Method and device for optimizing data processing model

A technology of data processing and processing models, applied in electrical digital data processing, instruments, calculations, etc., can solve problems such as low efficiency of optimization, and it is not easy to find wrong code modules

Active Publication Date: 2018-03-09
PING AN TECH (SHENZHEN) CO LTD
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for optimizing a data processing model, so as to solve the problem that the existi

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
  • Method and device for optimizing data processing model
  • Method and device for optimizing data processing model
  • Method and device for optimizing data processing model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 The implementation flow of the data processing model optimization method provided by the first embodiment of the present invention is shown, and the details are as follows:

[0046] In step S101, input parameters for calculation processing of the data processing model are received.

[0047] Specifically, the data processing model may be a multi-parameter calculation model widely used in various industries, such as an insurance premium calculation model used in the insurance industry, or an environmental index evaluation model, etc. When the data processing model is an insurance premium calculation model, the corresponding input parameters may include: one or more of insurance product code, insurance product type, insurance business type, occupation of the insured, monthly salary of the insured, and premium calculation direction .

[0048] The data processing model includes a new data processing model and an old data processing model. Wherein, the old data pr...

Embodiment 2

[0060] figure 2 The implementation flow of the data processing model optimization method provided by the second embodiment of the present invention is shown, and the details are as follows:

[0061] In step S201, input parameters for calculation processing of the data processing model are received.

[0062] In step S202, the input parameters are respectively input into the old data processing model and the new data processing model to generate a first processing result and a second processing result respectively.

[0063] Steps S201-S202 are basically the same as steps S101-S102 in Embodiment 1, and will not be repeated here.

[0064] In step S203, when the absolute value of the difference between the first processing result and the second processing result exceeds a preset threshold, according to the input parameter, the code module corresponding to the input parameter is searched.

[0065] Specifically, in the embodiment of the present invention, the corresponding relatio...

Embodiment 3

[0074] image 3 The implementation flow of the data processing model optimization method provided by the third embodiment of the present invention is shown, and the details are as follows:

[0075] In step S301, input parameters for calculation processing of the data processing model are received.

[0076] In step S302, the input parameters are respectively input into the old data processing model and the new data processing model to generate a first processing result and a second processing result respectively.

[0077] Steps S301-S302 are basically the same as steps S101-S102 in Embodiment 1, and will not be repeated here.

[0078] In step S303, the absolute values ​​of the differences between the plurality of first processing results and the second processing results are sorted from large to small.

[0079] When data processing is performed on input parameters, multiple abnormal results may appear within the same period of time (that is, the absolute value of the differen...

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

A method for optimizing a data processing model comprises the steps that input parameters for being calculated and processed by the data processing model are received; the input parameters are input into an old data processing model and the new data processing model respectively, and a first processing result and a second processing result are generated; when the absolute value of a difference value between the first processing result and the second processing result exceeds a preset threshold value, the new data processing model is optimized according to the input parameters, the first processing result and the second processing result. The first processing result and the second processing result are compared with a standard data processing result, therefore, possibly wrong code areas canbe checked more accurately, and the new data processing model is optimized more effectively.

Description

technical field [0001] The invention belongs to the field of software optimization, in particular to an optimization method and device for a data processing model. Background technique [0002] In order to obtain data results under the influence of multiple factors, technology developers usually build a data processing model including multi-parameter factors. In the data processing model, by analyzing the interaction between various parameter factors, the cumulative effect between multiple parameter factors, etc., the data processing results can be calculated and obtained relatively quickly and effectively. For example, for the insurance cost calculation model, after inputting the relevant information of the user, information such as the amount of the user's insurance premium can be automatically calculated. [0003] During the use of the data processing model, new parameter factors may be added to the data processing model to form a new data structure, or optimize the codi...

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
IPC IPC(8): G06F11/36
CPCG06F11/3628
Inventor 吴观峰丁杰凌剑吴海波马向东
Owner PING AN TECH (SHENZHEN) 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