A method and system for assessing network financial transaction risks

Abstract

The present invention provides a method and system for assessing online financial transaction risk, which can be used in the financial field or other technical fields. The system includes: at least two risk assessment model service modules, each of which is used to assess different types of online financial transaction risks; a model management module, connected to each risk assessment model service module and configured to invoke a risk assessment model service module corresponding to a risk monitoring request, so that the risk assessment model service module performs a risk assessment on the transaction information in the risk monitoring request; and at least two application programming interfaces (APIs), each of which is connected to the model management module and configured to obtain different types of risk monitoring requests from a first-category business system and transmit the risk monitoring requests to the model management module. The method and system for assessing online financial transaction risk provided by embodiments of the present invention can improve the capabilities and efficiency of financial transaction risk supervision, identification, and early warning.

Description

Technical Field

[0001] The present invention relates to the financial field or other technical fields, and in particular to a method and system for assessing the risks of online financial transactions. Background Art

[0002] With the development of financial technology, online businesses have become a key area of financial innovation for commercial banks. Commercial banks are rapidly developing open platforms, collaborating with third-party partners to build financial scenarios and share in the benefits of online finance. However, with the growth of online finance, unscrupulous third-party partners are exploiting their technological advantages to misappropriate, misuse, and resell banks' open platform interfaces, disrupting normal market order.

[0003] Currently, risk identification of online banking services mainly relies on manual identification after the fact. This identification method has the problems of large manual workload, poor timeliness and low identification accuracy. Summary of the Invention

[0004] In response to the problems in the prior art, embodiments of the present invention provide a method and system for assessing the risks of online financial transactions, which can at least partially solve the problems in the prior art.

[0005] On the one hand, the present invention proposes a network financial transaction risk assessment system, comprising: at least two risk assessment model service modules, wherein each of the risk assessment model service modules is used to assess different types of network financial transaction risks; a model management module, connected to each of the risk assessment model service modules, for calling the risk assessment model service module corresponding to the risk monitoring request, so that the risk assessment model service module performs risk assessment on the transaction information in the risk monitoring request, wherein each of the risk monitoring requests has at least two corresponding risk assessment model service modules; at least two application interfaces, each of the application interfaces is connected to the model management module, and each of the application interfaces is used to obtain different types of risk monitoring requests from the first type of business system, and send the risk monitoring requests to the model management module.

[0006] Optionally, the system also includes: a data lake module, connected to at least two of the risk assessment model service modules, for obtaining and storing transaction information of the second category business system; a task scheduling module, connected to the model management module, for notifying the model management module to call the risk assessment model service module corresponding to the second category business system according to the scheduling strategy corresponding to each of the second category business systems, so that the risk assessment model service module performs risk assessment on the transaction information of the second category business system, wherein each second category business system has at least one corresponding risk assessment model service module.

[0007] Optionally, after obtaining and storing the transaction information of the second type of business system, the data lake module is also used to calculate the risk detection parameters of the transaction information; the risk assessment model service module performs risk assessment on the transaction information of the second type of business system, including: performing risk assessment on the transaction information according to the risk detection parameters.

[0008] Optionally, the system also includes: a warning information generation module, which is connected to each of the risk assessment model service modules, and is used to obtain warning information of the transaction information evaluated by each of the risk assessment model service modules based on the risk assessment results generated by each of the risk assessment model service modules.

[0009] Optionally, the risk assessment model service module includes at least one of the following: a transaction limit warning module, a risky customer monitoring module, and a transaction amount distribution module.

[0010] On the other hand, the present invention proposes a method for assessing the risks of online financial transactions, including: obtaining a risk monitoring request from a first type of business system, wherein the risk monitoring request includes transaction information; calling a risk assessment model service module corresponding to the risk monitoring request to perform risk assessment on the transaction information, wherein each risk monitoring request has at least two corresponding risk assessment model service modules, and each risk assessment model service module is used to assess different types of online financial transaction risks.

[0011] Optionally, the method also includes: obtaining and storing transaction information of the second type of business system; calling the risk assessment model service module corresponding to the second type of business system to perform risk assessment on the transaction information according to the scheduling strategy corresponding to the second type of business system, wherein the second type of business system has at least one corresponding risk assessment model service module.

[0012] Optionally, calling the risk assessment model service module corresponding to the second type of business system to perform risk assessment on the transaction information according to the scheduling policy corresponding to the second type of business system includes: obtaining the risk assessment timing for the transaction information in the scheduling policy corresponding to the second type of business system; and calling the risk assessment model service module corresponding to the second type of business system to perform risk assessment on the transaction information according to the risk assessment timing.

[0013] Optionally, the obtaining and storing transaction information of the second category business system includes: obtaining and storing transaction information of the second category business system, and calculating risk detection parameters of the transaction information; the calling of the risk assessment model service module corresponding to the second category business system according to the scheduling strategy corresponding to the second category business system to perform risk assessment on the transaction information includes: calling the risk assessment model service module corresponding to the second category business system according to the scheduling strategy corresponding to the second category business system to perform risk assessment on the transaction information according to the risk detection parameters.

[0014] Optionally, the method further includes: obtaining early warning information of the transaction information evaluated by each of the risk assessment model service modules according to the risk assessment results generated by each of the risk assessment model service modules.

[0015] Optionally, the risk assessment model service module includes at least one of the following: a transaction limit warning module, a risky customer monitoring module, and a transaction amount distribution module.

[0016] On the other hand, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for assessing the risk of online financial transactions as described in any of the above embodiments are implemented.

[0017] In another aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for assessing the risk of online financial transactions described in any of the above embodiments.

[0018] The method and system for assessing the risks of online financial transactions provided by the embodiments of the present invention adopt the design concept of "model as a service" to combine multiple risk assessment model service modules into various types of risk monitoring services, and provide a service-based call interface (application programming interface) for each risk monitoring service. The input and output elements of each interface specification are formulated, and the risk monitoring service is published to the outside world through an API (application programming interface). In this way, the bank's business system or other business systems can use the standard interface published by this system to obtain the ability to monitor and warn of online financial transaction risks, thereby improving the ability to identify, warn and quickly deal with financial transaction risk supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0020] Figure 1 It is a structural diagram of the network financial transaction risk assessment system provided by the first embodiment of the present invention.

[0021] Figure 2 It is a flowchart of a method for assessing the risk of online financial transactions provided by the second embodiment of the present invention.

[0022] Figure 3 This is a partial flow chart of a method for assessing online financial transaction risks provided by the third embodiment of the present invention.

[0023] Figure 4 This is a partial flow chart of a method for assessing online financial transaction risks provided by the fourth embodiment of the present invention.

[0024] Figure 5 It is a schematic diagram of the physical structure of an electronic device provided by the fifth embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, unless there is a conflict, the embodiments and features in the embodiments of this application can be combined with each other in any manner.

[0026] Figure 1 FIG. 1 is a schematic diagram of a system for assessing the risk of online financial transactions according to an embodiment of the present invention. Figure 1 As shown, the network financial transaction risk assessment system provided by the embodiment of the present invention includes:

[0027] At least two risk assessment model service modules 11, wherein each risk assessment model service module 11 is used to assess different types of online financial transaction risks;

[0028] a model management module 12, connected to each of the risk assessment model service modules 11, configured to call the risk assessment model service module 11 corresponding to the risk monitoring request, so that the risk assessment model service module 11 performs a risk assessment on the transaction information in the risk monitoring request, wherein each risk monitoring request has at least two corresponding risk assessment model service modules 11;

[0029] At least two application programming interfaces 13, each of which is connected to the model management module 12, and each of which is used to obtain different types of risk monitoring requests from the first type of business system and send the risk monitoring requests to the model management module 12.

[0030] This embodiment can combine the existing risk assessment resources of the banking system (such as the Rong'an E-mail interface provided by the Industrial and Commercial Bank of China) and the historical transaction data accumulated by the banking system (such as the historical transaction data of the banking cooperative institutions, the historical transaction data accumulated by the special system of the Industrial and Commercial Bank of China Zhejiang Branch, etc.), and integrate the different data sources provided by the banking system through big data technology to reduce the complexity of the risk analysis of online financial transactions. Then, through machine learning, customer transaction behavior risk analysis is conducted on different scenarios of online financial transactions (insurance, funds, credit card repayments, water, electricity and gas payments, etc.), and each of the risk assessment model service modules is constructed.

[0031] Specifically, the risk assessment model service module can use the telecommunications fraud interface, financial blacklist interface and other interfaces provided by Rong'an E-mail to verify whether the transaction customer is a risky customer; in addition, the special system of the Industrial and Commercial Bank of China Zhejiang Branch has accumulated more than 10 million customer agreements after years of accumulation, among which there are a large number of blacklisted customers available for use by the risk assessment model service module; in addition, the transaction data of cooperative institutions continuously accumulated by the banking system is an important data source for risk identification and analysis. By mining and analyzing the historical maximum transaction amount and transaction amount distribution of the cooperative institutions, it helps to establish at least part of the risk assessment model service module.

[0032] For example, the risk assessment model service module may include: a transaction limit warning module, a transaction amount distribution module, a risky customer monitoring module, etc. The transaction limit warning module may be used to: monitor the number of times a cooperative institution reaches the daily cumulative transaction amount limit of the institution. If the proportion exceeds the specified threshold, a warning message will be generated. The transaction amount distribution module may be used to: analyze the transaction amount distribution of the institution. For example, if the transaction amount is generally an integer multiple of 100, there may be an application of financial product purchases, thereby generating relevant warning information. The risky customer monitoring module may be used to: regularly scan the transaction protocol library, and determine whether the customer is a risky customer by calling Rong'an E-mail telecommunications fraud, financial blacklist, default record and other interfaces. If a match is found, a corresponding warning message will be generated. Based on different business scenarios, a variety of other risk models can also be implemented, and the embodiments of the present invention do not limit this.

[0033] This risk assessment system can adopt the "model as a service" design concept, combine multiple risk assessment model service modules to form various types of risk monitoring services, and provide a service-based call interface (application programming interface) for each risk monitoring service, formulate the input and output elements of each interface specification, and publish the risk monitoring service to the outside world through the API (application programming interface), so that the bank's business system or other business systems can use the standard interface published by this system to obtain the ability to monitor and warn of online financial transaction risks.

[0034] Specifically, the process control module implemented in the Spring framework can be used to string together individual services (risk assessment model service modules) through XML configuration, allowing different services to work together to complete specific tasks. This process service orchestration approach allows multiple risk assessment model service modules to be flexibly combined to create a variety of risk monitoring services, increasing the scalability and accuracy of risk assessments.

[0035] The first type of business system may be a business system that can directly provide risk monitoring data in a risk monitoring request, that is, the transaction information in the risk monitoring request sent by the first type of business system includes risk monitoring data. In this way, after obtaining the risk monitoring data, the risk assessment model service module can directly use the risk monitoring data to perform risk assessment.

[0036] The model management module stores a risk assessment model service module combination corresponding to each of the application program interfaces. The model management module calls the risk assessment model service module corresponding to the risk monitoring request, including: calling each risk assessment model service module in the risk assessment model service module combination corresponding to the application program interface that sends the risk monitoring request, so that each risk assessment model service module performs risk assessment on the transaction information in the risk monitoring request.

[0037] The network financial transaction risk assessment system provided by the embodiment of the present invention adopts the "model as a service" design concept, combines multiple risk assessment model service modules into various types of risk monitoring services, and provides a service-based call interface (application programming interface) for each risk monitoring service. The input and output elements of each interface specification are formulated, and the risk monitoring service is published to the outside world through the API (application programming interface). In this way, the bank's business system or other business systems can use the standard interface published by this system to obtain the ability to automatically monitor and warn of network financial transaction risks, thereby improving the ability and efficiency of financial risk supervision identification, warning and rapid disposal.

[0038] Optionally, this risk assessment system can also provide a service-based call interface (application programming interface) for each risk assessment model service module, formulate the input and output elements of each interface specification, and publish the risk assessment model service module to the outside world through the API (application programming interface), so that other business systems can use the standard interface published by this system to obtain the ability to monitor and warn of network financial transaction risks.

[0039] During the development of a risk assessment system, big data technologies can be leveraged to integrate disparate data sources, significantly reducing the complexity of data collection and risk assessment calculations. Some banking system business data is stored in MySQL databases, while others are stored in Oracle databases. Collecting and processing data across these disparate data sources is inconvenient and inefficient. Therefore, customer agreement data and historical successful transaction data from various sources can be uniformly imported into a Hadoop data lake. This data can then be integrated and queried using big data query processing languages like Hive, improving the efficiency of data processing and risk assessment calculations.

[0040] like Figure 1 As shown, optionally, the system may further include:

[0041] A data lake module 14, connected to at least two of the risk assessment model service modules 11, for acquiring and storing transaction information of the second type of business system;

[0042] The task scheduling module 15 is connected to the model management module 12 and is used to notify the model management module 12 to call the risk assessment model service module 11 corresponding to the second-category business system according to the scheduling strategy corresponding to each second-category business system, so that the risk assessment model service module 11 performs risk assessment on the transaction information of the second-category business system, wherein each second-category business system has at least one corresponding risk assessment model service module 11.

[0043] In this embodiment, the model management module stores a risk assessment model service module corresponding to each second-category business system, and the task scheduling module stores a scheduling policy for each second-category business system. The scheduling policy is used to specify the timing of risk assessment of transaction information of the second-category business system, such as timed assessment. After the risk assessment model service module is activated, the transaction information of the second-category business system can be directly obtained in the data lake module.

[0044] The correspondence between the second-category business systems and risk assessment model service modules stored in the model management module can be determined based on the needs of the business system. For example, a business system needs to determine whether a customer is at risk of telecommunications fraud or is on the branch's special agreement blacklist, and at the same time, determine whether the customer's deduction behavior poses a risk of illegal transaction application. Therefore, the system can combine the Rong'an E-letter real-time API interface (which can be considered as one risk assessment model service module), the branch's special business blacklist library (which can be considered as another risk assessment model service module), and the machine learning-based institutional scenario risk behavior analysis library (which can be considered as another risk assessment model service module) to create a risk assessment model service module combination that meets its requirements.

[0045] Taking into account that some business systems (first category business systems) need to provide risk detection data through interfaces to obtain risk monitoring capabilities; and some business systems (second category business systems) only hope to provide transaction source data, and the calculation of risk detection data is completed in the risk assessment system. Therefore, this embodiment, based on the design of an API service interface to connect to the first category business system, also provides a data lake interface to connect to the second category business system; the data lake module can convert the source data in the transaction information into risk monitoring data and send it to the risk assessment model service module corresponding to the second category business system, so that the risk assessment model service module can directly perform risk assessment based on the risk monitoring data. Of course, when the second category business system can provide risk monitoring data, the data lake module can also only store the risk monitoring data of the second category business system, and the risk assessment model service module corresponding to the second category business system can directly obtain the risk monitoring data in the data lake module.

[0046] Optionally, after obtaining and storing the transaction information of the second type of business system, the data lake module is also used to calculate the risk detection parameters of the transaction information; the risk assessment model service module performs risk assessment on the transaction information of the second type of business system, including: performing risk assessment on the transaction information according to the risk detection parameters.

[0047] In this embodiment, the risk detection parameter refers to the input parameter that can be directly used by the risk assessment model service module when performing risk assessment. For example, for the transaction limit warning module, the risk detection parameter refers to the transaction amount of the institution on each trading day; for the risk customer monitoring module, the risk detection parameter refers to the customer name.

[0048] When the transaction information provided by the second-type business system is transaction source data, the data lake module can process the transaction source data and generate risk detection parameters corresponding to the transaction information, so that the risk assessment model service module can directly perform risk assessment on the transaction information based on the risk detection parameters.

[0049] like Figure 1 As shown, optionally, the system may also include: an early warning information generation module 16, which is connected to each of the risk assessment model service modules 11, and is used to obtain early warning information of the transaction information evaluated by each of the risk assessment model service modules 11 based on the risk assessment results generated by each of the risk assessment model service modules 11.

[0050] In this embodiment, after the risk assessment model service module performs risk assessment on the transaction information in the risk monitoring request / the second type of business system, it will generate a corresponding risk assessment result. For example, the risk assessment result is a risk hit value, which is 1 if it hits and 0 if it misses.

[0051] The warning information can be obtained by integrating the risk assessment results of each risk assessment model. For example, after the calculation of each risk assessment model service module is completed, the risk hit value output by each model is accumulated. When the accumulated value is equal to or higher than the target threshold (such as the target threshold is 1), a warning information is generated.

[0052] After the warning information is generated, the warning information can be saved in the risk list library, so that the risk alarm management platform can send SMS or email alarms based on the warning information.

[0053] The use of this system significantly improves the automated level of risk monitoring for online banking transactions within the banking system. For example, by monitoring a certain institution using the transaction amount distribution module and the customer agreement blacklist module, we discovered that the institution had a large number of transactions with amounts multiple of 100 within a certain period, and that some of the customers were on our agreement blacklist. Further offline verification confirmed that the institution had abused and misused online API interfaces, prompting us to swiftly cease business transactions with the associated partner, thus ensuring the compliance of our online business.

[0054] To better understand the present invention, the following describes in detail the network financial transaction risk assessment system provided by the embodiment of the present invention in different scenarios.

[0055] Scenario 1: The first-class business system is connected through a service interface. (1) A first-class business system uploads customer card number, ID number and other information to the risk assessment system by calling the first API service interface. (2) The risk assessment system calls the telecommunications fraud query service model, the litigation information query model, the historical abnormal transaction library comparison model, the branch agreement blacklist library model, etc. according to the risk assessment model service module corresponding to the interface to perform risk assessment on the information. (3) Each model generates a risk hit value, which is 1 if it hits and 0 if it does not hit. (4) After all risk assessment model service modules have completed the calculation, the risk hit values of each model are accumulated. If it is higher than the threshold (such as greater than or equal to 2), an early warning message is generated and recorded in the risk list library. (5) The risk alarm management platform is responsible for SMS and email alarms.

[0056] Scenario 2: The second-type business system is successfully connected through the data lake. (1) A second-type business system imports the transaction details of a certain day from the Oracle database into the data lake. The transaction details include customer card number, ID number, transaction amount and other elements. (2) The task scheduling module configures the scheduled task of the business system, which is triggered at 12 noon every day. (3) The risk assessment system calls the branch agreement blacklist library model and the institutional transaction amount distribution module in sequence according to the risk assessment model service module corresponding to the scheduled task to perform risk assessment. (3) Each model generates a risk hit value, which is 1 if it hits and 0 if it does not hit. (4) After all risk assessment model service modules are calculated, the risk hit values of each model are accumulated. If it is higher than the threshold (such as greater than or equal to 1), an early warning message is generated and recorded in the risk list library. (5) The risk alarm management platform is responsible for SMS and email alarms.

[0057] Figure 2 FIG. 1 is a flow chart of a method for assessing the risk of online financial transactions provided by an embodiment of the present invention. Figure 2 As shown, the method for assessing the risk of online financial transactions provided by the embodiment of the present invention includes:

[0058] S201. Obtain a risk monitoring request from a first-category business system, where the risk monitoring request includes transaction information.

[0059] S202. Call the risk assessment model service module corresponding to the risk monitoring request to perform risk assessment on the transaction information, wherein each risk monitoring request has at least two corresponding risk assessment model service modules, and each risk assessment model service module is used to assess different types of online financial transaction risks.

[0060] The method for assessing the risks of online financial transactions provided by an embodiment of the present invention can match multiple risk assessment model service modules for each risk monitoring request. Each of the risk assessment model service modules jointly completes the risk assessment work of the transaction information in the risk monitoring request, thereby increasing the scalability of risk assessment and improving the accuracy of risk assessment; the bank's business system or other business systems can use this method to obtain automatic monitoring and early warning capabilities for online financial transaction risks, thereby improving the financial risk supervision identification, early warning and rapid disposal capabilities and efficiency.

[0061] like Figure 3 As shown, optionally, the method may further include:

[0062] S203. Acquire and store transaction information of the second type of business system;

[0063] S204. According to the scheduling strategy corresponding to the second-category business system, call the risk assessment model service module corresponding to the second-category business system to perform risk assessment on the transaction information, wherein the second-category business system has at least one corresponding risk assessment model service module.

[0064] like Figure 4 As shown, optionally, calling the risk assessment model service module corresponding to the second type of business system to perform risk assessment on the transaction information according to the scheduling policy corresponding to the second type of business system may include:

[0065] S2041. Obtaining a risk assessment timing for the transaction information in a scheduling policy corresponding to the second-type business system;

[0066] S2042: Based on the risk assessment opportunity, call the risk assessment model service module corresponding to the second type of business system to perform risk assessment on the transaction information.

[0067] Optionally, the obtaining and storing transaction information of the second category business system may include: obtaining and storing transaction information of the second category business system, and calculating risk detection parameters of the transaction information; the calling of the risk assessment model service module corresponding to the second category business system according to the scheduling strategy corresponding to the second category business system to perform risk assessment on the transaction information includes: calling the risk assessment model service module corresponding to the second category business system according to the scheduling strategy corresponding to the second category business system to perform risk assessment on the transaction information according to the risk detection parameters.

[0068] Optionally, the method may further include: obtaining early warning information of the transaction information evaluated by each of the risk assessment model service modules according to the risk assessment results generated by each of the risk assessment model service modules.

[0069] Optionally, the risk assessment model service module includes at least one of the following: a transaction limit warning module, a risky customer monitoring module, and a transaction amount distribution module.

[0070] The execution subject of the method for assessing the risk of online financial transactions provided by the embodiment of the present invention includes but is not limited to a computer.

[0071] The specific execution process of the method for assessing the risk of online financial transactions provided by the embodiment of the present invention can refer to the detailed description of the above-mentioned assessment system embodiment, which will not be repeated here.

[0072] It should be noted that the method and system for assessing the risks of online financial transactions provided in the embodiments of the present invention can be used in the financial field, and can also be used in any technical field other than the financial field. The embodiments of the present invention do not limit the application fields of the method and system for assessing the risks of online financial transactions.

[0073] Figure 5 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention is shown in FIG. Figure 5As shown, the electronic device may include: a processor 301, a communications interface 302, a memory 303, and a communications bus 304, wherein the processor 301, the communications interface 302, and the memory 303 communicate with each other via the communications bus 304. The processor 301 may invoke logic instructions in the memory 303 to execute the following method: obtaining a risk monitoring request from a first-category business system, wherein the risk monitoring request includes transaction information; and invoking a risk assessment model service module corresponding to the risk monitoring request to perform a risk assessment on the transaction information, wherein each risk monitoring request has at least two corresponding risk assessment model service modules, each of which is used to assess different types of online financial transaction risks.

[0074] In addition, the logic instructions in the above-mentioned memory 303 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0075] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the methods provided by the above-mentioned method embodiments, for example, including: obtaining a risk monitoring request from a first-category business system, wherein the risk monitoring request includes transaction information; calling a risk assessment model service module corresponding to the risk monitoring request to perform a risk assessment on the transaction information, wherein each risk monitoring request has at least two corresponding risk assessment model service modules, and each risk assessment model service module is used to assess different types of online financial transaction risks.

[0076] This embodiment provides a computer-readable storage medium, which stores a computer program. The computer program enables the computer to execute the methods provided by the above-mentioned method embodiments, for example, including: obtaining a risk monitoring request from a first-category business system, wherein the risk monitoring request includes transaction information; calling a risk assessment model service module corresponding to the risk monitoring request to perform a risk assessment on the transaction information, wherein each risk monitoring request has at least two corresponding risk assessment model service modules, and each risk assessment model service module is used to assess different types of online financial transaction risks.

[0077] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0078] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0079] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0080] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0081] Throughout this specification, reference to terms such as "one embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0082] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A network financial transaction risk assessment system, characterized in that: include: At least two risk assessment model service modules, wherein each risk assessment model service module is used to assess different types of online financial transaction risks; a model management module connected to each of the risk assessment model service modules and configured to call a risk assessment model service module corresponding to a risk monitoring request, so that the risk assessment model service module performs a risk assessment on the transaction information in the risk monitoring request, wherein each risk monitoring request has at least two corresponding risk assessment model service modules; at least two application programming interfaces (APIs), each of which is connected to the model management module, and each of which is used to obtain different types of risk monitoring requests from the first type of business system and send the risk monitoring requests to the model management module; The system further comprises: a data lake module, connected to at least two of the risk assessment model service modules, for acquiring and storing transaction information of the second type of business system; a task scheduling module, connected to the model management module, for notifying the model management module to invoke the risk assessment model service module corresponding to each second-category business system based on the scheduling policy corresponding to the second-category business system, so that the risk assessment model service module performs a risk assessment on the transaction information of the second-category business system, wherein each second-category business system has at least one corresponding risk assessment model service module; Multiple risk assessment model service modules are combined to form various types of risk monitoring services. Each risk monitoring service provides an application program interface (API) for service-oriented calls. The first type of business system calls the corresponding API based on the type of risk monitoring request. Using the Spring framework to implement process control, individual risk assessment model service modules are connected together through XML configuration, so that different service modules can jointly complete specific tasks. The data lake interface is connected to the second type of business system. The data lake module converts the source data in the transaction information into risk monitoring data and sends it to the risk assessment model service module corresponding to the second type of business system, so that the risk assessment model service module can directly perform risk assessment based on the risk monitoring data; the second type of business system imports the transaction details of a certain period from the database into the data lake module.

2. The evaluation system according to claim 1, wherein: The system further comprises: The early warning information generation module is connected to each of the risk assessment model service modules and is used to obtain early warning information of the transaction information assessed by each of the risk assessment model service modules based on the risk assessment results generated by each of the risk assessment model service modules.

3. The evaluation system according to claim 1, wherein: The risk assessment model service module includes at least one of the following: a transaction limit warning module, a risky customer monitoring module, and a transaction amount distribution module.

4. A method for assessing the risk of online financial transactions, characterized in that: The method comprises: Obtaining a risk monitoring request from the first type of business system, wherein the risk monitoring request includes transaction information; Invoking a risk assessment model service module corresponding to the risk monitoring request to perform a risk assessment on the transaction information, wherein each risk monitoring request has at least two corresponding risk assessment model service modules, and each risk assessment model service module is used to assess different types of online financial transaction risks; Acquire and store transaction information of the second type of business system; Invoking a risk assessment model service module corresponding to the second-category business system to perform risk assessment on the transaction information according to a scheduling policy corresponding to the second-category business system, wherein the second-category business system has at least one corresponding risk assessment model service module; Multiple risk assessment model service modules are combined to form various types of risk monitoring services. Each risk monitoring service provides an application program interface (API) for service-oriented calls. The first type of business system calls the corresponding API based on the type of risk monitoring request. Using the Spring framework to implement process control, individual risk assessment model service modules are connected together through XML configuration, so that different service modules can jointly complete specific tasks. The data lake interface is connected to the second type of business system. The data lake module converts the source data in the transaction information into risk monitoring data and sends it to the risk assessment model service module corresponding to the second type of business system, so that the risk assessment model service module can directly perform risk assessment based on the risk monitoring data; the second type of business system imports the transaction details of a certain period from the database into the data lake module.

5. The method according to claim 4, characterized in that The step of calling the risk assessment model service module corresponding to the second type of business system to perform risk assessment on the transaction information according to the scheduling policy corresponding to the second type of business system includes: Obtaining a risk assessment timing for the transaction information in a scheduling strategy corresponding to the second-category business system; According to the risk assessment opportunity, the risk assessment model service module corresponding to the second type of business system is called to perform risk assessment on the transaction information.

6. The method according to claim 4, characterized in that The method further comprises: According to the risk assessment results generated by each of the risk assessment model service modules, early warning information of the transaction information assessed by each of the risk assessment model service modules is obtained.

7. The method according to claim 4, characterized in that The risk assessment model service module includes at least one of the following: a transaction limit warning module, a risky customer monitoring module, and a transaction amount distribution module.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 4 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 4 to 7 are implemented.

Images