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

Data correction method and device, equipment and storage medium

A data correction and data technology, applied in data processing applications, commerce, instruments, etc., can solve the problems of low model prediction accuracy, long data return cycle, incomplete machine learning model training data, etc., to ensure accuracy, The effect of improving the timeliness

Pending Publication Date: 2021-05-14
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, due to the long data return cycle, the training data of the machine learning model is incomplete, the timeliness of model training is poor, and the accuracy of model prediction is low.

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
  • Data correction method and device, equipment and storage medium
  • Data correction method and device, equipment and storage medium
  • Data correction method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0071] figure 1 It is a flow chart of a data correction method according to the first embodiment of the present application. This embodiment is applicable to the situation where unupdated sample data is added to the training process of the prediction model, and the method can be executed by a data correction device , the device is implemented in software and / or hardware, and is preferably configured in electronic equipment, such as a terminal or a server. Such as figure 1 As shown, the method specifically includes the following:

[0072] S110. Perform training according to the updated sample data to obtain a stable prediction model.

[0073] In the specific embodiment of the present application, the sample data refers to the data used to train the prediction model. The sample data consists of a large number of samples. Based on the prediction target, the samples can be divided into positive samples and negative samples. For example, in the scenario of predicting the convers...

no. 2 example

[0097] figure 2 It is a flowchart of a data correction method according to the second embodiment of the present application. On the basis of the first embodiment above, this embodiment further explains the training of the stable prediction model, and can be based on the updated sample data. On the basis of the cycle of time slices, the stable prediction model associated with each time slice is trained. Such as figure 2 As shown, the method specifically includes the following:

[0098] S210. Determine updated sample data and non-updated sample data according to the return time of the sample data and the conversion time threshold of the delivery party to which the sample data belongs.

[0099] In a specific embodiment of the present application, the publisher to which the sample data belongs refers to the client that puts the sample data on the Internet. For example, for sample data such as advertisements, the publisher is the advertiser. Each sample may include information...

no. 3 example

[0112] Figure 4 It is a flow chart of a data correction method according to the third embodiment of the present application. On the basis of the first embodiment above, this embodiment further explains the selection of the anchor point prediction model, which can be based on the stable prediction model On the basis of the data return ratio distribution of the sample data, the anchor time slice and its anchor prediction model are determined. Such as Figure 4 As shown, the method specifically includes the following:

[0113] S410. Perform training according to the updated sample data to obtain a stable prediction model.

[0114] S420. Determine the first data return proportion distribution of the unupdated sample data.

[0115] In a specific embodiment of the present application, the data return ratio distribution refers to the distribution formed by the data return ratio in different time periods. For example, 30% of the data is returned within 0-1 days, 50% of the data i...

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 embodiment of the invention discloses a data correction method and device, equipment and a storage medium, and relates to the technical field of big data. According to the specific implementation scheme, the method includes performing training according to updated sample data, and obtaining a stable prediction model; selecting an anchor point prediction model from the stable prediction model according to the unupdated sample data; predicting the updated sample data and the non-updated sample data according to the anchor point prediction model to obtain an updated prediction result and a non-updated prediction result respectively; and according to the updated prediction result and the non-updated prediction result, correcting the non-updated sample data for training a prediction model by adopting the corrected non-updated sample data. According to the invention, the incomplete non-updated sample data is corrected by using the relatively complete updated sample data, so that the sample data can still participate in model training under the condition that the conversion period is not reached and the sample data is incomplete, the timeliness of model training is improved, and meanwhile, the accuracy of model training is ensured.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, in particular to the field of big data technology, and specifically to a data correction method, device, device, and storage medium. Background technique [0002] With the rapid development of computer technology, more and more fields are using models for prediction to improve the effectiveness of data usage based on prediction results. For example, conversion rate prediction for advertisements or advertisers. At present, due to the long data return cycle, the machine learning model training data is incomplete, the timeliness of model training is poor, and the accuracy of model prediction is low. Contents of the invention [0003] The embodiment of the present application provides a data correction method, device, device and storage medium, which can correct the unupdated sample data, so as to add the unupdated sample data to the training of the model, and provide...

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): G06Q30/02G06Q10/04
CPCG06Q30/0242G06Q10/04Y02D10/00
Inventor 丁娇李沛龙刘琦凯秦首科
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) 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

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