CN114493837A - Credit agency marking method and device, electronic equipment and storage medium - Google Patents

Abstract

The invention discloses a marking method for a credit institution. The method includes: constructing an evaluation index system according to the operation status information of the credit institution, the evaluation index includes a continuous evaluation index and a discrete evaluation index; Determine the number of abnormal evaluation indicators at each time point within the first preset time period; when it is detected that the abnormal number of evaluation indicators at the first time point is greater than the preset threshold, the first time point is used as the dividing line to move forward The second preset time period is used to mark abnormal credit institution samples; wherein, the continuous evaluation indicators include the first overdue rate, the first six overdue rates, the first 12 overdue rates, the current 90+ overdue rate, the post-loan fraud rate and Loan rejection rate, the discrete evaluation indicators include institutional blacklist and business operation status. Through the above method, the state of the credit institution can be measured from multiple perspectives, and the abnormal time of the credit institution can be detected in time and an effective warning can be given.

Description

Credit institution marking method, device, electronic device and storage medium

technical field

The present application relates to the technical field of data processing, and in particular, to a credit institution marking method, device, electronic device and storage medium.

Background technique

For financial companies that are mainly engaged in offline credit business, the management of their branches is an extremely important part of the risk management system. At present, the commonly used method of institutional management is mainly to assess the quality of their assets, and to define the branch’s status by overdue indicators. Risk situation, mainly in the form of various overdue indicators monitoring reports, daily, weekly, monthly, quarterly, annual reports, etc.; further, select key indicators to give different weights and scores, and score and summarize various indicators based on expert experience .

At present, the marking scheme of the credit institution management model is based on the result marking, which is suitable for the evaluation after the risk is completely released. Effective evaluation cannot be carried out during the release process, resulting in the inability to measure the status of the credit institution from multiple perspectives and discover the credit in time. An unusual time for the institution.

Therefore, how to measure the status of credit institutions from multiple perspectives, detect the abnormal time of credit institutions in time and give effective early warning, is a technical problem to be solved at present.

SUMMARY OF THE INVENTION

The invention discloses a marking method for a credit institution, which is used to solve the problem in the prior art that the state of the credit institution cannot be measured from multiple perspectives, and the abnormal time of the credit institution can be detected in time and effectively warned. include:

Build an evaluation index system according to the operation status information of the credit institution, and the evaluation index includes a continuous evaluation index and a discrete evaluation index;

Judging the abnormal number of evaluation indicators at each time point within the first preset time period according to the continuous evaluation index threshold and the discrete evaluation index threshold;

When it is detected that the abnormal number of the evaluation index at the first time point is greater than the preset threshold, the credit institution sample is marked abnormally by using the first time point as the dividing line and a second preset time period ahead;

The continuous evaluation index includes the first overdue rate, the first six overdue rates, the first 12 overdue rates, the current 90+ overdue rate, the post-loan fraud rate and the loan rejection rate, and the discrete evaluation index includes the institutional blacklist and business status.

Optionally, according to the continuous evaluation index threshold and the discrete evaluation index threshold, determine the abnormal number of evaluation indicators at each time point in the first preset time period, specifically:

Arranging the continuous evaluation index and the discrete evaluation index in chronological order to obtain each evaluation index set rolling within the first preset time period;

If it is detected that the continuous evaluation index is greater than the threshold of the continuous evaluation index at the second time point, the credit institution is abnormal at the second time point and determines the number of abnormal evaluation indicators;

If it is detected that the discrete evaluation index is greater than the discrete evaluation index threshold at the third time point, the credit institution is abnormal at the third time point and determines the number of abnormal evaluation indexes;

The time series of the abnormal number of evaluation indicators is formed according to the abnormal number of evaluation indicators at each time point in the first preset time period.

Optionally, the method further includes:

If it is detected that the continuous evaluation index is smaller than the threshold of the continuous evaluation index at the second time point, the credit institution's evaluation index is normal at the second time point;

If it is detected that the discrete evaluation index is smaller than the discrete evaluation index threshold at the third time point, the credit institution's evaluation index is normal at the third time point.

Optionally, the method further includes:

When it is detected that the abnormal number of the evaluation index at the first time point is less than a preset threshold, the credit institution is marked as a good sample.

Optionally, a management model is constructed after the risk level of the credit institution is defined according to the marking result.

Correspondingly, the present invention also discloses a credit institution marking device, the device comprising:

The building module is used to construct an evaluation index system according to the operation status information of the credit institution, and the evaluation index includes a continuous evaluation index and a discrete evaluation index;

a judgment module, configured to judge the abnormal number of evaluation indexes at each time point within the first preset time period according to the continuous evaluation index threshold and the discrete evaluation index threshold;

The sample marking module is configured to use the first time point as the dividing line to conduct a second preset time period ahead of the credit institution sample abnormality when it is detected that the number of abnormal evaluation indicators at the first time point is greater than the preset threshold Marking;

The continuous evaluation index includes the first overdue rate, the first six overdue rates, the first 12 overdue rates, the current 90+ overdue rate, the post-loan fraud rate and the loan rejection rate, and the discrete evaluation index includes the institutional blacklist and business status.

Optionally, the judging module is specifically used for:

Arranging the continuous evaluation index and the discrete evaluation index in chronological order to obtain each evaluation index set rolling within the first preset time period;

If it is detected that the continuous evaluation index is greater than the threshold of the continuous evaluation index at the second time point, the credit institution is abnormal at the second time point and determines the number of abnormal evaluation indicators;

If it is detected that the discrete evaluation index is greater than the discrete evaluation index threshold at the third time point, the credit institution is abnormal at the third time point and determines the number of abnormal evaluation indexes;

The time series of the abnormal number of evaluation indicators is formed according to the abnormal number of evaluation indicators at each time point in the first preset time period.

Optionally, the device further includes:

a first detection module, configured to detect that the evaluation index of the credit institution is normal at the second time point if it is detected that the continuous evaluation index is smaller than the threshold of the continuous evaluation index at the second time point;

The second detection module is configured to, if it is detected that the discrete evaluation index is smaller than the discrete evaluation index threshold at the third time point, the credit institution's evaluation index at the third time point is normal.

In order to achieve the above object, according to another aspect of the present application, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program while implementing the steps of the method as described.

In order to achieve the above object, according to yet another aspect of the present application, a computer-readable storage medium is provided, a computer program is stored thereon, and the computer program implements the steps of the method when executed by a processor.

Compared with the prior art, the present invention has the following beneficial effects:

The invention discloses a marking method for a credit institution. The method includes: constructing an evaluation index system according to the operation state information of the credit institution, the evaluation index includes a continuous evaluation index and a discrete evaluation index; The number of abnormal evaluation indicators at each time point in the first preset time period is determined by the threshold value of the evaluation index; when it is detected that the abnormal number of evaluation indicators at the first time point is greater than the preset threshold, the first time point is used as the dividing line to move forward The second preset time period is used to mark abnormal credit institution samples; wherein, the continuous evaluation indicators include the first overdue rate, the first six overdue rates, the first 12 overdue rates, the current 90+ overdue rate, the post-loan fraud rate and Loan rejection rate, the discrete evaluation indicators include institutional blacklist and business operation status. Through the above method, the state of the credit institution can be measured from multiple angles, and the abnormal time of the credit institution can be detected in time and an effective warning can be given.

Description of drawings

The accompanying drawings, which constitute a part of this application, are used to provide a further understanding of the application and make other features, objects and advantages of the application more apparent. The accompanying drawings and descriptions of the exemplary embodiments of the present application are used to explain the present application, and do not constitute an improper limitation of the present application. In the attached image:

1 is a schematic flowchart of a method for marking a credit institution according to an embodiment of the present application;

2 is a schematic flowchart of another credit institution marking method according to an embodiment of the present application;

3 is a schematic structural diagram of a credit institution marking device according to an embodiment of the present application;

Detailed ways

In order to make those skilled in the art better understand the solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only The embodiments are part of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the scope of protection of the present application.

It should be noted that the embodiments in the present application and the features of the embodiments may be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general-purpose computing device, and they can be centralized on a single computing device or distributed in a network composed of multiple computing devices Alternatively, they can be implemented with program codes executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or they can be integrated into The multiple modules or steps are fabricated into a single integrated circuit module. As such, the present invention is not limited to any particular combination of hardware and software.

As shown in FIG. 1, a schematic flowchart of a credit institution marking method proposed by an embodiment of the present invention includes:

S201 , constructing an evaluation index system according to the operation state information of the credit institution, where the evaluation index includes a continuous evaluation index and a discrete evaluation index.

Specifically, the operation state information of the credit institution is obtained, and an evaluation index system is constructed according to the operation state information, and the evaluation index includes a continuous evaluation index and a discrete evaluation index. Among them, the continuous evaluation indicators include the first overdue rate, the overdue rate of the first 6 periods, the overdue rate of the first 12 periods, the current overdue rate of 90+, the post-loan fraud rate and the loan rejection rate. First overdue rate: The number of accounts/loans that are overdue for 15 days+ in the first installment of the institution's existing loans. Overdue rate for the first 6 phases: the number of accounts/loans that are overdue for 30 days + in the first 6 phases of the institution's existing loans. Overdue rate in the first 12 periods: the number of accounts/loans that are overdue for 30 days + in the first 12 periods of the institution's stock loans. Current 90+ overdue rate: The institution's stock loan retrospective node is overdue for 90 days + the number of accounts/number of loans in progress. Post-loan fraud rate: The number of post-loan fraud/loan loans in the institution's stock loan. Loan rejection rate: The number of accounts rejected by the institution/the number of accounts applied for. The discrete evaluation indicators include a total of 2 items: institutional blacklist and enterprise operating status. Institutional blacklist is aimed at enterprises, companies and other entities participating in credit business, such as guarantee companies, financial company branches, cooperative merchants, drainage channels, etc. Institutional blacklist generally refers to the list of institutions that have been confirmed to be involved in fraud. If the institution is blacklisted this month, it is recorded as "bad", otherwise it is recorded as "good".

S202 , according to the continuous evaluation index threshold and the discrete evaluation index threshold, determine the abnormal number of evaluation indexes at each time point within the first preset time period.

Specifically, according to the distribution of various continuous indicators of the institution, combined with expert experience, the thresholds of various continuous evaluation indicators are determined. When the indicators exceed the threshold, it means that the institution is abnormal. According to expert experience, determining the value of each discrete evaluation index indicates that there is an abnormality in the institution. According to the continuous evaluation index threshold value and the discrete evaluation index threshold value, the abnormal number of the evaluation index at each time point in the first preset time period is determined.

In order to accurately determine the abnormal number of evaluation indicators at each time point, in some embodiments, the abnormal number of evaluation indicators at each time point within the first preset time period is determined according to the continuous evaluation index threshold and the discrete evaluation index threshold, specifically: :

Arranging the continuous evaluation index and the discrete evaluation index in chronological order to obtain each evaluation index set rolling within the first preset time period;

If it is detected that the continuous evaluation index is greater than the threshold of the continuous evaluation index at the second time point, the credit institution is abnormal at the second time point and determines the number of abnormal evaluation indicators;

If it is detected that the discrete evaluation index is greater than the discrete evaluation index threshold at the third time point, the credit institution is abnormal at the third time point and determines the number of abnormal evaluation indexes;

The time series of the abnormal number of evaluation indicators is formed according to the abnormal number of evaluation indicators at each time point in the first preset time period.

Specifically, the second time point and the third time point defined in this application are both a random moment within the first preset time period. Taking a credit institution as an example, the continuous evaluation index and the discrete evaluation index are arranged in time sequence, so that each evaluation index set rolling in the first preset time period is obtained. For the continuous evaluation index, if it is detected that the continuous evaluation index is greater than the threshold of the continuous evaluation index at the second time point, the credit institution is abnormal at the second time point and determines the number of abnormal evaluation indicators. If it is detected that the discrete evaluation index is greater than the discrete evaluation index threshold at the third time point, the credit institution is abnormal at the third time point and determines the number of abnormal evaluation indexes. In this way, the abnormal number of each evaluation index at each time point in the first preset time period can be obtained, and then the time series of the abnormal number of evaluation indicators of the credit institution can be formed. Through the above method, it is possible to clearly find out the institution from normal to abnormal. changing trend. Find out the abnormal time of the institution in time.

In order to accurately determine the abnormal number of evaluation indicators at each time point, in some embodiments, it also includes:

If it is detected that the continuous evaluation index is smaller than the threshold of the continuous evaluation index at the second time point, the credit institution's evaluation index is normal at the second time point;

If it is detected that the discrete evaluation index is smaller than the discrete evaluation index threshold at the third time point, the credit institution's evaluation index is normal at the third time point.

Specifically, if it is detected that the continuous evaluation index is less than the threshold of the continuous evaluation index at the second time point within the first preset time, the credit institution's evaluation index is normal at the second time point; When the discrete evaluation index is smaller than the discrete evaluation index threshold at a third time point within the first preset time, the credit institution's evaluation index is normal at the third time point. This application can measure the state of the institution from multiple angles through a number of evaluation indicators, and discover the time when the institution is abnormal in time.

S203 , when it is detected that the abnormal number of the evaluation index is greater than a preset threshold at the first time point, use the first time point as the dividing line to mark the abnormality of the credit institution sample by a second preset time period.

Specifically, the first time point defined in this application is a random moment within the first preset time period. The preset threshold is determined based on the distribution of abnormal quantities of all historical data evaluation indicators of the credit institution in the past and the proportion of bad samples after marking, combined with expert experience. When it is detected that the abnormal number of the evaluation indicators at the first time point within the first preset time period is greater than the preset threshold, take the first time point as the dividing line and proceed to the second preset time period to conduct a sample of the credit institution Abnormal marking. For example: when the number of abnormal evaluation indicators is greater than the preset threshold, it means that the institution has abnormality at this time point, then the samples within a fixed period of time (such as 3 months, 6 months, etc.) before this time point are marked as Bad samples, the samples in the rest of the time period are marked as good samples. Because samples before anomalies are marked, it is helpful for institutional early warning of downstream tasks.

To mark a good sample of the credit institution, in some embodiments, it also includes:

When it is detected that the abnormal number of the evaluation index at the first time point is less than a preset threshold, the credit institution is marked as a good sample.

In order to construct the management model based on the marking result, in some embodiments, the management model is constructed after the risk level of the credit institution is defined according to the marking result.

Specifically, based on the marking results of this method, the risk level of offline institutions mainly engaged in credit business is defined, and then a management model is constructed to replace the traditional empirical model. Through retrospective processing of historical samples of credit institutions, the target variables that can be constructed based on this marking method can be used in statistical models or machine learning models. This application provides a relatively general method for marking credit institution management models, which has certain universality.

In order to further illustrate the technical idea of the present invention, the technical solutions of the present invention are now described with reference to specific application scenarios.

FIG. 2 is a schematic flowchart of another credit institution marking method according to an embodiment of the present application,

Step 1: Build an evaluation index system.

Specifically, the operation state information of the credit institution is obtained, and an evaluation index system is constructed according to the operation state information, and the evaluation index includes a continuous evaluation index and a discrete evaluation index. Among them, the continuous evaluation indicators include the first overdue rate, the overdue rate of the first 6 periods, the overdue rate of the first 12 periods, the current overdue rate of 90+, the post-loan fraud rate and the loan rejection rate. First overdue rate: The number of accounts/loans that are overdue for 15 days+ in the first installment of the institution's existing loans. Overdue rate for the first 6 phases: the number of accounts/loans that are overdue for 30 days + in the first 6 phases of the institution's existing loans. Overdue rate in the first 12 periods: the number of accounts/loans that are overdue for 30 days + in the first 12 periods of the institution's stock loans. Current 90+ overdue rate: The institution's stock loan retrospective node is overdue for 90 days + the number of accounts/number of loans in progress. Post-loan fraud rate: The number of post-loan fraud/loan loans in the institution's stock loan. Loan rejection rate: The number of accounts rejected by the institution/the number of accounts applied for. The discrete evaluation indicators include a total of 2 items: institutional blacklist and enterprise operating status. Institutional blacklist is aimed at enterprises, companies and other entities participating in credit business, such as guarantee companies, financial company branches, cooperative merchants, drainage channels, etc. Institutional blacklist generally refers to the list of institutions that have been confirmed to be involved in fraud. If the institution is blacklisted this month, it is recorded as "bad", otherwise it is recorded as "good".

Step 2: Determine the parameters required for the marking method.

Specifically, according to the distribution of various continuous indicators of the institution, combined with expert experience, the thresholds of various continuous evaluation indicators are determined. When the indicators exceed the threshold, it means that the institution is abnormal. According to expert experience, determining the value of each discrete evaluation index indicates that there is an abnormality in the institution. According to the continuous evaluation index threshold value and the discrete evaluation index threshold value, the abnormal number of the evaluation index at each time point in the first preset time period is determined.

Step 3: Construct the time series of the abnormal number of evaluation indicators.

Specifically, the continuous evaluation index and the discrete evaluation index are arranged in the order of time, so that each evaluation index set rolled in the first preset time period is obtained. For the continuous evaluation index, if it is detected that the continuous evaluation index is greater than the threshold of the continuous evaluation index at the second time point, the credit institution is abnormal at the second time point and determines the number of abnormal evaluation indicators. If it is detected that the discrete evaluation index is greater than the discrete evaluation index threshold at the third time point, the credit institution is abnormal at the third time point and determines the number of abnormal evaluation indexes. In this way, the abnormal number of each evaluation index at each time point in the first preset time period can be obtained, and then the time series of the abnormal number of evaluation indicators of the credit institution can be formed. Through the above method, it is possible to clearly find out the institution from normal to abnormal. changing trend. Find out the abnormal time of the institution in time.

Step 4: Institutional abnormal marking.

When it is detected that the abnormal number of the evaluation indicators at the first time point within the first preset time period is greater than the preset threshold, take the first time point as the dividing line and proceed to the second preset time period to conduct a sample of the credit institution Abnormal marking. For example: when the number of abnormal evaluation indicators is greater than the preset threshold, it means that the institution has abnormality at this time point, then the samples within a fixed period of time (such as 3 months, 6 months, etc.) before this time point are marked as Bad samples, the samples in the rest of the time period are marked as good samples. Because samples before anomalies are marked, it is helpful for institutional early warning of downstream tasks. Based on the marking results of this method, the risk level of offline institutions mainly engaged in credit business is defined. Through a number of evaluation indicators, the state of the organization can be measured from multiple angles, and the abnormal time of the organization can be detected in time. It provides a more general method for credit institution management model marking, which has certain universality.

In order to achieve the above technical purpose, an embodiment of the present application also proposes a credit institution marking device, as shown in FIG. 3 , the device includes:

The construction module 401 is used for constructing an evaluation index system according to the operation status information of the credit institution, and the evaluation index includes a continuous evaluation index and a discrete evaluation index;

The judgment module 402 is used for judging the abnormal quantity of the evaluation index at each time point within the first preset time period according to the continuous evaluation index threshold value and the discrete evaluation index threshold value;

The sample marking module 403 is configured to use the first time point as a dividing line to carry out a credit institution sample for a second preset time period when it is detected that the number of abnormal evaluation indicators at the first time point is greater than a preset threshold abnormal marking;

The continuous evaluation index includes the first overdue rate, the first six overdue rates, the first 12 overdue rates, the current 90+ overdue rate, the post-loan fraud rate and the loan rejection rate, and the discrete evaluation index includes the institutional blacklist and business status.

In the specific application scenario of the present application, the judgment module is specifically used for:

Arranging the continuous evaluation index and the discrete evaluation index in chronological order to obtain each evaluation index set rolling within the first preset time period;

If it is detected that the continuous evaluation index is greater than the threshold of the continuous evaluation index at the second time point, the credit institution is abnormal at the second time point and determines the number of abnormal evaluation indicators;

If it is detected that the discrete evaluation index is greater than the discrete evaluation index threshold at the third time point, the credit institution is abnormal at the third time point and determines the number of abnormal evaluation indexes;

The time series of the abnormal number of evaluation indicators is formed according to the abnormal number of evaluation indicators at each time point in the first preset time period.

In the specific application scenario of the present application, the device further includes:

a first detection module, configured to detect that the evaluation index of the credit institution is normal at the second time point if it is detected that the continuous evaluation index is smaller than the threshold of the continuous evaluation index at the second time point;

The second detection module is configured to, if it is detected that the discrete evaluation index is smaller than the discrete evaluation index threshold at the third time point, the credit institution's evaluation index at the third time point is normal.

The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method when executing the computer program.

The present application also provides a computer-readable storage medium in which a computer program is stored, and the computer program implements the above method when executed by a processor.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

The above descriptions are only preferred embodiments of the present application, and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims (10)

1. A credit agency marking method, the method comprising:

establishing an evaluation index system according to the operation state information of the credit agency, wherein the evaluation indexes comprise continuous evaluation indexes and discrete evaluation indexes;

judging the abnormal quantity of the evaluation indexes at each time point in a first preset time period according to the continuous evaluation index threshold and the discrete evaluation index threshold;

when the evaluation index abnormal quantity is larger than a preset threshold value at a first time point, performing credit agency sample abnormal marking by taking the first time point as a boundary in a second preset time period;

the continuous evaluation indexes comprise first-out rate, first-6-out rate, first-12-out rate, current 90+ out rate, post-loan fraud rate and refusal rate, and the discrete evaluation indexes comprise organization blacklists and enterprise operation states.

2. The method according to claim 1, wherein the determining the abnormal number of the evaluation indexes at each time point in the first preset time period according to the continuous evaluation index threshold and the discrete evaluation index threshold specifically comprises:

arranging the continuous evaluation indexes and the discrete evaluation indexes according to a time sequence to obtain each evaluation index set rolling in the first preset time period;

if the continuous evaluation index is detected to be larger than the continuous evaluation index threshold value at a second time point, the credit agency is abnormal at the second time point and determines the abnormal number of the evaluation indexes;

if the discrete evaluation index is detected to be larger than the discrete evaluation index threshold value at a third time point, the credit agency is abnormal at the third time point and determines the abnormal number of the evaluation indexes;

and forming a time sequence of the abnormal quantity of the evaluation indexes according to the abnormal quantity of each evaluation index at each time point in the first preset time period.

3. The method of claim 2, further comprising:

if the continuous evaluation index is smaller than the continuous evaluation index threshold value at a second time point, the credit agency evaluates the index normally at the second time point;

and if the fact that the discrete evaluation index is smaller than the discrete evaluation index threshold value at the third time point is detected, the credit agency evaluates the index normally at the third time point.

4. The method of claim 1, further comprising:

and marking good samples for the credit agency when the evaluation index abnormal quantity is smaller than a preset threshold value at the first time point.

5. The method of claim 4 wherein the management model is constructed after the credit agency's risk level is defined based on the marking results.

6. A credit agency marking device, the device comprising:

the credit organization evaluation system comprises a construction module, a verification module and a verification module, wherein the construction module is used for constructing an evaluation index system according to the operation state information of a credit organization, and the evaluation indexes comprise continuous evaluation indexes and discrete evaluation indexes;

the judging module is used for judging the abnormal quantity of the evaluation indexes at each time point in a first preset time period according to the continuous evaluation index threshold and the discrete evaluation index threshold;

the sample marking module is used for marking the credit agency sample abnormity in a second preset time period before the first time point is used as a boundary when the evaluation index abnormity number is detected to be larger than a preset threshold value at the first time point;

the continuous evaluation indexes comprise first-out rate, first-6-out rate, first-12-out rate, current 90+ out rate, post-loan fraud rate and refusal rate, and the discrete evaluation indexes comprise organization blacklists and enterprise operation states.

7. The apparatus of claim 6, wherein the determining module is specifically configured to:

arranging the continuous evaluation indexes and the discrete evaluation indexes according to a time sequence to obtain each evaluation index set rolling in the first preset time period;

if the continuous evaluation index is detected to be larger than the continuous evaluation index threshold value at a second time point, the credit agency is abnormal at the second time point and determines the abnormal number of the evaluation indexes;

if the discrete evaluation index is detected to be larger than the discrete evaluation index threshold value at a third time point, the credit agency is abnormal at the third time point and determines the abnormal number of the evaluation indexes;

and forming a time sequence of the abnormal quantity of the evaluation indexes according to the abnormal quantity of each evaluation index at each time point in the first preset time period.

8. The apparatus of claim 7, further comprising:

the credit agency is used for evaluating the continuous evaluation index at a first time point;

and the credit agency is used for evaluating the index at the third time point normally if the fact that the discrete evaluation index is smaller than the discrete evaluation index threshold value at the third time point is detected.

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 5 are implemented by the processor when executing the computer program.

10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.

Images