A sandbox-based risk control assessment method, system, terminal and storage medium

Abstract

The application provides a sandbox-based risk control evaluation method, system, terminal and storage medium, the method comprises the following steps: obtaining the credit application information of a user; in a sandbox environment, according to the credit application information and a preset access sequence, sequentially accessing a plurality of external data sources, and obtaining the simulation data output by the external data sources according to the historical query data and the credit application information stored by the external data sources after accepting the access, and according to the simulation data, performing a running test on an online configured risk control model, and judging whether the risk control model is normally running, if not, adjusting the preset access sequence, then returning to execute the step of obtaining the simulation data again, if yes, in an online environment, using the risk control model to analyze and process the real data returned by each external data source, and outputting a risk control evaluation result. The application can perform a running test on an online configured risk control model under the premise of meeting compliance requirements, and reduce the operation amount of the operator.

Description

Technical Field

[0001] This application relates to the field of risk assessment technology, and in particular to a sandbox-based risk control assessment method, system, terminal, and storage medium. Background Technology

[0002] Risk control is the core and key to consumer credit business. It uses big data analysis and artificial intelligence technology to conduct credit assessment of borrowers, thereby achieving accurate identification of borrowers' qualifications and controlling the risk of loan projects based on the assessment results. The traditional risk control assessment method is to pre-configure the risk control model, and then conduct credit assessment of users based on third-party data sources and external system data after users apply for credit. The traditional solution has the following problems: (1) Business personnel need to configure a lot of internal and external data sources. With frequent changes and additions to the model, there will be omissions or errors in configuration, resulting in abnormal credit granting. (2) If the risk control model configured online is to be tested, it is necessary to use real customer information to query the third-party data source and save it in the database, which does not meet the compliance requirements and will increase the query cost. (3) Since the risk control model is used directly online, the actual use effect is unknown, which means that it needs to be repeatedly verified and modified after configuration, increasing the workload of operators.

[0003] Therefore, how to conduct operational tests on online risk control models while meeting compliance requirements and reducing the workload of operators is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] To address the aforementioned technical issues, this application provides a sandbox-based risk control assessment method, which enables the online configuration of risk control models to be tested while meeting compliance requirements, and reduces the workload of operators. This application also provides a sandbox-based risk control assessment system, terminal, and storage medium, achieving the same technical effects.

[0005] The first objective of this application is to provide a sandbox-based risk assessment method.

[0006] The aforementioned objective of this application is achieved through the following technical solution:

[0007] A sandbox-based risk assessment method includes:

[0008] Obtain the user's credit application information;

[0009] In the sandbox environment, based on the credit application information and the preset access order, multiple external data sources are accessed sequentially, and the simulated data output by the external data sources after the access is accepted, based on their stored historical query data and the credit application information, is obtained.

[0010] In the sandbox environment, the online configured risk control model is tested based on the simulated data output by each external data source, and it is determined whether the risk control model is operating normally. If not, the preset access order is adjusted, and then the process is repeated: in the sandbox environment, multiple external data sources are accessed sequentially according to the credit application information and the preset access order, and the simulated data output by each external data source after accepting access is obtained based on its stored historical query data and the credit application information. If yes, then:

[0011] In an online environment, multiple external data sources are accessed sequentially according to the credit application information and the preset access order, and the actual data returned by the external data sources after the access is accepted according to the credit application information is obtained.

[0012] In an online environment, the risk control model is used to analyze and process the real data returned by each external data source, and output the risk control assessment results.

[0013] Preferably, in the sandbox-based risk control assessment method, obtaining the simulated data output by the external data source after access is granted, based on its stored historical query data and the credit application information, includes:

[0014] After the external data source is granted access, the first data is obtained from the historical query data stored in the external data source itself, based on the credit application information.

[0015] Determine whether the first data has a median. If it does, obtain the median of the first data and use it as the simulated data output by the external data source. If not, directly obtain the first data and use it as the simulated data output by the external data source.

[0016] Preferably, in the sandbox-based risk control assessment method, the external data source includes a first data source for providing user loan information, a second data source for providing user social security information, and a third data source for providing user fraud risk information.

[0017] Preferably, in the sandbox-based risk control assessment method, adjusting the preset access order includes:

[0018] The preset access order is adjusted using a preset adaptive algorithm.

[0019] Preferably, in the sandbox-based risk control assessment method, the credit application information includes one or more of the user's name, telephone number, ID card number, and facial information.

[0020] Preferably, in the sandbox-based risk control assessment method, the sandbox environment is configured with a code signing-based security mechanism.

[0021] The second objective of this application is to provide a sandbox-based risk assessment system.

[0022] The second objective of this application is achieved through the following technical solution:

[0023] A sandbox-based risk assessment system includes:

[0024] The acquisition unit is used to acquire the user's credit application information;

[0025] The first access unit is used to access multiple external data sources sequentially in a sandbox environment according to the credit application information and a preset access order, and to obtain the simulated data output by the external data sources after accepting the access based on their stored historical query data and the credit application information.

[0026] The running unit is used to run the online configured risk control model in a sandbox environment based on the simulated data output by each of the external data sources, and to determine whether the risk control model is running normally.

[0027] The first access unit is also used to adjust the preset access order in a sandbox environment when the risk control model is not running normally;

[0028] The second access unit is used to access multiple external data sources sequentially in an online environment according to the credit application information and the preset access order when the risk control model is running normally, and to obtain the real data returned by the external data sources according to the credit application information after the access is accepted.

[0029] The analysis unit is used in an online environment to analyze and process the real data returned by each of the external data sources using the risk control model, and output the risk control assessment results.

[0030] Preferably, in the sandbox-based risk control assessment system, the first access unit, when executing the step of obtaining the simulated data output by the external data source after accepting access, based on its stored historical query data and the credit application information, is specifically used for:

[0031] After the external data source is granted access, the first data is obtained from the historical query data stored in the external data source itself, based on the credit application information.

[0032] Determine whether the first data has a median. If it does, obtain the median of the first data and use it as the simulated data output by the external data source. If not, directly obtain the first data and use it as the simulated data output by the external data source.

[0033] The third objective of this application is to provide a sandbox-based risk assessment terminal.

[0034] The aforementioned objective three of this application is achieved through the following technical solution:

[0035] A sandbox-based risk assessment terminal includes: a storage medium and a processor;

[0036] The storage medium stores computer-executed instructions.

[0037] The processor executes computer execution instructions stored in the storage medium to implement any of the methods described in the sandbox-based risk control assessment methods above.

[0038] The fourth objective of this application is to provide a computer-readable storage medium.

[0039] The fourth objective of this application is achieved through the following technical solution:

[0040] A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement any of the methods described above in the sandbox-based risk control assessment method.

[0041] The above technical solution obtains the user's credit application information; in a sandbox environment, it sequentially accesses multiple external data sources according to the credit application information and a preset access order, and obtains simulated data output by the external data sources after accepting the access, based on their stored historical query data and credit application information; in the sandbox environment, it runs and tests the online configured risk control model based on the simulated data output by each external data source, and determines whether the risk control model is operating normally. The simulated data is generated based on historical query data from the external data sources. Running and testing the risk control model in the sandbox environment based on the simulated data effectively isolates the online code and effectively avoids compliance risks; when the risk control model does not operate normally, it runs and tests the preset access order in the sandbox environment. The process involves adjusting the access order and then re-executing the steps based on the credit application information and the preset access order. This involves sequentially accessing multiple external data sources and obtaining simulated data output by each external data source based on its stored historical query data and the credit application information. This automatically adjusts the preset access order, reducing the workload of repeated verification by operators. When the risk control model is running normally, in the online environment, multiple external data sources are accessed sequentially based on the credit application information and the preset access order. The actual data returned by each external data source after receiving the access is obtained. Using the risk control model running in the online environment, the actual data returned by each external data source is analyzed and processed to output a risk control assessment result, thus completing the credit approval process. In summary, the above technical solution can run and test the online configured risk control model while meeting compliance requirements and reducing the workload of operators. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating a sandbox-based risk control assessment method provided in an embodiment of this application.

[0044] Figure 2 This is a schematic diagram of the structure of a sandbox-based risk control assessment system provided in the embodiments of this application;

[0045] Figure 3 This is a structural schematic diagram of a sandbox-based risk control assessment terminal provided in the embodiments of this application. Detailed Implementation

[0046] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0047] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, and can be electrical, mechanical, or other forms.

[0048] It should be understood that the use of terms such as "system," "device," "unit," and / or "module" in this application is merely one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0049] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "a plurality of" or "several" means two or more, unless otherwise explicitly specified.

[0050] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0051] It should also be noted that, in this document, terms such as “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes the aforementioned element.

[0052] The embodiments in this application are written in a progressive manner.

[0053] like Figure 1 As shown in the embodiment of this application, a sandbox-based risk control assessment method is provided, including:

[0054] S101. Obtain the user's credit application information;

[0055] In S101, specifically, after a user initiates a credit application through a front-end WeChat official account or APP, the user's credit application information can be obtained in the corresponding system. The credit application information includes basic information required for analyzing the user's credit status. The specific method of obtaining the information does not affect the implementation of this embodiment. In some embodiments, the credit application information may include one or more of the user's name, telephone number, ID card, and facial information. This application does not impose any restrictions on this.

[0056] S102. In the sandbox environment, according to the credit application information and the preset access order, multiple external data sources are accessed sequentially, and the simulated data output by the external data sources after the access is accepted, based on their stored historical query data and credit application information;

[0057] In S102, specifically, the sandbox environment refers to a joint debugging and testing environment that is completely isolated from the production environment. Interface calls made by developers in the sandbox environment will not affect data in the production environment. In this embodiment, the sandbox environment is used to confine code to a specific scope within a virtual machine and strictly restrict access to local system resources. This ensures effective isolation of online code, prevents online simulations from altering the database, and addresses the problem of online-configured risk control models and rules being unable to be simulated for testing.

[0058] Specifically, external data sources can be existing credit reporting platform data sources or financial platform data sources. After obtaining the user's credit application information, multiple external data sources can be accessed sequentially in a sandbox environment according to the credit application information, a preset access order, and preset external data source addresses. This allows the acquisition of simulated data output by the external data sources based on their stored historical query data and credit application information. The historical query data can be data stored in the external data sources representing past queries by real customers. For example, historical query data can include past customer loan and repayment records, past customer borrowing behavior preferences, and past customer fraud risk data. The simulated data is used for subsequent risk control model operation testing. It is generated based on the historical query data in the external data sources, thereby avoiding erroneous operations such as multiple queries to customers and effectively mitigating compliance risks.

[0059] In some embodiments, one implementation of the step of obtaining simulated data output by an external data source after access is granted, based on its stored historical query data and credit application information, includes:

[0060] S201. After the external data source is accessed, the first data is obtained from the historical query data stored in the external data source itself, based on the credit application information;

[0061] Specifically, in S201, after the external data source is accessed, the first data required for the risk control model operation test can be selected from the historical query data stored in the external data source based on the credit application information. For example, when it is necessary to obtain loan information for risk control model operation test, the borrowing and repayment records of past customers can be selected from the historical query data of the external data source as the first data; when it is necessary to obtain fraud risk information for risk control model operation test, the fraud risk data of past customers can be selected from the historical query data of the external data source as the first data.

[0062] S202. Determine whether the first data has a median. If it does, obtain the median of the first data and use it as the simulated data output by the external data source. If not, directly obtain the first data and use it as the simulated data output by the external data source.

[0063] Specifically, in S202, it can be determined whether the first data has a median based on its data type. If the first data has a median, it can be used as the simulated data output by the external data source. For example, if the first data is the loan and repayment records of past customers, and the past customers have borrowed 100 times with loan amounts ranging from 100 yuan to 200,000 yuan, the median of the past 100 loan amounts can be taken to simulate the amount of the current loan, thus obtaining the simulated data returned in this query. Using the median for simulation is more representative. In a set of data, if there are extremely large or small values, the median is not affected by extreme values ​​and can better reflect the central position of the data. On the other hand, if there are outliers or irregularities in the data, the median also has better stability. If the first data does not have a median, it can be directly used as the simulated data output by the external data source.

[0064] In other embodiments, the external data source includes a first data source for providing user lending information, such as the People's Bank of China credit data source or Baihang credit data source; a second data source for providing user social security information, such as the Pudao credit data source; and a third data source for providing user fraud risk information, such as the internet finance platform data source. This application does not limit the scope of the data source.

[0065] In other embodiments, the sandbox environment is configured with a code signing-based security mechanism. Code signing involves digitally signing executable files or scripts to verify the software author and ensure that the software has not been modified or corrupted after signing. Specifically, by deploying application services on a server and configuring the aforementioned security mechanism, when other applications attempt to obtain the digital signature of an application in the sandbox, they must use a signing key from a pre-stored keystore to verify the digital signature. Only after successful signing can the application service continue execution, thereby enhancing the security of the sandbox operation.

[0066] S103. In the sandbox environment, based on the simulated data output by each external data source, run the risk control model configured online and determine whether the risk control model is running normally. If not, execute S104; if yes, execute S105.

[0067] In S103, specifically, the risk control model configured online can be run in a sandbox environment, and simulated data can be used as input for the risk control model to test its operation. If the risk control model completes all nodes normally in the sandbox environment and can determine whether the customer meets the credit conditions through the configured simulated data, it can be considered that the risk control model is configured and running normally, and then the subsequent online environment risk control assessment can be carried out, i.e., S105 is executed; otherwise, S104 is executed.

[0068] S104. In the sandbox environment, adjust the preset access order, and then return to re-execute S102;

[0069] In S104, specifically, due to the dependencies between different data sources during the risk control assessment process, if the data source access order is configured incorrectly, the risk control model may not be able to complete all nodes normally. In this step, when the risk control model cannot run normally, the preset access order is automatically adjusted, and S102 is re-executed to re-acquire simulation data and continue sandbox environment operation testing. At this time, the simulation data returned is not stored in the database, so multiple repeated runs have no impact. In some embodiments, one implementation of the step of adjusting the preset access order includes: using a preset adaptive algorithm to adjust the preset access order. Based on the preset adaptive algorithm, the preset access order can be automatically configured to adjust the access order of multiple external data sources and can reduce the amount of repeated verification operations by operators.

[0070] S105. In an online environment, based on the credit application information and the preset access order, access multiple external data sources sequentially, and obtain the actual data returned by the external data sources based on the credit application information after the access is accepted;

[0071] Specifically, in S105, when the risk control model is functioning correctly, in the online environment, based on the credit application information, a preset access order, and preset external data source addresses, multiple external data sources are accessed sequentially. The actual data returned by these external data sources after receiving the access is obtained, based on the credit application information. This actual data can be data stored in the external data sources required for analyzing the creditworthiness of the current credit applicant. For example, actual data may include the current credit applicant's loan repayment records, borrowing behavior preferences, fraud risk data, employment, social security, and housing provident fund data. In the online environment, the obtained actual data can be stored in a local database.

[0072] S106. In an online environment, using a risk control model, analyze and process the real data returned by each external data source, and output risk control assessment results.

[0073] Specifically, in S106, a risk control model running in an online environment is used to perform credit analysis and matching on the obtained real data according to the credit granting rules, calculate the user's credit limit, and output the risk control assessment result to complete the credit granting.

[0074] Traditional risk control assessment methods involve pre-configuring a risk control model, then having the user apply for credit, and conducting a credit assessment based on third-party data sources and external system data. The traditional approach has the following problems: (1) Business personnel need to configure numerous internal and external data sources. Frequent model changes and additions can lead to omissions or errors in configuration, resulting in credit approval anomalies. (2) Testing online risk control models requires querying and storing real customer information in the database, which does not meet compliance requirements and increases query costs. (3) Since the risk control model is used directly online, its actual effectiveness is unknown, requiring repeated verification and modification after configuration, increasing the workload for operators.

[0075] The above embodiments involve obtaining user credit application information; in a sandbox environment, accessing multiple external data sources sequentially according to the credit application information and a preset access order, and obtaining simulated data output by the external data sources based on their stored historical query data and credit application information after receiving access; in the sandbox environment, running tests are conducted on the online configured risk control model based on the simulated data output by each external data source, and it is determined whether the risk control model is operating normally. The simulated data is generated based on historical query data from the external data sources. Running tests on the risk control model running in the sandbox environment based on the simulated data can effectively isolate online code and effectively avoid compliance risks. When the risk control model does not operate normally, the preset access... The process involves adjusting the access order and then re-executing the steps based on the credit application information and the preset access order. This includes accessing multiple external data sources sequentially and obtaining simulated data output by each external data source based on its stored historical query data and the credit application information. This automatically adjusts the preset access order, reducing the workload of repeated verification by operators. When the risk control model is running normally, in the online environment, multiple external data sources are accessed sequentially according to the credit application information and the preset access order. The actual data returned by each external data source after receiving the access is obtained. Using the risk control model running in the online environment, the actual data returned by each external data source is analyzed and processed to output a risk control assessment result, thus completing the credit granting process. In summary, the above embodiment can test the online configured risk control model while meeting compliance requirements and reducing the workload of operators.

[0076] like Figure 2 As shown, in another embodiment of this application, a sandbox-based risk control assessment system is also provided, comprising:

[0077] Unit 10 is used to obtain the user's credit application information;

[0078] The first access unit 11 is used to access multiple external data sources sequentially in a sandbox environment according to the credit application information and the preset access order, and to obtain the simulated data output by the external data sources after accepting the access based on their stored historical query data and credit application information.

[0079] The running unit 12 is used to run the online configured risk control model in a sandbox environment based on the simulated data output by each external data source, and to determine whether the risk control model is running normally.

[0080] The first access unit 11 is also used to adjust the preset access order in the sandbox environment when the risk control model is not running normally;

[0081] The second access unit 13 is used to access multiple external data sources sequentially in an online environment according to the credit application information and the preset access order when the risk control model is running normally, and to obtain the real data returned by the external data sources according to the credit application information after the access is accepted.

[0082] Analysis unit 14 is used in an online environment to analyze and process real data returned by each external data source using a risk control model, and output risk control assessment results.

[0083] It should be noted that, in this embodiment, after the first access unit 11 completes the action of adjusting the preset access order, the first access unit 11 can re-execute the action of accessing multiple external data sources sequentially in the sandbox environment according to the credit application information and the preset access order, and obtaining the simulated data output by the external data sources after accepting the access based on their stored historical query data and credit application information, so as to obtain new simulated data; the running unit 12 can re-execute the action of running the online configured risk control model in the sandbox environment according to the simulated data output by each external data source, and determine whether the risk control model is running normally, so as to repeat the running test until the risk control model can run normally. This embodiment can run the online configured risk control model under the premise of meeting compliance requirements and reduce the workload of operators.

[0084] In other embodiments of this application, in the sandbox-based risk control assessment system, the first access unit 11, when executing the acquisition of simulated data output by the external data source after receiving access, based on its stored historical query data and credit application information, is specifically used for:

[0085] After the external data source is granted access, the first data is retrieved from the historical query data stored in the external data source itself, based on the credit application information.

[0086] Determine if the first data point has a median. If it does, obtain the median of the first data point and use it as the simulated data output from the external data source. Otherwise, directly obtain the first data point and use it as the simulated data output from the external data source.

[0087] like Figure 3 As shown, in another embodiment of this application, a sandbox-based risk control assessment terminal is also provided, including: a storage medium 20 and a processor 21;

[0088] Storage medium 20 stores computer-executed instructions;

[0089] The processor 21 executes computer execution instructions stored in the storage medium 20 to implement any of the methods described in the sandbox-based risk control assessment methods above.

[0090] The processor 21 may include one or more processing cores. The processor 21 executes instructions, programs, code sets, or instruction sets stored in the storage medium 20, and calls data stored in the storage medium 20 to perform various functions and process data according to this application. The processor 21 may be at least one of a specific application-specific integrated circuit, digital signal processor, digital signal processing device, programmable logic device, field-programmable gate array, central processing unit, controller, microcontroller, and microprocessor. It is understood that, for different devices, the electronic devices used to implement the functions of the processor 21 may also be other types.

[0091] The storage medium 20 can be used to store instructions, programs, code, code sets, or instruction sets. The storage medium 20 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing any of the aforementioned sandbox-based risk control assessment methods. The data storage area may store data involved in any of the aforementioned sandbox-based risk control assessment methods.

[0092] In another embodiment of this application, a computer-readable storage medium is also provided, which stores computer-executable instructions that, when executed by a processor, are used to implement any of the methods described in the above-described sandbox-based risk control assessment methods.

[0093] The computer-readable storage medium can be any medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory, random access memory, or optical disc.

[0094] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A sandbox-based risk control assessment method, characterized in that, include: Obtain the user's credit application information; In the sandbox environment, based on the credit application information and the preset access order, multiple external data sources are accessed sequentially, and the simulated data output by the external data sources after the access is accepted, based on their stored historical query data and the credit application information, is obtained. In the sandbox environment, the online configured risk control model is tested based on the simulated data output by each external data source, and it is determined whether the risk control model is operating normally. If not, the preset access order is adjusted, and then the process is repeated: in the sandbox environment, multiple external data sources are accessed sequentially according to the credit application information and the preset access order, and the simulated data output by each external data source after accepting access is obtained based on its stored historical query data and the credit application information. If yes, then: In an online environment, multiple external data sources are accessed sequentially according to the credit application information and the preset access order, and the actual data returned by the external data sources after the access is accepted according to the credit application information is obtained. In an online environment, the risk control model is used to analyze and process the real data returned by each external data source, and output the risk control assessment results.

2. The method as described in claim 1, characterized in that, The step of obtaining the simulated data output by the external data source after receiving access, based on its stored historical query data and the credit application information, includes: After the external data source is granted access, the first data is obtained from the historical query data stored in the external data source itself, based on the credit application information. Determine whether the first data has a median. If it does, obtain the median of the first data and use it as the simulated data output by the external data source. If not, directly obtain the first data and use it as the simulated data output by the external data source.

3. The method as described in claim 1, characterized in that, The external data sources include a first data source for providing user loan information, a second data source for providing user social security information, and a third data source for providing user fraud risk information.

4. The method as described in claim 1, characterized in that, The adjustment of the preset access order includes: The preset access order is adjusted using a preset adaptive algorithm.

5. The method as described in claim 1, characterized in that, The credit application information includes one or more of the user's name, phone number, ID card number, and facial information.

6. The method as described in claim 1, characterized in that, The sandbox environment is configured with a code signing-based security mechanism.

7. A sandbox-based risk assessment system, characterized in that, include: The acquisition unit is used to acquire the user's credit application information; The first access unit is used to access multiple external data sources sequentially in a sandbox environment according to the credit application information and a preset access order, and to obtain the simulated data output by the external data sources after accepting the access based on their stored historical query data and the credit application information. The running unit is used to run the online configured risk control model in a sandbox environment based on the simulated data output by each of the external data sources, and to determine whether the risk control model is running normally. The first access unit is also used to adjust the preset access order in a sandbox environment when the risk control model is not running normally; The second access unit is used to access multiple external data sources sequentially in an online environment, according to the credit application information and the preset access order, when the risk control model is running normally, and to obtain the real data returned by the external data sources according to the credit application information after the access is accepted; The analysis unit is used in an online environment to analyze and process the real data returned by each of the external data sources using the risk control model, and output the risk control assessment results.

8. The system as described in claim 7, characterized in that, The first access unit, when executing the step of obtaining the simulated data output by the external data source after accepting access, based on its stored historical query data and the credit application information, is specifically used for: After the external data source is granted access, the first data is obtained from the historical query data stored in the external data source itself, based on the credit application information. Determine whether the first data has a median. If it does, obtain the median of the first data and use it as the simulated data output by the external data source. If not, directly obtain the first data and use it as the simulated data output by the external data source.

9. A sandbox-based risk control assessment terminal, characterized in that, include: Storage media and processor; The storage medium stores computer-executed instructions. The processor executes computer execution instructions stored in the storage medium to implement the method as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 6.

Images