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

Supplier multi-index evaluation method based on error back-propagation algorithm

A technology of error back propagation and evaluation method, applied in business, computing, data processing applications, etc., can solve problems such as excessive subjective arbitrariness, and achieve the effect of improving fairness and rationality

Pending Publication Date: 2022-02-25
上海华能电子商务有限公司 +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the traditional evaluation process, the weight is mainly determined by human experience, and the subjective arbitrariness is too large

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
  • Supplier multi-index evaluation method based on error back-propagation algorithm
  • Supplier multi-index evaluation method based on error back-propagation algorithm
  • Supplier multi-index evaluation method based on error back-propagation algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] refer to figure 1 , which is the first embodiment of the present invention, this embodiment provides a supplier multi-index evaluation method based on the error back propagation algorithm, including:

[0052] S1: Unify the original evaluation data to obtain evaluation data.

[0053] What needs to be explained is that the evaluation data is scored according to the index system. Most of the indicators in different index systems are the same, and a small number of indicators are different. Therefore, the original evaluation data needs to be processed in a unified manner; the scoring method of each indicator It is divided into two types: discrete and continuous. Discrete grades such as fail, pass, good, and excellent are discrete data, and continuous grades are numerical grades.

[0054] If more than half of the indicators in the original evaluation data use discrete scoring, then make all the indicators in the original evaluation data adopt discrete scoring; otherwise, us...

Embodiment 2

[0106] In order to verify and explain the technical effect adopted in this method, this embodiment conducts simulation experiments on index data, and compares the test results by means of scientific demonstration, so as to verify the real effect of this method.

[0107] Select 200 simulated multi-indicator evaluation data, each evaluation data is composed of the supplier's score on 12 different indicators and the supplier's total score; firstly, the original evaluation data is unified, and the following table shows the processed part Evaluation data.

[0108] Table 1: Part of the evaluation data after unified processing.

[0109]

[0110] The weight of each indicator is set to 0.1 or 0.05, and the total score is obtained by the weighted sum of each indicator; the total score within [90,100] is set as grade A, and the total score within [80,90) is set as grade B , the total score in [70,80) is set as grade C, and the rest is set as grade D.

[0111] After the evaluation da...

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 supplier multi-index evaluation method based on an error back-propagation algorithm, and the method comprises the steps: carrying out the unified processing of original evaluation data, and obtaining the evaluation data; selecting indexes with obvious distinction degree by utilizing a decision tree, judging whether the indexes are included in the index system or not, if the indexes are not included in the index system, performing expert reexamination on the unincluded indexes, judging whether the indexes are included in the index system or not, and if the indexes are not included in the index system, deleting the indexes; if the indexes are included in the index system, replacing the indexes in the evaluation data with the selected indexes, and complementing vacancy values in the evaluation data; determining the weights of the selected indexes through the error back-propagation algorithm, establishing an evaluation model, inputting scores of the suppliers on the indexes into the evaluation model, and obtaining final scores. According to the method, the reasonable scoring rule can be automatically extracted, the weight of the index in the final score is intelligently determined, and the fairness and rationality of the evaluation result are improved.

Description

technical field [0001] The invention relates to the technical field of supplier index evaluation, in particular to a supplier multi-index evaluation method based on an error backpropagation algorithm. Background technique [0002] With the development of the economy and the progress of science and technology, the overall market environment has undergone earth-shaking changes, and the competition among enterprises has also developed into the competition among supply chains. Suppliers of electric power enterprises are the source of the supply chain. The quality of raw materials directly affects the quality of products. The overall level of suppliers of electric power enterprises is closely related to the operation and management of enterprises. It is one of the core tasks of modern enterprises to select and establish cooperation with the most high-quality electric power enterprise suppliers. High-quality electric power enterprise suppliers can not only improve the product qual...

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): G06Q10/06G06Q30/06
CPCG06Q10/06393G06Q10/067G06Q30/0605
Inventor 向泽江王绪繁胡俊马晓燕黄云飞黄杰刘超
Owner 上海华能电子商务有限公司