An intelligent anti-fraud method, system, device and medium based on a decision engine

Abstract

The present application relates to an intelligent anti-fraud method, system, device and medium based on a decision engine. The method includes: obtaining external warning clues, importing the external warning clues into the decision engine, screening the external warning clues through the decision engine, and classifying the clues suspected of fraud in the external warning clues; then, inputting the classified clues into the corresponding sub-decision engines for processing according to different fraud types, and setting labels for the classified clues according to the processing conditions; finally, judging whether the current clue contains fraudulent behavior according to the label, and making corresponding decisions according to different situations. Through the present application, the problems of high labor cost and high case incidence in the actual dissuasion process for different fraud types are solved, the dissuasion success rate of the decision engine is improved, the case incidence is reduced, and the labor cost is reduced.

Description

Technical Field

[0001] The present application relates to the field of information security technology, and in particular, to an intelligent anti-fraud method, system, device and medium based on a decision engine. Background Art

[0002] With the rapid development of information technology, new types of telecommunications network fraud crimes occur frequently at present. Fraud gangs continuously update their fraud methods and use various cross-platform tools such as telephones, text messages, website addresses, mobile phone apps or instant messaging software to conduct synthetic fraud, which has brought great harm to society.

[0003] At present, most anti-fraud dissuasions still rely on the manual intervention of police officers. Not only is the labor cost high, but also in the face of the increasing early warning data, the manpower of police officers is insufficient, and there is a high probability of untimely processing.

[0004] At present, in the related technology, in the actual dissuasion process for different types of fraud, there are problems of high labor cost and high incidence rate, and no effective solution has been proposed yet. Summary of the Invention

[0005] Embodiments of the present application provide an intelligent anti-fraud method, system, device and medium based on a decision engine to at least solve the problems of high labor cost and high incidence rate in the actual dissuasion process for different types of fraud in the related technology.

[0006] In a first aspect, embodiments of the present application provide an intelligent anti-fraud method based on a decision engine, and the method includes:

[0007] Obtain external early warning clues, import the external early warning clues into a decision engine, screen the external early warning clues through the decision engine, and classify the clues suspected of fraud in the external early warning clues;

[0008] Input the classified clues into corresponding sub-decision engines for processing according to different fraud types, and set labels for the classified clues according to the processing conditions;

[0009] Judge whether the current clue contains fraudulent behavior according to the label, and make corresponding decisions according to different situations.

[0010] In some of the embodiments, inputting the classified clues into corresponding sub-decision engines for processing according to different fraud types, and setting labels for the classified clues according to the processing conditions includes:

[0011] Make an AI outbound call according to the classified clues and judge the call status;

[0012] When the call is not connected, send anti-fraud text messages for warning and initiate multiple AI outbound calls within a preset time;

[0013] When the call is connected, judge the duration of the AI outbound call. If the duration is less than the first preset duration, continue to initiate the AI outbound call. If the duration is greater than the second preset duration, judge and set the label of the classified lead.

[0014] In some embodiments, judging and setting the label of the classified lead includes:

[0015] When it is judged that there is a high-risk behavior in the AI outbound call, set the label as a high-risk label, otherwise as a low-risk label.

[0016] In some embodiments, judging whether the current lead contains fraud according to the label and making corresponding decisions according to different situations includes:

[0017] If the label of the current lead is the high-risk label, it is considered that the current lead contains fraud, and the current lead needs to be assigned to a specific acceptance point for manual handling;

[0018] If the label of the current lead is the low-risk label, automatically close the case.

[0019] In a second aspect, an embodiment of the present application provides an intelligent anti-fraud system based on a decision engine, and the system includes:

[0020] An acquisition classification module, configured to acquire external warning leads and import the external warning leads into the decision engine, screen the external warning leads through the decision engine, and classify the leads suspected of fraud in the external warning leads;

[0021] A processing module, configured to input the classified leads into corresponding sub-decision engines for processing according to different fraud types, and set labels for the classified leads according to the processing conditions;

[0022] A decision module, configured to judge whether the current lead contains fraud according to the label and make corresponding decisions according to different situations.

[0023] In some embodiments, the processing module is further configured to make an AI outbound call according to the classified lead and judge the call status.

[0024] When the call is not connected, send anti-fraud text messages for warning and initiate multiple AI outbound calls within a preset time.

[0025] When the call has been connected, determine the duration of the AI outbound call. If the duration is less than the first preset duration, continue to initiate the AI outbound call. If the duration is greater than the second preset duration, then determine and set the label of the classified lead.

[0026] In some embodiments, the processing module is further configured to, when it is determined that there is a high-risk behavior in the AI outbound call, set the label to a high-risk label, otherwise a low-risk label.

[0027] In some embodiments, the decision-making module is further configured to, if the label of the current lead is the high-risk label, then consider that the current lead contains fraud behavior, and it is necessary to assign the current lead to a specific acceptance point for manual handling;

[0028] If the label of the current lead is the low-risk label, automatically close the case.

[0029] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the intelligent anti-fraud method based on a decision engine as described in the first aspect above is implemented.

[0030] In a fourth aspect, an embodiment of the present application provides a storage medium, on which a computer program is stored. When the program is executed by a processor, the intelligent anti-fraud method based on a decision engine as described in the first aspect above is implemented.

[0031] Compared with the related art, the intelligent anti-fraud method based on a decision engine provided by the embodiments of the present application obtains external early warning leads, imports the external early warning leads into the decision engine, screens the external early warning leads through the decision engine, and classifies the leads suspected of fraud in the external early warning leads; then, inputs the classified leads into the corresponding sub-decision engines for processing according to different fraud types, and sets labels for the classified leads according to the processing situation; finally, determines whether the current lead contains fraud behavior according to the label, and makes corresponding decisions according to different situations.

[0032] In the actual dissuasion process of different fraud types in the present application, through the patrol method, the decision engine is gradually optimized, and the disposal methods of different fraud types are accumulated, so as to gradually improve the dissuasion success rate of the decision engine, reduce the case incidence rate, and reduce the labor cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0034] Figure 1 It is a schematic diagram of the application environment of the intelligent anti-fraud method based on a decision engine according to an embodiment of the present application;

[0035] Figure 2 It is a flowchart of the intelligent anti-fraud method based on a decision engine according to an embodiment of the present application;

[0036] Figure 3 It is a schematic diagram of the intelligent anti-fraud operation process based on a decision engine according to an embodiment of the present application;

[0037] Figure 4 It is a block diagram of the structure of the intelligent anti-fraud system based on a decision engine according to an embodiment of the present application;

[0038] Figure 5 It is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0039] In order to make the purpose, technical solutions and advantages of the present application clearer and more understandable, the present application will be described and explained below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments provided in the present application without creative efforts belong to the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some designs, manufacturing or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be understood as the content disclosed in the present application being insufficient.

[0040] Referring to "embodiment" in the present application means that the specific features, structures or characteristics described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those of ordinary skill in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0041] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the ordinary meanings understood by those with ordinary skills in the technical field to which this application belongs. The words such as "a", "an", "one kind", "the" and the like involved in this application do not indicate a quantity limitation and may represent a singular or plural number. The terms "include", "comprise", "have" and any variations thereof involved in this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include steps or units not listed, or may further include other steps or units inherent to these processes, methods, products or devices. The similar words such as "connect", "be connected", "couple" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application means greater than or equal to two. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may represent: A exists alone, A and B exist simultaneously, and B exists alone. The terms "first", "second", "third" and the like involved in this application are only used to distinguish similar objects and do not represent a specific order of the objects.

[0042] The intelligent anti-fraud method based on a decision engine provided by this application can be applied to an application environment as Figure 1 shown. Figure 1 FIG. is a schematic diagram of the application environment of the intelligent anti-fraud method based on a decision engine according to an embodiment of this application, as Figure 1 shown. Among them, the terminal 11 communicates with the server 10 through a network. The server 10 obtains external warning clues, imports the external warning clues into the decision engine, screens the external warning clues through the decision engine, and classifies the clues suspected of fraud in the external warning clues; then, inputs the classified clues into the corresponding sub-decision engines for processing according to different fraud types, and sets labels for the classified clues according to the processing conditions; finally, determines whether the current clue contains fraudulent behavior according to the label, and makes corresponding decisions according to different situations and sends them to the terminal 11. Among them, the terminal 11 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers and portable wearable devices, and the server 10 can be implemented by an independent server or a server cluster composed of multiple servers.

[0043] This embodiment provides an intelligent anti-fraud method based on a decision engine. Figure 2 FIG. is a flowchart of the intelligent anti-fraud method based on a decision engine according to an embodiment of this application, as Figure 2 shown, and the process includes the following steps:

[0044] Step S201: Obtain external warning clues, import the external warning clues into the decision engine, filter the external warning clues through the decision engine, and classify the clues suspected of fraud in the external warning clues.

[0045] Figure 3 It is a schematic diagram of the intelligent anti-fraud operation process based on the decision engine according to an embodiment of the present application. As Figure 3 shown, the server 10 obtains external warning clues, imports the external warning clues into the anti-fraud general decision engine, filters the external warning clues through the decision engine, and classifies the clues suspected of fraud screened out in the external warning clues. Among them, common fraud types include online loans, brush order part-time jobs, blind date and making friends, impersonating public security, procuratorial and judicial organs, online gambling, impersonating customer service, etc.

[0046] It should be noted that the external warning clues in this embodiment include suspected fraud terms, scripts, etc.

[0047] Step S202: Input the classified clues into the corresponding sub-decision engines for processing according to different fraud types, and set labels for the classified clues according to the processing situation.

[0048] As Figure 3 shown, input the classified clues in step S201 into the corresponding sub-decision engines for processing according to the above different fraud types. Among them, the sub-decision engines include: loan fraud decision engine, brush order fraud decision engine, blind date and making friends fraud decision engine, etc.

[0049] The specific processing process is as follows:

[0050] Make an AI outbound call according to the classified clues and judge the call status. The call status includes unanswered, rejected, busy, powered off, and connected, etc.

[0051] In the case that the call is not connected, this embodiment will send an anti-fraud text message to the user to warn the user of the possible fraud risks, and initiate multiple AI outbound calls within a preset time. For example, initiate multiple AI outbound calls at a preset delay of 5 minutes. Among them, the anti-fraud text message contains a promotional link that allows the user to view cases of similar fraud types.

[0052] In the case that the call has been connected, judge the duration of the AI outbound call. If the call duration is less than the first preset duration, for example, 10 seconds, it means that the user hung up immediately after answering, and an AI outbound call needs to be initiated again. If the call duration is greater than the second preset duration, the call label needs to be judged.

[0053] Preferably, when it is determined that there are high-risk behaviors in the above AI outbound calls, for example, the call tags include: money has been transferred, about to transfer money, etc., the current tag can be set as a high-risk tag. When it is determined that there is no fraud behavior in the above AI outbound calls, the current tag is set as a low-risk tag.

[0054] Further, after the above decision engine finishes processing, the classified leads are tagged according to the processing situation. For example, when the user does not answer the fraud call, an anti-fraud text message is sent to the user's mobile phone in a timely manner. The user gets a warning through the text message and reports to the police or blocks the fraud call in a timely manner. Then the tags are set as: successful publicity, accurate early warning, reported to the police, manual anti-fraud prevention, low-risk, etc. On the contrary, if the user answers the fraud call and is deceived, or has transferred money, the tags are set as: deceived without reporting to the police, high-risk, etc. In addition, the fraud methods and groups can also be tagged, for example, elderly groups, high-risk groups, pig butchering scams, investment and financial management, impersonating leaders, game fraud, false gambling, false credit investigation, email fraud, online gambling, credit card fraud, etc.;

[0055] Step S203, determine whether the current lead contains fraud behavior according to the tag, and make corresponding decisions according to different situations.

[0056] As Figure 3 shown, if the tag of the current lead is a high-risk tag, it is considered that the current lead contains fraud behavior, and the current lead needs to be assigned to a specific acceptance point (such as a **police station) for manual handling;

[0057] If the tag of the current lead is a low-risk tag, it is automatically closed.

[0058] Through the above steps S201 to S203, in the actual dissuasion process of different fraud types in this embodiment, the decision engine is gradually optimized by means of patrol inspection, and the disposal methods of different fraud types are accumulated, so as to gradually improve the dissuasion success rate of the decision engine, reduce the incidence rate of cases, and reduce labor costs.

[0059] To facilitate understanding of the above technical solutions of the present application, the following will describe the present application in detail through a specific usage process.

[0060] First, obtain external early warning leads and import the external early warning leads into the decision engine. The decision engine screens the external early warning leads and classifies the leads suspected of fraud in the external early warning leads;

[0061] Next, the classified leads are input into the corresponding sub-decision engines for processing according to different fraud types.

[0062] For example, if the lead is a loan fraud call, it will first determine whether the current number has been intercepted. Among them, the specific interception rules can be customized, for example, whether it has been dialed today, etc.

[0063] If it is intercepted, the current lead ends, the lead label is set to the specific interception reason, and the processing of the current lead ends. If it is not intercepted, an intelligent call needs to be initiated, and a flash message is sent simultaneously to remind the user to be vigilant against fraud.

[0064] If the call is unsuccessful and the call status is: invalid number, turned off, out of service, rejected, unanswered, unable to connect, busy, then the corresponding call status is added to the lead label. For call statuses that are not invalid numbers and unanswered, set the corresponding second call interval, such as setting to initiate the call again after 10 minutes.

[0065] For successful calls, if the call label contains accurate early warning, then mark the current lead as accurate early warning. If it does not contain accurate early warning, then mark the current lead as invalid early warning.

[0066] If it is not connected after two calls, a text message reminder is sent to remind the user that they may be being scammed.

[0067] If the early warning level of the current lead is high risk, the lead status needs to be notified to the police, and the on-duty police officer needs to conduct manual follow-up and intervention.

[0068] In addition, there are other types of fraud. According to different types of fraud, specific processing can be carried out in different sub-decision engines, and the processing process can be customized by the user without specific limitations.

[0069] It should be noted that the steps shown in the above process or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0070] This embodiment also provides an intelligent anti-fraud system based on a decision engine. This system is used to implement the above embodiments and preferred implementation manners, and those that have been described will not be repeated. As used below, terms such as "module", "unit", "sub-unit", etc. can be a combination of software and / or hardware that can achieve a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0071] Figure 4 is a structural block diagram of an intelligent anti-fraud system based on a decision engine according to an embodiment of the present application, as Figure 4As shown in the figure, the system includes an acquisition and classification module 41, a processing module 42, and a decision-making module 43:

[0072] The acquisition and classification module 41 is used to acquire external warning clues, import the external warning clues into the decision-making engine, screen the external warning clues through the decision-making engine, and classify the clues suspected of fraud in the external warning clues; the processing module 42 is used to input the classified clues into the corresponding sub-decision-making engines for processing according to different fraud types, and set labels for the classified clues according to the processing conditions; the decision-making module 43 is used to judge whether the current clue contains fraudulent behavior according to the label, and make corresponding decisions according to different situations.

[0073] Through the above system, in the actual dissuasion process of different fraud types in this embodiment, by means of patrol inspection, the decision-making engine is gradually optimized, and the disposal methods of different fraud types are accumulated, so as to gradually improve the dissuasion success rate of the decision-making engine, reduce the case incidence rate, and reduce the labor cost.

[0074] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation manners, and will not be repeated here.

[0075] In addition, it should be noted that the above-mentioned each module can be a functional module or a program module, and can be implemented either by software or by hardware. For the modules implemented by hardware, the above-mentioned each module can be located in the same processor; or the above-mentioned each module can also be located in different processors in any combination form.

[0076] This embodiment also provides an electronic device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0077] Optionally, the above-mentioned electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above-mentioned processor, and the input / output device is connected to the above-mentioned processor.

[0078] In addition, in combination with the intelligent anti-fraud method based on the decision-making engine in the above embodiments, the embodiments of the present application can be implemented by providing a storage medium. A computer program is stored on the storage medium; when the computer program is executed by a processor, it implements any one of the intelligent anti-fraud methods based on the decision-making engine in the above embodiments.

[0079] In one embodiment, a computer device is provided, and the computer device may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements an intelligent anti-fraud method based on a decision engine. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0080] In one embodiment, Figure 5 is a schematic internal structure diagram of an electronic device according to an embodiment of the present application, as Figure 5 shown, an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as Figure 5 shown. The electronic device includes a processor, a network interface, an internal memory, and a non-volatile memory connected through an internal bus. Among them, the non-volatile memory stores an operating system, a computer program, and a database. The processor is used to provide computing and control capabilities. The network interface is used to communicate with an external terminal through a network connection. The internal memory is used to provide an environment for the operation of the operating system and the computer program. When the computer program is executed by the processor, it implements an intelligent anti-fraud method based on a decision engine. The database is used to store data.

[0081] Those skilled in the art can understand that Figure 5 the structure shown in

[0082] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. This computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0083] Those skilled in the art should understand that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0084] The above embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. An intelligent anti-fraud method based on a decision engine, characterized in that, The method includes: Obtain external warning clues, import the external warning clues into a decision-making engine, screen the external warning clues through the decision-making engine, and classify the clues suspected of fraud in the external warning clues; Input the classified clues into corresponding sub-decision-making engines for processing according to different fraud types, and set labels for the classified clues according to the processing conditions. Among them, the sub-decision-making engines include: loan fraud decision-making engine, brush order fraud decision-making engine, blind date fraud decision-making engine; Input the classified clues into corresponding sub-decision-making engines for processing according to different fraud types, and set labels for the classified clues according to the processing conditions, including: Conduct AI outbound calls according to the classified clues and judge the call status; In the case that the call is not connected, send anti-fraud text messages for warning and initiate multiple AI outbound calls within a preset time; In the case that the call has been connected, judge the duration of the AI outbound call. If the duration is less than the first preset duration, continue to initiate the AI outbound call. If the duration is greater than the second preset duration, judge and set the label of the classified clues; Judge whether the current clue contains fraud behavior according to the label and make corresponding decisions according to different situations, including: if the label of the current clue is a high-risk label, it is considered that the current clue contains fraud behavior, and the current clue needs to be assigned to a specific acceptance point for manual handling; if the label of the current clue is a low-risk label, it is automatically closed.

2. The method according to claim 1, wherein Judge and set the label of the classified clues, including: When it is judged that there is high-risk behavior in the AI outbound call, set the label as a high-risk label, otherwise it is a low-risk label.

3. An intelligent anti-fraud system based on a decision-making engine, characterized in that, The system includes: An acquisition and classification module, used to obtain external warning clues, import the external warning clues into a decision-making engine, screen the external warning clues through the decision-making engine, and classify the clues suspected of fraud in the external warning clues; A processing module, used to input the classified clues into corresponding sub-decision-making engines for processing according to different fraud types, and set labels for the classified clues according to the processing conditions. Among them, the sub-decision-making engines include: loan fraud decision-making engine, brush order fraud decision-making engine, blind date fraud decision-making engine; Input the classified clues into corresponding sub-decision-making engines for processing according to different fraud types, and set labels for the classified clues according to the processing conditions, including: Conduct AI outbound calls according to the classified clues and judge the call status; In the case that the call is not connected, send anti-fraud text messages for warning and initiate multiple AI outbound calls within a preset time; In the case that the call has been connected, judge the duration of the AI outbound call. If the duration is less than the first preset duration, continue to initiate the AI outbound call. If the duration is greater than the second preset duration, judge and set the label of the classified clues; A decision-making module, configured to determine whether the current lead contains fraud based on the label, and make corresponding decisions according to different situations, including: if the label of the current lead is a high-risk label, it is considered that the current lead contains fraud, and then the current lead needs to be assigned to a specific acceptance point for manual handling; if the label of the current lead is a low-risk label, it will be automatically closed.

4. The system according to claim 3, wherein The processing module is further configured to set the label as a high-risk label when it is determined that there is a high-risk behavior in the AI outbound call, otherwise it is a low-risk label.

5. An electronic device, comprising a memory and a processor, characterized in that, A computer program is stored in the memory, and the processor is configured to run the computer program to execute the intelligent anti-fraud method based on the decision engine according to any one of claims 1 to 2.

6. A storage medium, characterized in that, A computer program is stored in the storage medium, wherein the computer program is configured to execute the intelligent anti-fraud method based on the decision engine according to any one of claims 1 to 2 when running.

Images