Unlock instant, AI-driven research and patent intelligence for your innovation.

Data processing method, device, electronic device and storage medium

A data processing and data technology, applied in the computer field, can solve problems affecting the classification accuracy of classification models, achieve the effect of improving data processing efficiency and accuracy, and reducing data processing costs

Active Publication Date: 2021-07-23
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF14 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the prior art, in the application of training classification models based on training data and classifying and identifying objects based on the trained classification models, the quality of the training data directly affects the classification accuracy of the trained classification models. Therefore, it is necessary to provide a A scheme to improve the training data

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 processing method, device, electronic device and storage medium
  • Data processing method, device, electronic device and storage medium
  • Data processing method, device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] A data processing method provided by an embodiment of the present disclosure, such as figure 1 As shown, the method includes steps 110 to 140 .

[0028] Step 110, train the target model based on the training data.

[0029] Wherein, the training data includes preset labels.

[0030] In the process of supervised model training, a large number of training samples need to be collected first as training data. Each training sample is a piece of training data. Usually, each piece of training data is preset with a sample label. Taking the training image quality classification model as an example, the training data is one image after another. Before training the image quality classification model, a sample label is set for each piece of training data, that is, each image, and the sample label is used to indicate the quality level of the image. Taking training a three-category model as an example, the sample label of each piece of training data can be preset to any one of the ...

Embodiment 2

[0049] Embodiments of the present disclosure provide a data processing method, such as figure 2 As shown, the method includes steps 210 to 250 .

[0050] Step 210, train the target model based on the training data.

[0051] Wherein, the training data includes preset labels.

[0052] For the specific implementation manner of training the target model based on the training data, refer to Embodiment 1, which will not be repeated in this embodiment.

[0053] Step 220: Predict the test data by using the target model to determine the prediction accuracy of the target model.

[0054] For the specific implementation of predicting the test data by using the target model and determining the prediction accuracy of the target model, refer to Embodiment 1, which will not be repeated in this embodiment.

[0055] Step 230: Predict the training data by using the target model, and determine the prediction label and the confidence level of the prediction result for each piece of the trainin...

Embodiment 3

[0072] Embodiments of the present disclosure provide a data processing method, such as Figure 4 As shown, the method includes steps 410 to 450 .

[0073] Step 410, train the target model based on the training data.

[0074] Wherein, the training data includes preset labels.

[0075] For the specific implementation manner of training the target model based on the training data, refer to Embodiment 1, which will not be repeated in this embodiment.

[0076] Step 420: Predict the test data by using the target model to determine the prediction accuracy of the target model.

[0077] For the specific implementation of predicting the test data by using the target model and determining the prediction accuracy of the target model, refer to Embodiment 1, which will not be repeated in this embodiment.

[0078] Step 430: Predict the training data by using the target model, and determine the prediction label and the confidence level of the prediction result for each piece of the trainin...

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 data processing method disclosed in the present disclosure belongs to the field of computer technology, and solves the problems of high cost and low efficiency of data processing using manual methods in the prior art. The data processing method in the embodiment of the present disclosure includes: training a target model based on training data; predicting test data through the target model, and determining the prediction accuracy of the target model; predicting the training data through the target model , determine the prediction label and prediction result confidence of each piece of the training data; process the training data according to the preset label, prediction label and prediction result confidence of the training data, and the prediction accuracy. The data processing method provided in this disclosure determines the prediction accuracy of the target model based on the test data, and processes the training data in combination with the prediction accuracy of the target model and the confidence of the prediction result of the training data, which helps to improve the efficiency and accuracy of data processing. and reduce data processing costs.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular, to a data processing method, apparatus, electronic device, and storage medium. Background technique [0002] Classification and recognition based on a model obtained by training is a common method for object classification at present, wherein objects include but are not limited to images, user behaviors, and merchants. Taking the hotel image quality classification of the wine travel platform as an example, it is usually first to train the hotel image quality classification model based on the hotel images manually calibrated with the quality level labels of the graph, and then to classify the target hotel images based on the trained hotel image quality classification model. Classification recognition is performed to determine the quality level of the target hotel image. In the prior art, in the application of training a classification model based on training data, an...

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): G06F16/215G06K9/62G06Q10/06G06Q50/12
CPCG06Q10/06395G06Q50/12G06F18/214
Inventor 康丽萍
Owner BEIJING SANKUAI ONLINE TECH CO LTD