CN-122022998-A - Enterprise credit risk determination method, device, equipment and medium

CN122022998ACN 122022998 ACN122022998 ACN 122022998ACN-122022998-A

Abstract

The embodiment of the invention discloses an enterprise credit risk determining method, device, equipment and medium, and relates to the technical field of financial science and technology. The method comprises the steps of obtaining target basic data of a target enterprise, wherein the target basic data comprises target attribute data, target business data and target login data, determining a target resource probability prediction model of the target enterprise, inputting the target attribute data and the target business data into the target resource probability prediction model to obtain target resource probability, inputting the target attribute data into the login probability prediction model to obtain target login probability, grouping the target enterprise according to the target resource probability and the target login probability to obtain an enterprise risk group, determining a reference enterprise corresponding to the enterprise risk group, and determining target credit risk levels of all target enterprises in the enterprise risk group according to the reference basic data of the reference enterprise and the target basic data of the target enterprise. The accuracy and the efficiency of enterprise credit risk determination are improved.

Inventors

TANG SHANSHAN
ZENG WENHUA
LI YAJING

Assignees

中国工商银行股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260126

Claims (10)

1. A method for determining credit risk of an enterprise, comprising: acquiring target basic data of a target enterprise, wherein the target basic data comprises target attribute data, target service data and target login data; determining a target resource probability prediction model of a corresponding target enterprise according to the target business data, and inputting target attribute data and target business data of the target enterprise into the corresponding target resource probability prediction model to obtain target resource probability of the target enterprise; Inputting the target attribute data of the target enterprise into a trained login probability prediction model to obtain the target login probability of the target enterprise, and grouping the target enterprise according to the target resource probability and the target login probability to obtain an enterprise risk group; And determining at least one reference enterprise corresponding to the enterprise risk group according to the candidate resource probability and the candidate login probability of each candidate enterprise in a preset enterprise list, and determining the target credit risk level of each target enterprise in the enterprise risk group according to the reference basic data of the reference enterprise and the target basic data of the target enterprise.
2. The method of claim 1, wherein determining the target credit risk level for each target enterprise in the enterprise risk group based on the reference base data for the reference enterprise and the target base data for the target enterprise comprises: For any enterprise risk group, determining a reference basic vector of a corresponding reference enterprise according to reference basic data of each reference enterprise corresponding to the enterprise risk group, and determining a target basic vector of a corresponding target enterprise according to target basic data of each target enterprise in the enterprise risk group; Determining candidate vector similarity between target basic vectors of target enterprises in the enterprise risk group and reference basic vectors of reference enterprises respectively; and determining the target credit risk level of the corresponding target enterprise according to the similarity of the candidate vectors.
3. The method of claim 2, wherein determining the target credit risk level for the respective target enterprise based on the candidate vector similarity comprises: For any target enterprise, determining target vector similarity from candidate vector similarity of the target enterprise; and determining a target similarity interval in which the target vector similarity is positioned from a preset candidate similarity interval, and taking the candidate credit risk grade corresponding to the target similarity interval as the target credit risk grade of the target enterprise according to the corresponding relation between the preset candidate similarity interval and the candidate credit risk grade.
4. The method of claim 1, wherein grouping the target enterprises according to the target resource probability and the target login probability to obtain an enterprise risk group comprises: Based on a preset grouping coordinate axis, determining the distribution condition of the target enterprise on the preset grouping coordinate axis according to the target resource probability and the target login probability; and dividing target enterprises in the same quadrant into a group according to the distribution condition to obtain an enterprise risk group.
5. The method according to claim 4, wherein the method further comprises: Determining the quadrant distribution quantity of a target enterprise in each quadrant according to the distribution condition, and determining the distribution quantity difference value between different quadrants according to the quadrant distribution quantity; And if the distribution number difference value between any two quadrants is larger than a preset number difference value threshold, adjusting the coordinate axis origin in the preset grouping coordinate axes.
6. The method according to any one of claims 1-5, wherein determining a target resource probability prediction model for a respective target enterprise from the target business data comprises: aiming at any target enterprise, determining a target resource stage of the target enterprise according to target business data of the target enterprise; and taking the reference resource probability prediction model corresponding to the target resource stage as a target resource probability prediction model of the target enterprise.
7. An enterprise credit risk determination apparatus, comprising: The system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring target basic data of a target enterprise, and the target basic data comprises target attribute data, target service data and target login data; The target resource probability determining module is used for determining a target resource probability prediction model of a corresponding target enterprise according to the target business data, and inputting target attribute data and target business data of the target enterprise into the corresponding target resource probability prediction model to obtain target resource probability of the target enterprise; The enterprise risk group determining module is used for inputting the target attribute data of the target enterprise into a trained login probability prediction model to obtain the target login probability of the target enterprise, and grouping the target enterprise according to the target resource probability and the target login probability to obtain an enterprise risk group; The credit risk level determining module is used for determining at least one reference enterprise corresponding to the enterprise risk group according to the candidate resource probability and the candidate login probability of each candidate enterprise in a preset enterprise list, and determining the target credit risk level of each target enterprise in the enterprise risk group according to the reference basic data of the reference enterprise and the target basic data of the target enterprise.
8. An electronic device, comprising: one or more processors; A memory for storing one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement an enterprise credit risk determination method as claimed in any one of claims 1 to 6.
9. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements an enterprise credit risk determination method as claimed in any one of claims 1-6.
10. A computer program product comprising computer programs/instructions which when executed by a processor implement the steps of the enterprise credit risk determination method of any of claims 1-6.

Description

Enterprise credit risk determination method, device, equipment and medium Technical Field The embodiment of the invention relates to the technical field of financial science and technology, in particular to an enterprise credit risk determining method, device, equipment and medium. Background In the financial field, the enterprise credit risk refers to the possibility that an enterprise cannot fulfill debts or contractual obligations on time and at full cost due to various uncertain factors in the business activities, thereby bringing economic losses to interested parties. In the prior art, the credit risk of the enterprise is usually determined manually, and the conditions of lower accuracy and efficiency exist. Disclosure of Invention The invention provides an enterprise credit risk determining method, device, equipment and medium, which are used for improving the accuracy and efficiency of enterprise credit risk determination. According to an aspect of the present invention, there is provided an enterprise credit risk determining method, including: acquiring target basic data of a target enterprise, wherein the target basic data comprises target attribute data, target service data and target login data; determining a target resource probability prediction model of a corresponding target enterprise according to the target business data, and inputting target attribute data and target business data of the target enterprise into the corresponding target resource probability prediction model to obtain target resource probability of the target enterprise; Inputting the target attribute data of the target enterprise into a trained login probability prediction model to obtain the target login probability of the target enterprise, and grouping the target enterprise according to the target resource probability and the target login probability to obtain an enterprise risk group; And determining at least one reference enterprise corresponding to the enterprise risk group according to the candidate resource probability and the candidate login probability of each candidate enterprise in a preset enterprise list, and determining the target credit risk level of each target enterprise in the enterprise risk group according to the reference basic data of the reference enterprise and the target basic data of the target enterprise. According to another aspect of the present invention, there is provided an enterprise credit risk determination apparatus, including: The system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring target basic data of a target enterprise, and the target basic data comprises target attribute data, target service data and target login data; The target resource probability determining module is used for determining a target resource probability prediction model of a corresponding target enterprise according to the target business data, and inputting target attribute data and target business data of the target enterprise into the corresponding target resource probability prediction model to obtain target resource probability of the target enterprise; The enterprise risk group determining module is used for inputting the target attribute data of the target enterprise into a trained login probability prediction model to obtain the target login probability of the target enterprise, and grouping the target enterprise according to the target resource probability and the target login probability to obtain an enterprise risk group; The credit risk level determining module is used for determining at least one reference enterprise corresponding to the enterprise risk group according to the candidate resource probability and the candidate login probability of each candidate enterprise in a preset enterprise list, and determining the target credit risk level of each target enterprise in the enterprise risk group according to the reference basic data of the reference enterprise and the target basic data of the target enterprise. According to another aspect of the present invention, there is provided an electronic apparatus including: one or more processors; A memory for storing one or more programs; The one or more programs, when executed by the one or more processors, enable the one or more processors to perform any one of the enterprise credit risk determination methods provided by the embodiments of the present invention. According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement any one of the enterprise credit risk determination methods provided by the embodiments of the present invention when executed. According to another aspect of the present invention, there is provided a computer program product comprising a computer program/instruction which, when executed by a processor, implements any of th