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

Model optimization method, device and system, and equipment

An optimization method and model technology, applied in the computer field, can solve the problems of data comparison troubles that are not intuitive, long cycle, low efficiency, etc.

Pending Publication Date: 2021-05-14
上海销氪信息科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This optimization method is inefficient and long-term, and will be coupled with business releases, causing great project risks
In addition, the online effect query must query the database report, and the data comparison is very troublesome and not intuitive.

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
  • Model optimization method, device and system, and equipment
  • Model optimization method, device and system, and equipment
  • Model optimization method, device and system, and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043]The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0044] Most of the existing model optimization training programs need to compare before and after based on the collected effect data, choose a model with better effect, or further test on the basis of adjusting the algorithm of the model according to the existing effect. This offline training method needs to update the model every time, and then resend it online to run for a period of time to collect effect data before performing comparison and optimization agai...

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 model optimization method, device and system, and equipment. The method comprises the following steps: receiving a service scene type and input parameter information sent by a client; determining a target operation model from a preset model library according to the service scene type, and configuring the target operation model by using input features in the input parameter information; based on an ABTest experimental framework, utilizing the configured target operation model to perform corresponding operation processing so as to obtain a model operation result corresponding to the service scene type, and returning the model operation result to the client; and obtaining effect data which is returned by the client and can represent the recognition degree of the model operation result, and determining an optimal model from the target operation model based on the effect data. According to the method, the plurality of offline operation models under the specified service scene type are tested based on the ABTest experimental framework, an optimal model is determined by checking and analyzing the effect data returned by the client online, the optimization period is shortened, and the optimization efficiency is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a model optimization method, device, system and equipment. Background technique [0002] Usually, businesses related to big data use calculation models to a greater or lesser extent. Training is carried out based on user usage and other effect data, and the models are continuously optimized to improve the accuracy of model calculations. However, the optimization training of the model needs to compare before and after according to the collected effect data, that is, the result of model calculation, and choose a model with better effect, or further test on the basis of adjusting the algorithm of the model according to the existing effect. This offline training method requires each time the model is updated, it is resent to the line to run for a period of time to collect performance data, and then it can be compared and optimized again. This optimization method is ineffic...

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): G06F11/36
CPCG06F11/3688G06F11/3664
Inventor 吴限亮
Owner 上海销氪信息科技有限公司
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