Hybrid machine learning model operation method and device and related equipment

A technology of machine learning model and operation method, which is applied in the field of machine learning, can solve problems such as many data instructions, low service efficiency, and many interactions between the client and the server, so as to reduce network delay, improve service efficiency, and reduce The Effect of Logical Complexity

Pending Publication Date: 2021-03-23
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the number of data instructions sent by the client to the server will lead to

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
  • Hybrid machine learning model operation method and device and related equipment
  • Hybrid machine learning model operation method and device and related equipment
  • Hybrid machine learning model operation method and device and related equipment

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0059]An exemplary embodiment of the present invention will be described in more detail below with reference to the accompanying drawings. While the exemplary embodiments of the present invention are shown in the drawings, it is understood that the present invention can be implemented in various forms and is not limited thereto. Instead, these embodiments are provided to be more thoroughly understood, and the range of the scope of the invention can be communicated to those skilled in the art.

[0060]Such asfigure 1 As shown, the present embodiment proposes a method of operating a hybrid machine learning model, and a plurality of machine learning models may include multiple machine learning models in the hybrid machine learning model. The operating method can be applied to electronic devices, and electronic devices can save assembly line definition files, and electronic devices can deploy a linear engine, each machine learning model, and various machine learning models respectively 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 hybrid machine learning model operation method and device and related equipment, and the method comprises the steps: obtaining initial input data, and employing an assembly line engine to analyze an assembly line definition file so as to determine the operation sequence of all machine learning models; and inputting the initial input data into a machine learning model witha first operation sequence in the hybrid machine learning model, and sequentially operating the corresponding machine learning models by using the operation environment according to the determined operation sequence to obtain final output data output by the hybrid machine learning model. According to the method, after the primary data instruction including the initial input data sent by the client is obtained, the hybrid machine learning model is controlled to operate to obtain the final output data output by the hybrid machine learning model, the client does not need to send the data instruction again, the interaction frequency between the client and the electronic equipment, namely the server, can be reduced. The network delay generated by interaction between the client and the server is reduced, and the service efficiency is effectively improved.

Description

Technical field[0001]The present invention relates to the field of machine learning, and more particularly to a method, apparatus, and related equipment of a hybrid machine learning model.Background technique[0002]With the rapid development of artificial intelligence science and technology, machine learning technology has continued to improve.[0003]Currently, when the prior art provides users with the user with a hybrid machine learning model, the various machine learning models in the hybrid machine learning model can be deployed at the server, and the control logic of the control logic to the machine learning model is deployed on the client. . The server can return the output data of the hybrid machine learning model to the client to provide users with relevant services.[0004]The prior art is in the use of a hybrid machine learning model, the client needs to control each machine learning model to start running by sending multiple network requests to the server, such as two machine...

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
IPC IPC(8): G06F9/48G06F9/445G06N20/00
CPCG06F9/4881G06F9/44521G06N20/00Y02D10/00
Inventor 郝滋雨
Owner BEIJING QIYI CENTURY SCI & 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