Enterprise risk analysis method, apparatus, computer device and storage medium

Abstract

The present application relates to the field of big data technology and is applied to the financial industry, and provides an enterprise risk analysis method, an apparatus, a computer device and a storage medium. The methods include: obtaining the data information of the enterprise to be analyzed, data indicators are generated to obtain target portrait data of the enterprise to be analyzed, Obtaining the risk case portrait data in the preset case base, measuring the risk similarity between the target portrait data and the risk case portrait data, obtaining the risk index corresponding to the risk case portrait data whose risk similarity exceeds the set threshold, comparing the data index with the risk index, and obtaining the risk information of the enterprise to be analyzed. By means of similarity measurement and analysis between the data of the enterprises to be analyzed and the data in the case base, acquiring the risk information of the enterprises to be analyzed based on the comparison results of the data indexes and the risk indexes, without the model training steps, thus saving time and improving the efficiency of risk analysis.

Description

technical field [0001] The present application relates to the technical field of big data, in particular to an enterprise risk analysis method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of technology, forecasting and analysis technologies based on various algorithms have emerged, which can use the assessment and analysis of enterprise risks. [0003] Most of the traditional methods for enterprise risk analysis are machine learning algorithms, such as: logistic regression, random forest, neural network, etc., but these algorithm models, especially neural network algorithms, require a large amount of training data to accurately learn their In some models, the training and learning of a large amount of data takes a long time. For real-time systems, the control range of response time makes the use of these models have certain disadvantages, resulting in analysis efficiency that cannot meet the requirements. Contents...

AI Technical Summary

Problems solved by technology

[0003] Most of the traditional methods for enterprise risk analysis are machine learning algorithms, such as: logistic regression, random forest, neural network, etc., but these algorithm models, especially neural network algorithms, require a large amount of training data to accurately learn their In some models, the training and learning of a large amount of data takes a long time. For real-time systems, the control range of response time makes the use of these models have certain disadvantages, resulting in analysis efficiency that cannot meet the demand.

Images