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

Modeling method and device, storage medium and electronic equipment

A modeling method and modeling data technology, applied in the field of artificial intelligence, can solve problems such as poor prediction accuracy of artificial intelligence models, sudden changes in the trend of input variables, and deviations of indicators to be predicted.

Pending Publication Date: 2021-06-04
CHINA CONSTRUCTION BANK
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the current artificial intelligence model has certain limitations. When an unexpected event occurs in a specific small time interval within a certain period of time, causing a sudden change in the trend of a variable entered into the model or a significant deviation in the index to be predicted, the artificial intelligence model will fail. Poor prediction 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
  • Modeling method and device, storage medium and electronic equipment
  • Modeling method and device, storage medium and electronic equipment
  • Modeling method and device, storage medium and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1 It is a schematic flowchart of a modeling method provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of creating a high-precision prediction model in the presence of data mutations. This method can be implemented by the modeling device provided by the embodiment of the present invention. For execution, the modeling device may be implemented by software and / or hardware, and the modeling device may be configured on an electronic computing device such as a computer or a server. The method specifically includes the following steps:

[0050] S110. Acquire historical data for modeling, where the historical data includes impact factors and result factors.

[0051] S120. Set a dummy variable and a variable value of the dummy variable based on the mutation of the outcome factor.

[0052] S130. Construct a prediction model based on the dummy variable, the impact factor, and the outcome factor.

[0053] The prediction model pred...

Embodiment 2

[0078] Figure 4 is an example flow diagram of a modeling method provided in Embodiment 2 of the present invention, which is optimized on the basis of the above embodiments. Optionally, based on the dummy variable, the impact factor and the result factor Before constructing the prediction model, the method further includes: preprocessing each of the impact factors based on the type of each of the impact factors. Specifically, the method does not include:

[0079] S210. Acquire historical data for modeling, where the historical data includes impact factors and result factors.

[0080] S220. Set a dummy variable and a variable value of the dummy variable based on the mutation of the outcome factor.

[0081] S230. Perform preprocessing on each of the impact factors based on the type of each of the impact factors.

[0082] S240. Construct a prediction model based on the dummy variable, the impact factor, and the outcome factor.

[0083] In this embodiment, due to the different...

Embodiment 3

[0088] Figure 5 It is a schematic flowchart of a modeling method provided by Embodiment 3 of the present invention, which is optimized on the basis of the above embodiments. Optionally, the method further includes: creating a stress scenario; under the stress scenario, based on The prediction model performs a prediction task to obtain a prediction result. The method specifically includes:

[0089] S310. Acquire historical data for modeling, where the historical data includes impact factors and result factors.

[0090] S320. Set a dummy variable and a variable value of the dummy variable based on the mutation of the outcome factor.

[0091] S330. Perform preprocessing on each of the impact factors based on the type of each of the impact factors.

[0092] S340. Construct a prediction model based on the dummy variable, the impact factor, and the outcome factor.

[0093] S350. Create a stress scenario. Under the stress scenario, perform a prediction task based on the predicti...

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 relates to the technical field of artificial intelligence, and discloses a modeling method and device, a storage medium and electronic equipment. The modeling method comprises the steps: acquiring the historical data used for modeling, wherein the historical data comprise influence factors and result factors; setting a virtual variable and a variable value of the virtual variable based on the mutation of the result factor; and constructing a prediction model based on the virtual variable, the influence factor and the result factor. In the embodiment of the invention, the virtual variable is set on the basis of the historical data used for modeling, and the virtual variable is used for representing the burst factor, that is, the influence of the burst factor is considered in the modeling process, so the pressure measurement capability and the prediction precision of the prediction model are improved; the prediction value under the emergency can be accurately predicted through the prediction model, the coping strategy can be set in advance according to the prediction result, and the adverse effect caused by the emergency can be avoided.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of artificial intelligence, and in particular to a modeling method, device, storage medium and electronic equipment. Background technique [0002] With the continuous development of artificial intelligence, artificial intelligence is widely used in different technical fields, such as the prediction of financial risks and the order prediction of e-commerce platforms. [0003] However, the current artificial intelligence model has certain limitations. When an unexpected event occurs in a specific small time interval within a certain period of time, causing a sudden change in the trend of a variable entered into the model or a significant deviation in the index to be predicted, the artificial intelligence model will fail. Poor prediction accuracy. Contents of the invention [0004] Embodiments of the present invention provide a modeling method, device, storage medium, and electronic...

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): G06Q10/04G06Q10/06G06F17/18
CPCG06F17/18G06Q10/04G06Q10/0639
Inventor 夏成扬舒杨
Owner CHINA CONSTRUCTION BANK