Transaction risk prediction method and device
By generating risk units and building risk models, risk prediction and processing of transaction data is solved, and the problem of hysteresis response of risk scenario monitoring systems in the existing technology is solved, and the rapid expansion of risk monitoring scenarios and the timeliness of risk warning are achieved.
Patent Information
- Application Number
- CN202011006272.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-09-23
- Publication Date
- 2024-12-31
- Estimated Expiration
- 2040-09-23
AI Technical Summary
The existing risk scenario monitoring system has a narrow scope and cannot respond to new risk scenarios quickly, resulting in slow iteration of risk monitoring and response methods, and the inability to timely discover and handle risk operations in the business process.
By generating risk units based on transaction process records, determining the target transaction process to build a risk model, making risk predictions for transaction data based on the risk model, and improving the accuracy and visual display of prediction results through screening, review and evaluation processing, achieving rapid expansion of risk monitoring Scene.
It significantly shortens the time from discovery to risk scenarios when they are put into use, improves the timeliness and accuracy of risk monitoring and early warning, can quickly respond to new risk scenarios, and reduces the delay in risk monitoring and processing.
Smart Images
Figure CN111967801B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer monitoring technology, and in particular to a method and device for predicting transaction risks. Background Art
[0002] With the development of society, more and more people go to commercial banks to handle related business. With the gradual electronicization and dataization of commercial bank counter business, the increase of bank products and the complexity of business processes, intentional or unintentional errors have occurred in counter business. In order to achieve rapid error correction and rectification of business, a risk monitoring and early warning system based on big data is needed. This risk monitoring and early warning system can flexibly configure risk models (risk models refer to a series of rule statements and parameter configurations developed based on specific risk scenarios) according to risk scenarios (risk scenarios refer to operational violations and behaviors that do not comply with regulations and systems during counter transactions), and timely discover risk operations in the business process by executing risk models.
[0003] Currently, in terms of risk scenario monitoring, commercial banks basically develop specific models based on existing risk scenarios. When a new risk scenario emerges, they first conduct a demand analysis, then develop code based on the demand. After development is completed, the corresponding test is carried out and the model is finally put online, becoming an embedded module of the existing risk control system.
[0004] However, the existing risk scenario monitoring has a narrow scope and can only monitor specific transaction scenarios. In addition, the iteration of the screening methods is slow. When a new risk scenario emerges, it takes a long time to formulate the corresponding response measures. Summary of the invention
[0005] In response to the problems in the prior art, the present invention provides a method and device for predicting transaction risks, which can greatly shorten the vacuum period from the discovery of a risk scenario to the use of the corresponding risk model, and realize the rapid expansion of risk monitoring scenarios.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In a first aspect, the present invention provides a method for predicting transaction risk, comprising:
[0008] Generate risk units corresponding to each transaction process according to the transaction data recorded in each transaction process;
[0009] Determine a target transaction process in a risk scenario, and construct a risk model based on risk units corresponding to the target transaction process;
[0010] Based on the risk model, risk prediction is performed on the target transaction data in the risk scenario to obtain a risk prediction result.
[0011] Furthermore, after performing risk prediction on the target transaction data in the risk scenario based on the risk model, the method further includes:
[0012] Generate a display template corresponding to the risk prediction according to the preset display fields;
[0013] The various fields of the risk prediction results are configured in the display template, and the display template is visualized.
[0014] Furthermore, after performing risk prediction on the target transaction data in the risk scenario based on the risk model, the method further includes:
[0015] Screening the risk prediction results to eliminate interference results in the risk prediction results and obtain screening results;
[0016] A review process for risk prediction is performed based on the screening results.
[0017] Furthermore, the screening process of the risk prediction results includes:
[0018] Obtaining interference results of each elimination; forming an interference result set according to the obtained interference results;
[0019] Screening out a target risk prediction result that is the same as any interference result in the interference result set from the risk prediction results;
[0020] The risk prediction results are interference results in the risk prediction results to be eliminated.
[0021] Furthermore, after the risk prediction results are screened, the method further includes:
[0022] Evaluating the risk model according to the screening result;
[0023] A status of the risk model is marked based on the results of the evaluation process.
[0024] The step of generating risk units corresponding to each transaction process according to the transaction data recorded in each transaction process includes:
[0025] Determine each source table storing the transaction data and determine target data in each source table;
[0026] Configure the regular expressions corresponding to the fields in each of the target data and the operation logic between the regular expressions;
[0027] The risk unit is obtained by fitting the association relationship between each source table and configuring the operation logic between each source table.
[0028] The operation logic includes at least one of AND logic, OR logic, NOT logic and priority logic.
[0029] Wherein, the risk model includes: a main model and a sub-model;
[0030] The prediction result of the output of the sub-model is used as the data input of the main model.
[0031] In a second aspect, the present invention provides a transaction risk prediction device, comprising:
[0032] The sub-unit module is used to generate risk units corresponding to each transaction process according to the transaction data recorded in each transaction process;
[0033] A risk model module, used to determine a target transaction process in a risk scenario, and to construct a risk model based on risk units corresponding to the target transaction process;
[0034] The risk prediction module is used to perform risk prediction on target transaction data in the risk scenario based on the risk model to obtain a risk prediction result.
[0035] Furthermore, it also includes:
[0036] A display configuration module, used to generate a display template corresponding to the risk prediction according to the preset display fields;
[0037] The visualization module is used to configure various fields of the risk prediction results in the display template and perform visualization processing on the display template.
[0038] Furthermore, it also includes:
[0039] A screening module is used to screen the risk prediction results so as to remove interference results in the risk prediction results and obtain screening results;
[0040] A review module is used to review the risk prediction based on the screening results.
[0041] Furthermore, it also includes:
[0042] An evaluation module, used for evaluating the risk model according to the screening result;
[0043] A marking module is used to mark the status of the risk model based on the result of the evaluation process.
[0044] In a third aspect, 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 the processor implements the steps of the transaction risk prediction method when executing the program.
[0045] In a fourth 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 transaction risk prediction method.
[0046] It can be seen from the above technical scheme that the present invention provides a method and device for predicting transaction risks, which generate risk units corresponding to each transaction process according to the transaction data recorded in each transaction process; determine the target transaction process in the risk scenario, construct a risk model based on the risk units corresponding to the target transaction process, and predict the risk of the target transaction data in the risk scenario based on the risk model to obtain a risk prediction result, realize customization of the risk model in a configuration-based manner, and quickly convert the risk scenario into a risk model, which can greatly shorten the vacuum period from the discovery of a risk scenario to the use of the corresponding risk model. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0048] Figure 1 It is a first flow chart of the method for predicting transaction risk in an embodiment of the present invention.
[0049] Figure 2 Schematic diagram of a second flow chart of the method for predicting transaction risk in an embodiment of the present invention.
[0050] Figure 3 It is a third flow chart of the method for predicting transaction risk in an embodiment of the present invention.
[0051] Figure 4 Schematic diagram of the process of step S106 in the transaction risk prediction method in the embodiment of the present invention.
[0052] Figure 5 It is a fourth flow chart of the method for predicting transaction risk in an embodiment of the present invention.
[0053] Figure 6 Schematic diagram of the flow of step S101 in the transaction risk prediction method in the embodiment of the present invention.
[0054] Figure 7 It is a schematic diagram of the structure of the transaction risk prediction system in an embodiment of the present invention.
[0055] Figure 8 A schematic diagram of the relationship between the main model and the sub-model in the transaction risk prediction method of an embodiment of the present invention.
[0056] Fig. 9 It is a schematic diagram of the structure of an application computing device in a transaction risk prediction system according to an embodiment of the present invention.
[0057] Fig.10 It is a schematic diagram of the flow of rectification processing in the transaction risk prediction system according to an embodiment of the present invention.
[0058] Fig.11 Schematic diagram of the structure of a device for predicting transaction risk in an embodiment of the present invention.
[0059] Fig.12 Schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION
[0060] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0061] The present invention provides an embodiment of a method for predicting transaction risk, see Figure 1 The transaction risk prediction method specifically includes the following contents:
[0062] S101: Generate risk units corresponding to each transaction process according to transaction data recorded in each transaction process;
[0063] In this step, the transaction data generated in the transaction process is recorded. The transaction data can be transaction data or business data. Transaction data can be call data and order data, etc., and business data can be transaction details and reference data, etc.
[0064] According to the transaction data generated in the transaction process, the filtering rules for each field in the transaction data are formulated, which constitutes the risk unit corresponding to the transaction process. For example, if the content of the field is the transaction amount, the filtering rule is formulated as: the transaction amount is not greater than the transaction limit. If the content of the field is the transaction date, the filtering rule is formulated as: between XX and YY.
[0065] S102: Determine a target transaction process in a risk scenario, and construct a risk model based on risk units corresponding to the target transaction process;
[0066] In this step, each target transaction process involved in the risk scenario is determined. According to the correspondence between each transaction process and the risk unit determined in step S101, the risk unit corresponding to each target transaction process is queried. Each risk unit constitutes a risk model. Among them, the risk model includes: a main model and a sub-model; the prediction result of the output of the sub-model is used as the data input of the main model.
[0067] The main model corresponds to one risk unit, one main model corresponds to multiple sub-models, and each sub-model corresponds to one risk unit.
[0068] The structure of multiple sub-models and a single main model can ensure that the risk model has the ability to handle complex risk scenarios. Each main model depends on the operating results of its sub-model. The one-main-multiple-sub-model structure ensures that the risk model has the ability to handle complex risk scenarios. Users can split complex risk scenarios into multiple simple risk scenarios and implement them into single sub-models, and then combine these sub-models into the final result through the main model.
[0069] S103: Perform risk prediction on target transaction data in the risk scenario based on the risk model to obtain a risk prediction result.
[0070] In this step, the target transaction data in the risk scenario is synchronized from the upstream system through the big data system (such as GreenPlum), and the batch scheduling (such as Control-M) generates tasks to execute the configured risk model and output the risk prediction results. Among them, the timeliness of risk discovery can be accelerated by timing and batch processing tasks.
[0071] It should be noted that the risk prediction results output by the risk model are all risky results.
[0072] From the above description, it can be seen that the transaction risk prediction method provided in the embodiment of the present invention generates risk units corresponding to each transaction process according to the transaction data recorded in each transaction process; determines the target transaction process in the risk scenario, constructs a risk model based on the risk units corresponding to the target transaction process, and predicts the risk of the target transaction data in the risk scenario based on the risk model to obtain a risk prediction result, thereby realizing customization of the risk model in a configuration-based manner, and quickly converting the risk scenario into a risk model, which can greatly shorten the vacuum period from the discovery of a risk scenario to the use of the corresponding risk model.
[0073] In one embodiment of the present invention, see Figure 2After step S103 of the transaction risk prediction method, the following contents are specifically included:
[0074] S104: generating a display template corresponding to the risk prediction according to the preset display fields;
[0075] In this step, the preset display fields include all fields of each transaction data in each transaction process. The target fields in the preset display fields are determined according to the display requirements or user usage requirements, such as transaction date, account number, and counter. The target fields constitute the display template corresponding to the risk prediction.
[0076] S105: configuring each field of the risk prediction result in the display template, and performing visualization processing on the display template.
[0077] In this step, when displaying fields, they are mainly used as risk data in risk treatment; when configuring sub-model display fields, they are mainly used to determine the content of the intermediate table fields corresponding to the sub-model. The main model counts the results of all sub-models to obtain the final result.
[0078] It can be seen from the above description that this embodiment can realize the display of risk prediction results based on a visual interface.
[0079] In one embodiment of the present invention, see Figure 3 After step S103 of the transaction risk prediction method, the following contents are specifically included:
[0080] S106: screening the risk prediction results to remove interference results in the risk prediction results and obtain screening results;
[0081] S107: Reviewing the risk prediction based on the screening results.
[0082] In this embodiment, the risk prediction results are screened to remove interference results that do not contain risks in the risk prediction results, thereby improving the accuracy of the risk prediction results. The accuracy of the risk prediction results can be further improved by reviewing the risk prediction of the screening results.
[0083] In the specific implementation, see Figure 4 , the risk prediction results are screened and processed, and the screening is achieved through the following steps, which specifically include the following contents:
[0084] S1061: Obtain interference results of each elimination; and form an interference result set according to the obtained interference results;
[0085] S1062: Filter out a target risk prediction result that is the same as any interference result in the interference result set from the risk prediction results;
[0086] The risk prediction results are interference results in the risk prediction results to be eliminated.
[0087] It is understandable that the screening results are sent to an artificial intelligence terminal or a manual service end, which will review the risk prediction of the screening results. Or based on a preset big data system, the big data system replaces manual screening to avoid human errors and improve timeliness. The risk warning capability is enhanced through big data, and early detection and early handling of risks are achieved.
[0088] It can be seen from the above description that this embodiment can screen and review the risk prediction results to improve the accuracy of the risk model.
[0089] In one embodiment of the present invention, see Figure 5 After step S103 of the transaction risk prediction method, the following contents are specifically included:
[0090] S108: Evaluate the risk model according to the screening result;
[0091] S109: Marking the status of the risk model based on the result of the evaluation process.
[0092] In this embodiment, the risk model is evaluated based on the screening results, including calculating a comprehensive score of the risk model based on the number of valid warnings, the total number of warnings generated, the number of problems requiring rectification, and the number of problems generated in the screening results.
[0093] The comprehensive score of the risk model is calculated as follows:
[0094] The comprehensive score of the risk model = 100x(1-model running time / 86400)x(number of effective warnings / total number of warnings generated)x(number of problems requiring rectification / number of problems generated).
[0095] It should be noted that the unit of model running time is hours, the number of valid warnings is the number of warnings corresponding to the screening results, the total number of warnings generated is the number of warnings in the risk prediction results, the number of problems requiring rectification is the number of warnings that have been rectified in the screening results, and the number of problems generated is the number of warnings that have not been rectified in the screening results.
[0096] When marking the status of the risk model based on the results of the evaluation process, the comprehensive score of the risk model is compared with the preset target score. If the comprehensive score of the risk model is lower than the preset target score, the status of the risk model is first marked, and the mark is not disabled or to be optimized. If the comprehensive score of the risk model is higher than the preset target score, the status of the risk model is second marked, and the mark is normal.
[0097] From the above description, it can be seen that in this embodiment, by introducing the risk model evaluation link and using a multi-dimensional scoring strategy to score the risk model, the effectiveness of the risk model can be quickly obtained to help users decide whether the model needs to be optimized. The effectiveness of the model is judged by multi-dimensional statistical data, so that the effectiveness of the model itself can be supported by data.
[0098] In one embodiment of the present invention, see Figure 6 , generating the risk unit corresponding to each transaction process according to the transaction data recorded in each transaction process, specifically includes the following contents:
[0099] S1011: Determine each source table storing the transaction data and determine target data in each source table;
[0100] In this step, you can select various source tables of transaction data according to risk scenarios or business relationships, and select the data required to configure the risk unit in each source table. The selected data is the target data. For example, select various source tables related to the business, and the data in the source table related to the data required to configure the risk unit is the transaction details table, where the transaction details table includes: date, amount, transaction party and transaction institution, etc.
[0101] Furthermore, the usage data range of the target data is configured, for example, the date range, the amount range, who the transaction party must be, etc.
[0102] S1012: configuring a regular expression corresponding to each field in each of the target data and an operation logic between each regular expression;
[0103] In this step, filter rules are configured to set conditions for the attributes of interest. For example, conditions are set for the attributes of interest (such as amount, transaction date, transaction institution).
[0104] Set filtering rules for specific fields in the source table to generate multiple rule expressions.
[0105] For example, if three concerned attributes are set as conditions in source table 1 and two concerned attributes are set as conditions in source table 2, then one rule expression is set for each condition. Using source table 1 and source table 2, five rule expressions are generated.
[0106] S1013: Fit the association relationship between the source tables and configure the operation logic between the source tables to obtain the risk unit.
[0107] In this step, the operation logic between each expression is determined according to the regular expression generated in the previous step.
[0108] Associate the key fields of two or more source tables, establish connections between multiple tables, generate multiple association expressions, and unify multiple tables.
[0109] When establishing a connection between multiple tables, the relationship between any two tables is obtained based on the same fields in the two tables. The generated association expressions are configured to obtain the operation logic between the expressions.
[0110] The operation logic includes at least one of AND logic, OR logic, NOT logic and priority logic.
[0111] It should be noted that each sub-model or main model in each risk model has the same model configuration steps.
[0112] From the above description, it can be seen that the embodiments of the present invention can realize multi-channel and multi-type data access, realize rapid expansion of risk monitoring scenarios, and enhance the ability to convert risk scenarios into model configurations.
[0113] The present invention provides an embodiment of a transaction risk prediction system, see Figure 7 , specifically including: a risk model matching device 1, an application calculation device 2, a risk early warning device 3 and a risk model scoring device 4.
[0114] The risk model configuration device 1 is responsible for providing the configuration of the risk model, so that the user can add, modify, delete and debug the risk model on the visual interface.
[0115] The risk model configuration device 1 provides a series of general model configuration tools to make the model development process visual, easy to operate, and code-free. The risk model represents multiple sub-models and a main model. The relationship between the main model and the sub-model is as follows: Figure 8 As shown in the figure, the structure of multiple sub-models and a single main model can ensure that the risk model has the ability to handle complex risk scenarios. Each main model depends on the operating results of its sub-model. The one-main-multiple-sub-model structure ensures that the risk model has the ability to handle complex risk scenarios. Users can split complex risk scenarios into multiple simple risk scenarios and implement them into single sub-models, and then combine these sub-models into the final result through the main model.
[0116] Through the master-sub mode and the standardized model configuration process, after realizing the visual interface, the user can configure his own risk model according to his needs. When the risk model is configured, it enters the application calculation device 2.
[0117] The application computing device 2 is responsible for accessing the data set required for the operation of the risk model and regularly operating the risk model.
[0118] like Fig. 9 As shown, the application computing device 2 synchronizes the data required for the risk model operation from the upstream system through a big data system (such as GreenPlum), and the batch scheduling (such as Control-M) periodically generates tasks to execute the user-configured risk model and output the risk prediction results.
[0119] The risk warning device 3 is responsible for sending the risk prediction results generated by the risk model to the processing party or processing terminal, and providing a complete disposal process to track and manage the warning.
[0120] The risk warning device 3 corrects the risk prediction results generated by the risk model, screens out the transactions that are really risky and tracks them, see Fig.10 The specific rectification process is as follows:
[0121] S1: Perform operations on warnings;
[0122] In this step, the operation on the early warning is to start judging or checking the risk prediction results.
[0123] S2: Determine whether the warning is effective;
[0124] In this step, judging whether the warning is effective refers to whether the risk model outputs the risk prediction result. If so, execute S3, otherwise end.
[0125] S3: Generate questions;
[0126] In this step, generating a problem means that the risk model outputs a risk prediction result.
[0127] S4: Whether rectification is needed;
[0128] The risk prediction results are traversed to determine whether they need to be modified. If they need to be modified, it indicates that they are not interference results, and the process proceeds to step S5. If they do not need to be modified, the process ends.
[0129] S5: Correction tracking;
[0130] Make corrections to risk prediction results.
[0131] S6: Whether rectification has been completed;
[0132] If the rectification of the risk prediction results is completed, the process ends; if the rectification of the risk prediction results is not completed, step S5 is executed.
[0133] The risk model scoring device 4 is responsible for collecting multi-dimensional risk prediction results and scoring the model based on the risk prediction results.
[0134] The risk model scoring device 4 scores the risk model based on the data generated by the risk warning device 3. The evaluation dimensions mainly include: model running time, total number of warnings generated, number of effective warnings, number of generated problems, and number of problems that need to be rectified.
[0135] The embodiment of the present invention provides a specific implementation of a transaction risk prediction device that can implement all the contents of the transaction risk prediction method, see Fig.11 The transaction risk prediction device specifically includes the following contents:
[0136] The sub-unit module 10 is used to generate risk units corresponding to each transaction process according to the transaction data recorded in each transaction process;
[0137] A risk model module 20, used to determine a target transaction process in a risk scenario, and to construct a risk model based on risk units corresponding to the target transaction process;
[0138] The risk prediction module 30 is used to perform risk prediction on target transaction data in the risk scenario based on the risk model to obtain a risk prediction result.
[0139] Furthermore, it also includes:
[0140] A display configuration module 40, for generating a display template corresponding to the risk prediction according to a preset display field;
[0141] The visualization module 50 is used to configure various fields of the risk prediction result in the display template and perform visualization processing on the display template.
[0142] Furthermore, it also includes:
[0143] A screening module 60 is used to screen the risk prediction results so as to remove interference results in the risk prediction results and obtain screening results;
[0144] The review module 70 is used to review the risk prediction based on the screening results.
[0145] Furthermore, it also includes:
[0146] An evaluation module 80, used to evaluate the risk model according to the screening result;
[0147] The marking module 90 is used to mark the status of the risk model based on the result of the evaluation process.
[0148] The embodiment of the transaction risk prediction device provided by the present invention can be specifically used to execute the processing flow of the embodiment of the transaction risk prediction method in the above embodiment. Its functions are not repeated here, and reference can be made to the detailed description of the above method embodiment.
[0149] From the above description, it can be seen that the transaction risk prediction device provided in the embodiment of the present invention generates risk units corresponding to each transaction process according to the transaction data recorded in each transaction process; determines the target transaction process in the risk scenario, constructs a risk model based on the risk units corresponding to the target transaction process, and predicts the risk of the target transaction data in the risk scenario based on the risk model to obtain a risk prediction result, thereby realizing customization of the risk model in a configuration-based manner, and quickly converting the risk scenario into a risk model, which can greatly shorten the vacuum period from the discovery of a risk scenario to the use of the corresponding risk model.
[0150] The present application provides an embodiment of an electronic device for implementing all or part of the content of the transaction risk prediction method. The electronic device specifically includes the following content:
[0151] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between related devices; the electronic device can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the electronic device can be implemented with reference to the embodiment of the method for realizing the prediction of transaction risk and the embodiment of the device for realizing the prediction of transaction risk, the contents of which are incorporated herein and the repeated parts are not repeated.
[0152] Fig.12 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig.12 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig.12 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.
[0153] In one embodiment, the transaction risk prediction function may be integrated into the central processor 9100. The central processor 9100 may be configured to perform the following control:
[0154] Generate risk units corresponding to each transaction process based on the transaction data recorded in each transaction process; determine the target transaction process in the risk scenario, construct a risk model based on the risk units corresponding to the target transaction process, and perform risk prediction on the target transaction data in the risk scenario based on the risk model to obtain a risk prediction result.
[0155] From the above description, it can be seen that the electronic device provided in the embodiment of the present application generates risk units corresponding to each transaction process according to the transaction data recorded in each transaction process; determines the target transaction process in the risk scenario, constructs a risk model based on the risk units corresponding to the target transaction process, and performs risk prediction on the target transaction data in the risk scenario based on the risk model to obtain a risk prediction result, thereby realizing customization of the risk model in a configuration-based manner, and quickly converting the risk scenario into a risk model, which can greatly shorten the vacuum period from the discovery of a risk scenario to the commissioning of the corresponding risk model.
[0156] In another embodiment, the transaction risk prediction device may be configured separately from the central processor 9100. For example, the transaction risk prediction device may be configured as a chip connected to the central processor 9100, and the transaction risk prediction function may be implemented through the control of the central processor.
[0157] like Fig.12 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig.12 In addition, the electronic device 9600 may also include Fig.12 For components not shown, reference may be made to the prior art.
[0158] like Fig.12 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600.
[0159] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.
[0160] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.
[0161] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.
[0162] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).
[0163] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.
[0164] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.
[0165] The embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps in the method for predicting transaction risks in the above embodiment. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, all the steps in the method for predicting transaction risks in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:
[0166] Generate risk units corresponding to each transaction process based on the transaction data recorded in each transaction process; determine the target transaction process in the risk scenario, construct a risk model based on the risk units corresponding to the target transaction process, and perform risk prediction on the target transaction data in the risk scenario based on the risk model to obtain a risk prediction result.
[0167] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present invention generates risk units corresponding to each transaction process according to the transaction data recorded in each transaction process; determines the target transaction process in the risk scenario, constructs a risk model based on the risk units corresponding to the target transaction process, and performs risk prediction on the target transaction data in the risk scenario based on the risk model to obtain a risk prediction result, thereby realizing customization of the risk model in a configuration-based manner, and quickly converting the risk scenario into a risk model, which can greatly shorten the vacuum period from the discovery of a risk scenario to the use of the corresponding risk model.
[0168] Although the present invention provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiments is only one way of executing the order of many steps and does not represent the only execution order. When the actual device or client product is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, in a parallel processor or multi-threaded processing environment).
[0169] It should be understood by those skilled in the art that the embodiments of this specification may be provided as methods, devices (systems) or computer program products. Therefore, the embodiments of this specification may take the form of complete hardware embodiments, complete software embodiments or embodiments combining software and hardware. Moreover, 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 disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0170] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, 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 flowchart and / or block diagram. 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.
[0171] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate 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 A function specified in one or more boxes.
[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0173] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that there is any such actual relationship or order between these entities or operations. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention is not limited to any single aspect, nor is it limited to any single embodiment, nor is it limited to any combination and / or permutation of these aspects and / or embodiments. Moreover, each aspect and / or embodiment of the present invention can be used alone or in combination with one or more other aspects and / or embodiments thereof.
[0174] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.
Claims
1. A method for predicting transaction risk, characterized in that: include: Generate risk units corresponding to each transaction process according to the transaction data recorded in each transaction process; Determine a target transaction process in a risk scenario, and construct a risk model based on risk units corresponding to the target transaction process; Based on the risk model, risk prediction is performed on the target transaction data in the risk scenario to obtain a risk prediction result; The generating of risk units corresponding to each transaction process according to the transaction data recorded in each transaction process includes: Determine each source table storing the transaction data and determine target data in each source table; Configure the regular expressions corresponding to the fields in each of the target data and the operation logic between the regular expressions; Fit the associations between the source tables and configure the operation logic between the source tables to obtain the risk unit; The fitting of the association relationship between the source tables includes: associating key fields of two or more source tables, establishing a connection between multiple source tables, generating multiple association expressions, and realizing the connection between multiple source tables.
2. The method for predicting transaction risk according to claim 1, characterized in that: After performing risk prediction on the target transaction data in the risk scenario based on the risk model, the method further includes: Generate a display template corresponding to the risk prediction according to the preset display fields; The various fields of the risk prediction results are configured in the display template, and the display template is visualized.
3. The method for predicting transaction risk according to claim 1, characterized in that: After performing risk prediction on the target transaction data in the risk scenario based on the risk model, the method further includes: Screening the risk prediction results to eliminate interference results in the risk prediction results and obtain screening results; A review process for risk prediction is performed based on the screening results.
4. The method for predicting transaction risk according to claim 3, characterized in that: The screening process of the risk prediction results includes: Obtaining interference results of each elimination; forming an interference result set according to the obtained interference results; Screening out a target risk prediction result that is the same as any interference result in the interference result set from the risk prediction results; The risk prediction results are interference results in the risk prediction results to be eliminated.
5. The method for predicting transaction risk according to claim 3, characterized in that: After the risk prediction results are screened, the method further includes: Evaluating the risk model according to the screening result; A status of the risk model is marked based on the results of the evaluation process.
6. The method for predicting transaction risk according to claim 1, characterized in that: The operation logic includes at least one of AND logic, OR logic, NOT logic and priority logic.
7. The method for predicting transaction risk according to claim 1, characterized in that: The risk model includes: a main model and a sub-model; The prediction result of the output of the sub-model is used as the data input of the main model.
8. A transaction risk prediction device, characterized in that: include: The sub-unit module is used to generate risk units corresponding to each transaction process according to the transaction data recorded in each transaction process; A risk model module, used to determine a target transaction process in a risk scenario, and to construct a risk model based on risk units corresponding to the target transaction process; A risk prediction module, used to perform risk prediction on target transaction data in a risk scenario based on the risk model to obtain a risk prediction result; The subunit module is specifically used for: Determine each source table storing the transaction data and determine target data in each source table; Configure the regular expressions corresponding to the fields in each of the target data and the operation logic between the regular expressions; Fit the associations between the source tables and configure the operation logic between the source tables to obtain the risk unit; The fitting of the association relationship between the source tables includes: associating key fields of two or more source tables, establishing a connection between multiple source tables, generating multiple association expressions, and realizing the connection between multiple source tables.
9. The transaction risk prediction device according to claim 8, characterized in that: Also includes: A display configuration module, used to generate a display template corresponding to the risk prediction according to the preset display fields; The visualization module is used to configure various fields of the risk prediction results in the display template and perform visualization processing on the display template.
10. The transaction risk prediction device according to claim 8, characterized in that: Also includes: A screening module is used to screen the risk prediction results so as to remove interference results in the risk prediction results and obtain screening results; A review module is used to review the risk prediction based on the screening results.
11. The transaction risk prediction device according to claim 10, characterized in that: Also includes: An evaluation module, used for evaluating the risk model according to the screening result; A marking module is used to mark the status of the risk model based on the result of the evaluation process.
12. 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 transaction risk prediction method according to any one of claims 1 to 7 are implemented.
13. 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 for predicting transaction risks described in any one of claims 1 to 7 are implemented.