Service processing method and device and electronic equipment

A service processing and service unit technology, applied in the field of communication, can solve problems such as governance that does not support microservices, protocol conversion, data format conversion, redeployment, etc.

Pending Publication Date: 2020-12-08
ALIBABA GRP HLDG LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1. The model service application is monolithic and does not support micro-service governance, resulting in the inability to dynamically expand and contract service resources when the model is running according to different workload types;
[0005] 2. The routing management of the model service is tightly coupled with the machine learning model algorithm, so t...

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
  • Service processing method and device and electronic equipment
  • Service processing method and device and electronic equipment
  • Service processing method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] The solution idea based on the above model deployment, such as figure 2 As shown, it is the flow of the model processing method shown in the embodiment of the present invention Figure 1 , which can be accessed via figure 1 The service grid controller 103 shown in coordinates the execution of the model service processor 104, the service grid metadata processor 106, and the model service orchestrator 112 to complete. Such as figure 2 As shown, the service processing method includes the following steps:

[0079] S210. Create multiple model service units for building model services.

[0080] Specifically, before building a model service based on a machine learning model, the model service with specified business processing capabilities to be built can be subdivided according to the business processing capabilities it has, and presented in the form of multiple model service units, each Each model service unit is endowed with corresponding partial business processing c...

Embodiment 2

[0102] Such as image 3 Shown is the flow of the service processing method of the embodiment of the present invention Figure II . The method steps shown in this example can be used as a supplementary solution to the method in Example 1. Such as image 3 As shown, after the model service is built, the following steps can also be performed:

[0103] S310. Acquire a changed business model used to create a model service unit.

[0104] After the model service is built, if you need to change the business processing algorithm of one of the model service units, you can directly perform machine learning on the business model corresponding to the model service unit to obtain the changed business model without modifying other model services unit as well as the management model to make changes.

[0105] S320. Inject the network proxy in the service grid into the change business model to form a change model service unit.

[0106] S330. Orchestrate the change model service unit and i...

Embodiment 3

[0127] Such as Figure 6 Shown is the structure of the service processing device of the embodiment of the present invention Figure 1 , the service processing device can be set in figure 1 In the service mesh controller shown, for executing figure 2 The method steps shown in, it comprises:

[0128] A service unit creation module 610, configured to create multiple model service units for building model services;

[0129] The management model editing module 620 is used to edit the management models corresponding to multiple model service units, and the management model is used to manage the communication status between the model service units during operation;

[0130] The model service arrangement module 630 is configured to arrange a plurality of model service units and their corresponding management models to construct model services.

[0131] Further, as Figure 7 As shown, the above-mentioned service unit creation module 610 may include:

[0132] A business model acq...

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 embodiment of the invention provides a service processing method and device and electronic equipment, and the method comprises the steps: building a plurality of model service units for building amodel service; editing management models corresponding to the plurality of model service units, wherein the management models are used for managing mutual communication states of the model service units during operation; and arranging the plurality of model service units and the management models corresponding to the model service units, and constructing the model service. According to the schemeprovided by the embodiment of the invention, the defect that the model service is single can be effectively avoided, the micro-service governance is supported, and the flexible deployment of the model service can be realized.

Description

technical field [0001] The present application relates to the technical field of communications, and in particular to a service processing method, device and electronic equipment. Background technique [0002] With the wide application of machine learning, how to efficiently deploy the trained machine learning model to the production environment as a model service is being supported by more and more tools. The formation of model service includes several links: data acquisition, data analysis, data deformation, data verification, data training, model creation, model verification, large-scale training, model release, service provision, model monitoring and logging. In the process, many machine learning tools provide different choices for model developers, and also bring different challenges to model deployment. [0003] Traditional model deployment and runtime environment support have certain drawbacks, including: [0004] 1. The model service application is monolithic and d...

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): G06F8/60G06F9/50G06N20/00
CPCG06F8/60G06F9/5016G06F9/505G06F9/5072G06N20/00
Inventor 王夕宁易立张凯车漾
Owner ALIBABA GRP HLDG 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