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

Dirty data removal method, device, terminal device and readable storage medium

A dirty data, credible technology, applied in the dirty data cleaning method, terminal equipment and readable storage media, device field, can solve the problem that the recognition results affect the accuracy of the recognition model, lack of verification of the accuracy of the recognition results, reduce the recognition accuracy, etc. problem, to achieve the effect of reducing time-consuming recognition, improving user experience, and improving recognition accuracy

Active Publication Date: 2022-04-19
TECHVISION INTELLIGENT TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] With the continuous development of artificial intelligence technology, intelligent recognition technology is widely used, such as face recognition, target tracking, product recognition, etc., the main work of most current intelligent recognition strategies is concentrated before recognition, such as the construction of recognition models, The training of the recognition model, the acquisition and processing of the training sample set, etc. lack the verification of the accuracy of the recognition results. Therefore, for some recognition models that rely on the recognition results for training, the wrong recognition results will affect the accuracy of the recognition model. Reduce recognition accuracy

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
  • Dirty data removal method, device, terminal device and readable storage medium
  • Dirty data removal method, device, terminal device and readable storage medium
  • Dirty data removal method, device, terminal device and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] In this embodiment, a method for clearing dirty data is proposed, which is applied to a terminal device, so that dirty data can be dynamically cleared during image recognition by the terminal device, so as to prevent the dirty data from affecting the accuracy of subsequent recognition.

[0066] Exemplary, see figure 1 , in this embodiment, the method for clearing dirty data includes the following steps S100-S300:

[0067] Step S100, using the recognizer to recognize the current image based on the current sample set to obtain a corresponding target recognition result.

[0068] Before the recognizer recognizes the image, it is generally necessary to manually set a control threshold, which will affect the number of recognized targets in the target recognition result. For example, taking the control threshold as similarity as an example, the larger the control threshold, the similar The higher the degree is, the fewer targets may be identified in the target recognition res...

Embodiment 2

[0134] See Figure 7 , in this embodiment, a dirty data cleaning device 10 is proposed, which includes: an acquisition module 11 , an update module 12 and a cleaning module 13 .

[0135] The acquisition module 11 is used to use the recognizer to identify the current image based on the current sample set to obtain the corresponding target recognition result; the update module 12 is used to update the current image according to the target recognition result, the current linked list and the current hash table. Linked list and the current hash table; a clearing module 13, configured to automatically clear dirty data according to the updated current linked list and the current hash table.

[0136] In this embodiment, the dirty data clearing device 10 is used in conjunction with the acquisition module 11, the update module 12 and the clearing module 13 to implement the dirty data clearing method described in the above-mentioned embodiment, and the implementation schemes invol...

Embodiment 3

[0141] In this embodiment, a terminal device is proposed, including a memory and a processor, the memory stores a computer program, and when the computer program runs on the processor, the dirty data clearing method described in the embodiment of the present application is executed.

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 present application discloses a method, device, terminal device and readable storage medium for cleaning dirty data. The method includes using a recognizer to recognize the current image to obtain a corresponding target recognition result; according to the target recognition result, the current linked list and The current hash table updates the current linked list and the current hash table; automatically clears dirty data according to the updated current linked list and the current hash table. This application uses the respective advantages of linked list and hash table to realize automatic clearing of dirty data with extremely low memory overhead and fast response speed, which can not only avoid dirty data occupying memory, but also improve subsequent recognition accuracy and reduce recognition by automatically clearing dirty data Time-consuming, which greatly improves the user experience.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a dirty data cleaning method, device, terminal equipment and readable storage medium. Background technique [0002] With the continuous development of artificial intelligence technology, intelligent recognition technology is widely used, such as face recognition, target tracking, commodity recognition, etc., the main work of most current intelligent recognition strategies is concentrated before recognition, such as the construction of recognition models, The training of the recognition model, the acquisition and processing of the training sample set, etc. lack the verification of the accuracy of the recognition results. Therefore, for some recognition models that rely on the recognition results for training, wrong recognition results will affect the accuracy of the recognition model. Reduce the recognition accuracy. Contents of the invention [0003] In...

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): G06F16/215G06F16/22
CPCG06F16/215G06F16/2255
Inventor 刘世荣李晓辉
Owner TECHVISION INTELLIGENT TECH
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