Enterprise credit evaluation method and device and electronic equipment

Abstract

The invention provides an enterprise credit evaluation method and device and electronic equipment. The method comprises the steps of obtaining feature information of a to-be-evaluated enterprise, wherein the feature information comprises dimension indexes and enterprise data corresponding to each dimension index, and the dimension indexes comprise at least one of a total order completion rate, a cost profit rate, a product quality qualification rate, an on-time delivery rate, an order management cost, an inventory cost and a communication cost; inputting the feature information into a pre-trained probabilistic graph model, so that the probabilistic graph model outputs a credit value of the to-be-evaluated enterprise according to the feature information, wherein the probabilistic graph model is obtained based on enterprise relationship training in the supply chain; therefore, the relation between other enterprises and the to-be-evaluated enterprise is effectively utilized from the angle of the supply chain of the enterprise in the enterprise credit value evaluation process by utilizing the probability graph model, the evaluation method is enriched, and the credit value precision of the to-be-evaluated enterprise is improved.

Description

technical field [0001] The invention relates to the technical field of enterprise credit, in particular to an enterprise credit evaluation method, device and electronic equipment. Background technique [0002] In the current era of big data, corporate credit is a comprehensive expression of corporate product services, capital operations, public relations, operating status, and management capabilities. Corporate credit has become an invisible asset and proof of comprehensive strength for companies in the era of big data. Therefore, it has long-term significance to establish a reliable, accurate, updated and timely enterprise credit evaluation system. [0003] The existing methods mainly use linear regression to evaluate personal credit or corporate credit. In the supervised learning scenario, linear regression modeling is performed on the collected corporate information and known credit evaluation values, so that the trained regression model Output the credit rating of the e...

AI Technical Summary

Problems solved by technology

Although this method can realize the evaluation of enterprise credit ratings, the characteristic data is relatively single, and most of them are enterprise data of enterprises to be evaluated artificially. Therefore, the existing evaluation methods are relatively single, which reduces the credit evaluation value of enterprises and leads to Credit rating is not ideal

Images