Query-based classifier training method and device

A training method and classifier technology, applied in the field of query-based classifier training, can solve problems such as classifier training redundancy.

Active Publication Date: 2021-09-07
BEIJING GRIDSUM TECH CO LTD
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Embodiments of the present invention provide a query-based classifier training method and device to at least solve the technical problem of redundancy in the prior art when performing classifier training for a single query

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
  • Query-based classifier training method and device
  • Query-based classifier training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] According to an embodiment of the present invention, a method embodiment of a query-based classifier training method is provided. It should be noted that the steps shown in the flow chart of the accompanying drawings can be implemented in a computer system such as a set of computer-executable instructions and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that shown or described herein.

[0023] figure 1 is a query-based classifier training method according to an embodiment of the present invention, such as figure 1 As shown, the method includes the following steps:

[0024] Step S102, using the query training set to train a weight model and using each training sample in the query training set to train a ranking model respectively, wherein the query training set includes multiple queries, and the training samples include at least two queries.

[0025] Specifically, the query ...

Embodiment 2

[0043] According to an embodiment of the present invention, a product embodiment of a query-based classifier training device is provided, figure 2 is a query-based classifier training device according to an embodiment of the present invention, such as figure 2 As shown, the device includes a training module, a first determination module, a second determination module and a third determination module, wherein the training module is used to use the query training set to train the weight model and use each training sample of the query training set to A ranking model is obtained through training, wherein the query training set includes multiple queries, and the training samples include at least two queries; the first determination module is used to determine the first macro average accuracy of the weight model and the second macro average accuracy of each ranking model Accuracy rate; the second determination module is used to determine the gain of the classifier according to the...

Embodiment 3

[0054] According to an embodiment of the present invention, a product embodiment of a storage medium is provided, on which a program is stored, and when the program is running, the device where the storage medium is located is controlled to execute the above query-based classifier training method, or when the program is executed by the processor Implements the query-based classifier training method described above.

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 query-based classifier training method and device. Wherein, the method includes: using the query training set to train the weight model and using each training sample of the query training set to train respectively to obtain the sorting model, wherein the query training set includes multiple queries, and the training samples include at least two queries; determining the weight The first macro average accuracy of the model and the second macro average accuracy of each ranking model; the gain of the classifier is determined according to the first macro average accuracy and the second macro average accuracy; the classifier is determined according to the gain. The invention solves the technical problem of redundancy in the prior art when classifier training is performed for a single query.

Description

technical field [0001] The invention relates to the field of computer internet, in particular to a query-based classifier training method and device. Background technique [0002] With the rapid development of online social networks, social networks have become an important source of information in people's daily life. The most representative Twitter abroad and the most representative Sina Weibo in China have attracted hundreds of millions of people from all over the world. Internet users. Taking Weibo as an example, there are a lot of news generated on Weibo every minute and every second, and it has even become one of the fastest and most comprehensive news sources. However, the overwhelming news updates every day also make it difficult for users to quickly browse the effective information they really need—it must be highly relevant to user input queries while ensuring the timeliness of Weibo. Therefore, how to quickly and effectively return user requests, that is, microb...

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): G06F16/9535G06F16/9536G06K9/62G06Q50/00
CPCG06Q50/01G06F16/9535G06F18/24
Inventor 马庆丽
Owner BEIJING GRIDSUM 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