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

Updating method, device and equipment of search model and computer readable storage medium

A model and sub-model technology, applied in the field of search model update methods, equipment and computer-readable storage media, and devices, can solve problems such as model degradation and reduce search accuracy, so as to improve deployment efficiency and alleviate the phenomenon of model degradation. Effect

Pending Publication Date: 2022-04-12
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, after analyzing the experimental results, it is found that there will be model degradation during the "hot refresh" process. This phenomenon is caused by "negative inversion", that is, pictures that can be retrieved correctly by the old model cannot be correctly retrieved by the new model, thereby reducing the search accuracy. Rate

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
  • Updating method, device and equipment of search model and computer readable storage medium
  • Updating method, device and equipment of search model and computer readable storage medium
  • Updating method, device and equipment of search model and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] In order to make the purpose, technical solutions and advantages of the application clearer, the application will be further described in detail below in conjunction with the accompanying drawings. All other embodiments obtained under the premise of creative labor belong to the scope of protection of this application.

[0073] In the following description, references to "some embodiments" describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or a different subset of all possible embodiments, and Can be combined with each other without conflict.

[0074] In the following description, the term "first\second\third" is only used to distinguish similar objects, and does not represent a specific ordering of objects. Understandably, "first\second\third" Where permitted, the specific order or sequencing may be interchanged such that the embodiments of the application described herein can be practiced in sequences oth...

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 provides a search model updating method and device, equipment and a computer readable storage medium. The method comprises the steps of obtaining an old search model currently used online, a new search model to be deployed online and training data, wherein the training data comprises a plurality of training images and label information corresponding to each training image; performing feature extraction on the plurality of training images by using the old search model to obtain old training features; performing degradation-free compatible training on the new search model by utilizing the training data and the old training features to obtain a trained new search model; and deploying the trained new search model to be online, and carrying out candidate image library updating and image search by utilizing the trained new search model. Through the method, the waiting period of model deployment can be shortened, and the prediction accuracy of the search model can be ensured.

Description

technical field [0001] The present application relates to artificial intelligence technology, and in particular to a search model updating method, device, equipment and computer-readable storage medium. Background technique [0002] Image retrieval means that when the user inputs a picture of interest (query picture), the search system first extracts the features of the picture, and then retrieves pictures related to the query picture from the candidate image database by comparing the feature similarity . With the optimization of the deep learning framework and the increase of training data, in order to improve system performance and improve user experience, the industry usually requires regular system updates. The system update includes cold refresh and hot refresh. The "cold refresh" update mode refers to re-extracting features from the candidate image library with the updated new model, and the new model cannot be deployed online until the feature update is completed. Th...

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): G06N3/08G06N3/04G06V10/774G06V10/771G06V10/764G06V10/40
Inventor 张斌杰葛艺潇李昱徐敘远王烨鑫单瀛
Owner TENCENT TECH (SHENZHEN) CO LTD
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