Task relationship determination method and device and equipment

A technology for determining method and task relationship, applied in the field of communication, which can solve problems such as poor reliability and inability to guarantee the accuracy of multi-task transfer learning.

Pending Publication Date: 2021-12-28
HUAWEI CLOUD COMPUTING TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] At present, the association between multiple tasks usually depends on the advice of experts in the field to which the task belongs. The expert determines the association between multiple tasks based on his own knowledge, which usually has poor credibility and cannot guarantee multi-task migration. Accuracy of learning and other deficiencies

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
  • Task relationship determination method and device and equipment
  • Task relationship determination method and device and equipment
  • Task relationship determination method and device and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Before describing a method and device for determining a task relationship provided by the embodiment of the present application, the concepts involved in the embodiment of the present application will be described first:

[0050] (1), task, sample

[0051] In this embodiment of the present application, a data processing process in a scenario may be called a task, and different tasks correspond to different scenarios, and data in different tasks follow different rules (that is, objective functions). The data processing process in a scenario can be performed by a model, for example, a flaw detection model can be used to detect defects on a printed circuit board (PCB), and a face detection model can be used to detect faces in an image. detection.

[0052] Taking PCB defect detection as an example, the defect detection of PCBs produced by one production line can be regarded as one task, while the defect detection of PCBs produced by different production lines is a differen...

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 task relationship determination method and device and equipment, which are used for automatically determining an association relationship between tasks. In the application, a relationship discovery device can firstly determine sample attributes and corresponding attribute values in each task; then, according to the sample attribute of each task and the corresponding attribute value, the task attribute of each task and the corresponding attribute value is determined; after each task attribute and the corresponding attribute value are determined, the mixed attribute of each task is determined on the basis of the sample attribute and / or the task attribute of each task, and then the associated tasks, namely the association relationship between the tasks, are determined on the basis of the task mixed attribute of each task, so that the whole process does not depend on related personnel; the associated task can be efficiently determined.

Description

technical field [0001] The present application relates to the field of communication technology, and in particular to a method, device and equipment for determining task relationship. Background technique [0002] Machine learning is the core of artificial intelligence. It mainly uses computers to simulate human learning behavior. In essence, machine learning is to construct an objective function. The error of the prediction results of the objective function based on training samples is as small as possible. Machine learning In the process, it is necessary to use sufficient training samples to fit an objective function to ensure that the objective function can fully display the statistical distribution of the data. [0003] But at present, machine learning is only used to construct the objective function of a single scene (also can be understood as a single task), but in actual application, the objective function constructed by machine learning needs to predict the data of m...

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): G06F9/48G06N20/00
CPCG06F9/4881G06N20/00
Inventor 郑子木任浩
Owner HUAWEI CLOUD COMPUTING 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