A simulation evaluation method and device for running an algorithm model on a mobile terminal

A technology of algorithm model and evaluation method, applied in the field of artificial intelligence, to achieve the effect of ensuring correctness and authenticity, improving evaluation efficiency, improving evaluation efficiency and coverage

Active Publication Date: 2022-07-22
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, model evaluation for mobile devices is a pain point for end-side intelligence

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
  • A simulation evaluation method and device for running an algorithm model on a mobile terminal
  • A simulation evaluation method and device for running an algorithm model on a mobile terminal
  • A simulation evaluation method and device for running an algorithm model on a mobile terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0019] In order to realize device-side intelligence, the machine learning model produced on the cloud side can be compressed and converted to obtain a device-side machine learning model with a smaller model size and suitable for mobile devices. Based on the device-side machine learning model, model inference can be achieved. The process is comp...

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

Embodiments of the present application provide a simulation evaluation method and device for running an algorithm model on a mobile terminal. In the embodiment of the present application, in the model evaluation oriented to the mobile terminal, for some device evaluation environments, a cloud evaluation environment adapted to the cloud side resources is simulated, which can replace some real device devices for model evaluation, and solve the problem of The problem of model evaluation for all real machine equipment; for another part of the equipment evaluation environment, the corresponding real machine equipment is used for real machine evaluation, and the machine learning model is evaluated based on the real machine environment and the cloud evaluation environment. The problem of model evaluation for real machine equipment provides conditions for the implementation of end-to-end intelligence. It can also take into account the evaluation advantages of both the model evaluation based on the real machine environment and the model evaluation based on the cloud evaluation environment. The evaluation efficiency of the machine learning model, the correctness and authenticity of the evaluation results, and the automatic evaluation for the mobile terminal.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a simulation evaluation method and device for running an algorithm model on a mobile terminal. Background technique [0002] Machine learning is the study of computer algorithms, which hopes to automatically optimize the performance of computer algorithms (or models) through data or previous experience. Usually, machine learning models are obtained by machine learning engineers completing data collection and algorithm design for the problem, and then using traditional cloud-side machine learning frameworks such as TensorFlow and PyTorch for model training in the cloud. In the model inference process, the mobile device initiates a model request to the cloud, and the cloud uses the machine learning model to perform related computing tasks and returns the task results to the mobile device for further processing by the mobile device. This way of using ...

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): G06F11/34G06N20/00
CPCG06F11/3409G06F11/3447G06F11/3457G06N20/00
Inventor 吕承飞吴飞牛超越顾仁杰
Owner ZHEJIANG UNIV
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