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

Deep learning model release method and device

A deep learning and model technology, which is applied in other database retrieval, website content management, network data retrieval, etc., can solve the problems of time-consuming and inefficient model release process relying on labor, etc., to shorten release time, improve release efficiency, and save labor Effects on cost and O&M costs

Active Publication Date: 2020-09-15
TENCENT TECH (SHENZHEN) CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a deep learning model release method and device, which can solve the problem that the model release process is heavily dependent on labor, time-consuming and inefficient, and can improve the efficiency of model release

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
  • Deep learning model release method and device
  • Deep learning model release method and device
  • Deep learning model release method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the technical solutions and advantages of the present invention clearer, the embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0033] This disclosure is mainly applied to the release automation of models under the network platform, and supports core capabilities such as sample management, model management, model release, and model monitoring. Supports a series of complex operations such as daily routine management of models, model training, model evaluation, model release, model update, and manual rollback on the network platform. The user interface of the network platform such as figure 1 Shown; the technical framework of the network platform is shown in figure 2 As shown, it mainly includes: front end, webserver, data storage, scheduling engine, functional modules, data engine and other parts.

[0034] Among them, the front end can use the bootstrap framework combined wit...

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 a deep-learning model publishing method and a device. The deep-learning model publishing method comprises the following steps: receiving model generation event information of afirst user and storing the model generation event information in a database; sending the model generation event information to a second user; upon receiving a pre-issue instruction of the second user,pre-publishing the generated model stored in the target disk based on the model generation event information of the generated model carried by the test machine and the pre-issued instruction, and publishing the generated model to the target platform when the running condition of the generated model meets the first preset condition. By publishing the in-depth learning training model completely automatically on the network platform, not only the publishing time can be greatly shortened, but also the publishing efficiency of the in-depth learning system model can be improved. At the same time, due to the zero manual release, the labor cost and operation and maintenance costs are greatly saved.

Description

technical field [0001] The present invention relates to the field of model distribution, in particular to a method and device for publishing a deep learning model. Background technique [0002] With the rise of artificial intelligence and big data, deep learning technology has been widely used in many fields, such as computer vision, image processing, natural language processing, information classification, search, recommendation, and big data, which have played a huge role in promoting effect. [0003] Many network platforms have launched recommendation and search services based on deep neural network algorithms (Deep Neural Network, DNN). This recommendation and search service is usually implemented by building deep learning models into network platforms. These models need to be developed by technical personnel. Conduct training and publish it on the platform for users to use. [0004] At present, when publishing models on the network platform, one type adopts a fully ma...

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 Patents(China)
IPC IPC(8): G06F16/958
Inventor 马国俊
Owner TENCENT TECH (SHENZHEN) CO LTD