Embodiment 3

[0125] Figure 7 It is a schematic structural diagram of an electronic device provided by Embodiment 3 of the present invention. The electronic device includes a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the computer program, the automatic iterative operation and maintenance method of the AI ​​model in Embodiment 1 is implemented. Figure 7 The electronic device 30 shown is only an example, and should not limit the functions and scope of use of the embodiments of the present invention.

[0126] Such as Figure 7 As shown, electronic device 30 may take the form of a general-purpose computing device, which may be a server device, for example. Components of the electronic device 30 may include, but are not limited to: at least one processor 31 , at least one memory 32 , and a bus 33 connecting different system components (including the memory 32 and the processor 31 ).

[0127] The bus 33 include...

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 an automatic iterative operation and maintenance method and system for an AI model, equipment and a storage medium. The automatic iterative operation and maintenance method forthe AI model comprises the steps of obtaining a version number corresponding to a training set and a version name corresponding to a to-be-trained AI model; automatically downloading the training setand the to-be-trained AI model from the file system by using the training service according to the version number and the version name; enabling the training service to use the training set to automatically train the AI model to be trained; enabling the training service to automatically evaluate the training effect to obtain an evaluation result; and enabling the training service to judge whetherto replace the model according to the evaluation result, and if yes, automatically and thermally loading the replacement model. According to the method, the AI training side service is taken as the center, the management end is matched, automatic iterative operation and maintenance of the AI model can be realized, and various different model operation and maintenance and version configurations can be realized according to different scenes; and operation and maintenance personnel are isolated from complex logic of each service model, the version is transparent, and the operation and maintenance efficiency can be improved on the basis of reducing the operation and maintenance cost.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an automatic iterative operation and maintenance method, system, device and storage medium of an AI (Artificial Intelligence, artificial intelligence) model. Background technique [0002] Based on AI technology, a variety of businesses will generate a large number of deep learning or machine learning models. The training data of the models comes from online, and the online data will change over a long period of time, such as changes in the ratio of black and white samples and the proportion of dirty data. , however, the model produced by training with historical data cannot perceive changes in online data, which will cause the model to no longer fit the actual data, and the accuracy or recall rate will decrease. For the iteration of the AI ​​model, it is necessary to regularly fetch online data, retrain the model after data cleaning, or do incremental trai...

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): G06N3/00G06N20/00
CPCG06N3/008G06N20/00
Inventor 范博周海刚陈宇艾青王乐
Owner SHANGHAI CTRIP COMMERCE CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com