Method, system and device for determining transaction risk and computer readable storage medium

Abstract

The application provides a transaction risk determination method, system, device and computer readable storage medium, the method comprising: acquiring a transaction voucher image corresponding to a transaction, and determining the type of the transaction; determining a to-be-identified area in the transaction voucher image according to the type; identifying the to-be-identified area to obtain first identification information; and when the first identification information matches preset identification information, determining that the transaction does not have a risk. In the application, the transaction is automatically determined for a risk according to the type of the transaction, manual searching for early warning rules for determining the risk of the transaction is not required, the duration of determining the risk of the transaction is shortened, and the efficiency of determining the risk of the transaction is improved.

Description

Technical Field

[0001] This invention relates to communication technology, and more particularly to a method, system, apparatus, and computer-readable storage medium for determining transaction risk. Background Technology

[0002] In recent years, due to the rapid development of financial business, transaction volume has increased year by year. In order to ensure the security of transactions, it is necessary to conduct risk verification of transactions.

[0003] Currently, transaction risk is determined through manual verification. Financial institution personnel conduct risk checks on transactions using early warning rules. However, different transactions involve different businesses, and different businesses require different early warning rules, resulting in a large number of early warning rules.

[0004] When manually determining the risk of a transaction, it is necessary to find the corresponding warning rule for the current exchange among a large number of trading rules. Finding the warning rule consumes a lot of time, resulting in low efficiency in determining the risk of a transaction. Summary of the Invention

[0005] This invention provides a method, system, apparatus, and computer-readable storage medium for determining transaction risk, in order to solve the problem of low efficiency in determining transaction risk.

[0006] On one hand, the present invention provides a method for determining transaction risk, comprising:

[0007] Obtain the transaction certificate image corresponding to the exchange and determine the type of the transaction;

[0008] The region to be identified in the transaction certificate image is determined according to the type described;

[0009] The region to be identified is identified to obtain first identification information;

[0010] When the first identification information matches the preset identification information, it is determined that the transaction does not pose a risk.

[0011] On the other hand, the step of determining the region to be identified in the transaction certificate image according to the type includes:

[0012] Based on the type, determine the coordinates and coordinate offset of the region to be identified in the transaction voucher image;

[0013] The region to be identified is determined in the transaction certificate image based on the coordinates and the coordinate offset.

[0014] On the other hand, the step of determining the coordinates and coordinate offset of the region to be identified in the transaction certificate image according to the type includes:

[0015] Determine the voucher template image corresponding to the type;

[0016] The coordinates and coordinate offset associated with the voucher template image are determined as the coordinates and coordinate offset of the region to be identified in the transaction voucher image.

[0017] On the other hand, the step of determining the coordinates and coordinate offset of the region to be identified in the transaction certificate image according to the type includes:

[0018] Determine the risk warning level corresponding to the type;

[0019] The coordinates and coordinate offsets associated with the risk warning level are determined as the coordinates and coordinate offsets of the area to be identified in the transaction certificate image.

[0020] On the other hand, after the step of identifying the region to be identified to obtain the first identification information, the method further includes:

[0021] When the first identification information does not match the preset identification information, a prompt message is output, which is used to instruct the information in the area to be identified to be manually compared.

[0022] Obtain the comparison results from manual comparison;

[0023] When the comparison result shows that the information in the area to be identified matches the preset identification information, it is determined that the transaction does not pose a risk.

[0024] On the other hand, after the step of obtaining the comparison results of manual comparison, the method further includes:

[0025] When the comparison result shows that the first identification information does not match the preset identification information, the risk element corresponding to the first identification information is determined.

[0026] The risk factors are stored to indicate the risks associated with the transaction.

[0027] In another aspect, the present invention also provides a system for determining transaction risk, comprising:

[0028] The acquisition module is used to acquire the transaction certificate image corresponding to the exchange and determine the type of the transaction;

[0029] The determination module is used to determine the region to be identified in the transaction certificate image according to the type;

[0030] The identification module is used to identify the area to be identified to obtain first identification information;

[0031] The determining module is further configured to determine that there is no risk in the transaction when the first identification information matches the preset identification information.

[0032] In another aspect, the present invention also provides a device for determining transaction risk, comprising: a memory and a processor;

[0033] The memory stores computer-executed instructions;

[0034] The processor executes computer execution instructions stored in the memory, causing the processor to perform the transaction risk determination method as described above.

[0035] In another aspect, the present invention also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method for determining transaction risk as described above.

[0036] In another aspect, the present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for determining transaction risk.

[0037] The present invention provides a method, system, apparatus, and computer-readable storage medium for determining transaction risk. It acquires the type corresponding to the transaction certificate image of a transaction, determines the area to be identified in the transaction certificate image according to the type, and identifies the area to be identified to obtain identification information. If the identification information matches preset identification information, it can be determined that there is no risk in the transaction. In this invention, transaction risk is automatically determined based on the transaction type, eliminating the need for manual searching of warning rules, thus shortening the time required for risk determination and improving its efficiency. Attached Figure Description

[0038] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0039] Figure 1 This is a flowchart illustrating the first embodiment of the method for determining transaction risk according to the present invention.

[0040] Figure 2 This is a flowchart illustrating the second embodiment of the method for determining transaction risk according to the present invention.

[0041] Figure 3 This is a flowchart illustrating the third embodiment of the method for determining transaction risk according to the present invention.

[0042] Figure 4 This is a schematic diagram of the transaction risk determination system of the present invention;

[0043] Figure 5 This is a schematic diagram of the modules of the transaction risk determination system of the present invention;

[0044] Figure 6 This is a schematic diagram of the hardware structure of the device for determining transaction risk according to the present invention.

[0045] The accompanying drawings have illustrated specific embodiments of this disclosure, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concepts of this disclosure to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0046] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0047] In recent years, due to the rapid development of financial business, transaction volume has increased year by year. In order to ensure the security of transactions, it is necessary to conduct risk verification of transactions.

[0048] Currently, transaction risk is determined through manual verification. Financial institution personnel conduct risk checks on transactions using early warning rules. However, different transactions involve different businesses, and different businesses require different early warning rules, resulting in a large number of early warning rules.

[0049] The inventors of this patent discovered that when determining the risk of a transaction manually, it is necessary to find the warning rule corresponding to the current transaction from a large number of transaction rules. Searching for the warning rule consumes a lot of time, resulting in low efficiency in determining the risk of a transaction.

[0050] The inventor of this patent therefore conceived of automatically determining the risk of a transaction based on its type, eliminating the need for manual searching of warning rules, thus shortening the time required for risk determination and improving its efficiency.

[0051] The technical solutions of the present invention and how they solve the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0052] Reference Figure 1 , Figure 1This is a first embodiment of the method for determining transaction risk according to the present invention. The method for determining transaction risk includes the following steps:

[0053] Step S101: Obtain the transaction certificate image corresponding to the exchange and determine the type of transaction.

[0054] In this embodiment, the executing entity is the transaction risk determination system. For ease of description, the term "system" will be used to refer to the transaction risk determination system below. The system can be any terminal device with data processing capabilities.

[0055] The system stores data for multiple transactions, each with a corresponding serial number. The system retrieves the serial number to be detected from each serial number; the transaction corresponding to that serial number is the transaction to be detected.

[0056] Each transaction has a corresponding transaction voucher image, which indicates that the transaction is complete. The transaction voucher image includes multiple transaction elements, such as the transaction amount, transaction process, transaction rules, and the identifiers of both parties. The transaction data is associated with a serial number; the system retrieves the transaction data based on the serial number and then extracts the transaction voucher image from the transaction data.

[0057] Different transactions correspond to different business operations, and different business operations have different early warning rules, meaning that different business operations need to verify different risks. Therefore, the system needs to determine the type of transaction, and thus determine which risks the system needs to verify for that transaction.

[0058] Step S102: Determine the region to be identified in the transaction voucher image according to the type.

[0059] The transaction document image has multiple regions, each containing corresponding transaction elements. Different transactions require different transaction elements for risk verification. The system stores the regions associated with each type, and the transaction elements in each region all need to be verified. Therefore, after determining the type, the system retrieves the regions associated with each type, and the regions to be identified within each region. The system can store the information corresponding to the regions and determine the regions to be identified in the transaction document image based on this information. For example, if the information of the region associated with a type is its location, and this location is recorded as the first region in the first row of the image, the system can determine the first region in the first row of the transaction document image as the region to be identified. The system uses this method to determine one or more regions to be identified in the transaction document image.

[0060] Step S103: Identify the region to be identified to obtain first identification information.

[0061] After determining the area to be identified, the system identifies the information within that area to obtain initial identification information. The system can employ OCR (optical character recognition) technology to identify the area to be identified.

[0062] Step S104: When the first identification information matches the preset identification information, it is determined that there is no risk in the transaction.

[0063] Each region to be identified has corresponding preset identification information. After the system obtains the first identification information corresponding to the region to be identified, it compares the first identification information with the preset identification information corresponding to the region to be identified. If the first identification information matches the preset identification information, it can be determined that the first identification information matches the preset identification information, and thus it can be determined that there is no risk in the transaction.

[0064] It should be noted that if there are multiple areas to be identified, the transaction can only be considered risk-free if the first identification information corresponding to each area is consistent with the corresponding preset identification information.

[0065] In this embodiment, the type of the transaction certificate image corresponding to the transaction is obtained, and the area to be identified is determined in the transaction certificate image according to the type. The area to be identified is then identified to obtain identification information. If the identification information matches the preset identification information, it can be determined that there is no risk in the transaction. In this invention, the risk of a transaction is automatically determined by the type of the transaction, eliminating the need for manual searching of warning rules for risk determination, thus shortening the risk determination time and improving the efficiency of risk determination.

[0066] Reference Figure 2 , Figure 2 This is a second embodiment of the method for determining transaction risk of the present invention. Based on the first embodiment, step S102 includes:

[0067] Step S201: Determine the coordinates and coordinate offset of the area to be identified in the transaction voucher image according to the type.

[0068] In this embodiment, the system stores the coordinates and coordinate offsets of the type-associated regions to be identified. The coordinates refer to the coordinates of the regions to be identified in the transaction document image, and the coordinate offsets refer to the coordinate error values ​​of the regions to be identified in the transaction document image.

[0069] In one example, the type is associated with a voucher template image. The voucher template image is an image of the transaction template corresponding to each type of transaction. The transaction template marks the coordinates of the areas where each transaction element is located, along with their corresponding coordinate offsets. The system can associate the voucher template image with these coordinates and offsets. After determining the transaction type, the system determines the voucher template image based on the type, and then obtains the coordinates and coordinate offsets from the voucher template image. In other words, the system determines the voucher template image corresponding to the type, and then uses the coordinates and coordinate offsets associated with the voucher template image to determine the coordinates and coordinate offsets of the area to be identified within the transaction voucher image.

[0070] In another example, different risk warning levels are set for different transactions, with varying risk warning levels. However, the same template is used to fill in the transaction elements for different transactions. Since different risk warning levels require different transaction elements to be verified, the system first determines the transaction elements corresponding to each risk warning level, then obtains the coordinates and offsets of these transaction elements within the template, and thus associates the coordinates and offsets with the risk warning level. The system determines the risk warning level corresponding to the transaction type, and then uses the coordinates and offsets associated with the risk warning level to determine the coordinates and offsets of the area to be identified in the transaction document image.

[0071] It should be noted that the order in which the various regions to be identified are compared differs depending on the risk warning level. Therefore, after determining the risk warning level, the system obtains the comparison order for each region to be identified, and then compares the first identification information of each region with its corresponding preset identification information based on this comparison order.

[0072] Step S202: Determine the region to be identified in the transaction voucher image based on the coordinates and coordinate offset.

[0073] After determining the type of transaction, the system obtains the coordinates and coordinate offset associated with the type, and then determines the area to be identified in the transaction voucher image based on the coordinates and coordinate offset.

[0074] For example, the type-associated coordinates include four coordinates, which correspond to the coordinates of the four corner points of the area to be identified; each coordinate has a corresponding coordinate offset, and the coordinates are corrected based on the coordinate offset to obtain the target coordinates. The system determines the points corresponding to the four target coordinates in the transaction certificate image, and the line connecting each point is the area to be identified.

[0075] It should be noted that the system can first use coordinates to determine the area to be identified. If the first identification information in the area to be identified does not match the preset identification information, the coordinates are corrected by the coordinate offset to obtain the target coordinates. The area to be identified is then determined based on the target coordinates. Finally, the first identification information in the area to be identified is compared with the preset identification information.

[0076] In this embodiment, the system determines the coordinates and coordinate offset of the region to be identified in the transaction voucher image based on the type of transaction, thereby accurately determining the region to be identified in the transaction voucher image based on the coordinates and coordinate offset.

[0077] Reference Figure 3 , Figure 3 This is a third embodiment of the method for determining transaction risk of the present invention. Based on the first or second embodiment, after step S102, it further includes:

[0078] Step S301: When the first identification information does not match the preset identification information, a prompt message is output. The prompt message is used to instruct the information in the area to be identified to be manually compared.

[0079] In this embodiment, if the system determines that the first identification information does not match the preset identification information, it may be due to an error in the system's identification of the information in the area to be identified, which can be verified manually. Therefore, when the system determines that the first identification information does not match the preset identification information, it outputs a prompt message instructing the system to manually compare the information in the area to be identified.

[0080] It should be noted that when there are multiple regions to be identified, the prompt message is used to instruct manual comparison of the information in the region where the first mismatched identification information is located.

[0081] Step S302: Obtain the comparison results of manual comparison.

[0082] The system can directly display transaction voucher images, which are marked with areas requiring manual comparison and will output alarm information. Risk investigators compare the information in the areas to be identified with the corresponding preset identification information and then input the comparison results into the system.

[0083] Step S303: When the comparison result shows that the information in the area to be identified matches the preset identification information, it is determined that there is no risk in the transaction.

[0084] When the comparison result shows that the information in the area to be identified matches the preset identification information, it can be determined that there is no risk in the transaction. If the system determines that multiple pieces of first identification information do not match the corresponding preset identification information, then the transaction can only be determined to be risk-free when the comparison result shows that the information in each area to be identified matches the corresponding preset identification information.

[0085] When the comparison result shows a mismatch between the information in the area to be identified and the preset identification information, risk registration is required. Based on the registered risk, the transaction node is rectified. Specifically, when the comparison result shows a mismatch between the information in the area to be identified and the preset identification information, the system identifies and stores the risk element corresponding to the first identification information. This risk element indicates the risk issues present in the transaction. By identifying these risk issues, the transaction process can be optimized to avoid such risks.

[0086] In this embodiment, when the system determines that the first identification information does not match the preset identification information, it performs manual verification of the information in the area to be identified, thereby avoiding misjudgment due to identification errors.

[0087] Reference Figure 4 The system consists of a web server 100, an application server 200, a file server 300, and a database server 400. The web server is responsible for parameter management and risk handling, specifically including business functions such as template configuration, rule configuration, manual verification, and problem rectification. Template configuration refers to transaction templates, rule configuration refers to configuring rule tables, which include preset identification information, manual verification refers to the aforementioned manual comparison, and problem rectification refers to the storage of risk factors and the optimization of transaction nodes based on risk factors.

[0088] The functions of the application server 200 include transaction type identification and intelligent comparison.

[0089] File server 300 is responsible for storing transaction certificate images.

[0090] Database server 400 is responsible for storing transaction templates, rule tables, early warning tables, and voucher index tables. Among them, the early warning table is set with a unique serial number (transaction date + log number), which can be associated with transaction templates, rule tables, voucher index tables, etc. to assist in verification, and intelligently verify business elements such as account, amount, and document type step by step.

[0091] Application server 200 obtains risky transactions based on the early warning table, matches the transaction serial number in the early warning table with the voucher index in the voucher index table, and then downloads the transaction voucher image associated with the voucher index from file server 300. It obtains the coordinates and coordinate offsets of the business elements in the area to be identified from the transaction template and rule table in the early warning table, and then determines the area to be identified from the transaction voucher image based on the coordinates and coordinate offsets. Finally, it automatically compares the business elements identified in the area to be identified (first identification information) with the business elements in the early warning table (preset identification information).

[0092] This invention also provides a system for determining transaction risk, referring to... Figure 5 The 500 system for determining transaction risk includes:

[0093] The acquisition module 510 is used to acquire the transaction certificate image corresponding to the exchange and determine the type of transaction;

[0094] The determination module 520 is used to determine the region to be identified in the transaction document image according to the type;

[0095] The recognition module 530 is used to recognize the area to be recognized and obtain first recognition information;

[0096] The determination module 520 is used to determine that there is no risk in the transaction when the first identification information matches the preset identification information.

[0097] In one embodiment, the transaction risk determination system 500 includes:

[0098] The determination module 520 is used to determine the coordinates and coordinate offset of the area to be identified in the transaction voucher image according to the type.

[0099] The determination module 520 is used to determine the region to be identified in the transaction certificate image based on the coordinates and coordinate offset.

[0100] In one embodiment, the transaction risk determination system 500 includes:

[0101] Module 520 is used to determine the voucher template image corresponding to the type;

[0102] The determination module 520 is used to determine the coordinates and coordinate offsets associated with the voucher template image as the coordinates and coordinate offsets of the area to be identified in the transaction voucher image.

[0103] In one embodiment, the transaction risk determination system 500 includes:

[0104] Module 520 is used to determine the risk warning level corresponding to the type.

[0105] The determination module 520 is used to determine the coordinates and coordinate offsets associated with the risk warning level as the coordinates and coordinate offsets of the area to be identified in the transaction certificate image.

[0106] In one embodiment, the transaction risk determination system 500 includes:

[0107] The output module is used to output a prompt message when the first identification information does not match the preset identification information. The prompt message is used to instruct the information in the area to be identified to be manually compared.

[0108] The acquisition module 510 is used to acquire the comparison results of manual comparison;

[0109] The determination module 520 is used to determine that there is no risk in the transaction when the comparison result shows that the information in the area to be identified matches the preset identification information.

[0110] In one embodiment, the transaction risk determination system 500 includes:

[0111] The determination module 520 is used to determine the risk element corresponding to the first identification information when the comparison result shows that the first identification information does not match the preset identification information;

[0112] The storage module stores risk factors, which indicate the risks associated with a transaction.

[0113] Figure 6 This is a hardware structure diagram of a device for determining transaction risk according to an exemplary embodiment.

[0114] The transaction risk determination device 600 may include: a processor 601, such as a CPU, a memory 602, and a transceiver 603. Those skilled in the art will understand that... Figure 6 The structure shown does not constitute a limitation on the means of determining transaction risk and may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. Memory 602 may be implemented by any type of volatile or non-volatile storage device or combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0115] The processor 601 can call the computer program stored in the memory 602 to complete all or part of the steps of the above-described method for determining transaction risk.

[0116] Transceiver 603 is used to receive information sent by external devices and to send information to external devices.

[0117] A non-transitory computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor of a transaction risk determination device, the transaction risk determination device is able to perform the aforementioned transaction risk determination method.

[0118] A computer program product includes a computer program that, when executed by a processor of a transaction risk determination device, enables the transaction risk determination device to perform the aforementioned transaction risk determination method.

[0119] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0120] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for determining transaction risk, characterized in that, include: Obtain the transaction voucher image corresponding to the exchange and determine the type of the transaction. The transaction voucher image includes multiple transaction elements, including transaction amount, transaction process, transaction rules, and identifiers of the two parties to the transaction. The type refers to the type of business. The risk warning level corresponding to the type of transaction is determined, and the coordinates and coordinate offsets associated with the risk warning level corresponding to the type of transaction are determined as the coordinates and coordinate offsets of the area to be identified in the transaction voucher image. Before determining the coordinates and coordinate offsets, the method further includes: determining the transaction element corresponding to the risk warning level, obtaining the coordinates and coordinate offsets of the transaction element in the transaction template, and associating the coordinates and coordinate offsets with the risk warning level. The transaction template marks the coordinates of the area where each transaction element is located and the corresponding coordinate offsets. Different transactions use the same transaction template to fill in the transaction elements. The coordinates are used to determine the region to be identified, and the region to be identified is then identified to obtain first identification information; If the first identification information in the area to be identified does not match the preset identification information corresponding to the area to be identified, the coordinates are corrected by the coordinate offset to obtain the target coordinates, the area to be identified is re-determined based on the target coordinates, and the first identification information of the new area to be identified is compared with the preset identification information. When the new first identification information matches the preset identification information, it is determined that the transaction does not pose a risk.

2. The method for determining transaction risk according to claim 1, characterized in that, After the step of identifying the region to be identified to obtain the first identification information, the method further includes: When the first identification information does not match the preset identification information, a prompt message is output, which is used to instruct the information in the area to be identified to be manually compared. Obtain the comparison results from manual comparison; When the comparison result shows that the information in the area to be identified matches the preset identification information, it is determined that the transaction does not pose a risk.

3. The method for determining transaction risk according to claim 2, characterized in that, After the step of obtaining the comparison results from manual comparison, the method further includes: When the comparison result shows that the first identification information does not match the preset identification information, the risk element corresponding to the first identification information is determined. The risk factors are stored to indicate the risks associated with the transaction.

4. A system for determining transaction risk, characterized in that, include: The acquisition module is used to acquire the transaction voucher image corresponding to the exchange and determine the type of the transaction. The transaction voucher image includes multiple transaction elements, including transaction amount, transaction process, transaction rules, and identifiers of the two parties to the transaction. The type refers to the type of business. The determination module is used to determine the risk warning level corresponding to the type of transaction, thereby determining the coordinates and coordinate offsets associated with the risk warning level corresponding to the type of transaction as the coordinates and coordinate offsets of the area to be identified in the transaction voucher image. Before determining the coordinates and coordinate offsets, the module further includes: determining the transaction elements corresponding to the risk warning level, obtaining the coordinates and coordinate offsets of the transaction elements in the transaction template, thereby associating the coordinates and coordinate offsets with the risk warning level. The transaction template marks the coordinates of the area where each transaction element is located and the corresponding coordinate offsets. Different transactions use the same transaction template to fill in the transaction elements. The identification module is used to determine the region to be identified using coordinates and to identify the region to be identified to obtain first identification information; if the first identification information in the region to be identified does not match the preset identification information, the coordinates are corrected using coordinate offset to obtain target coordinates, the region to be identified is re-determined based on the target coordinates, and the first identification information of the new region to be identified is compared with the preset identification information. The determining module is further configured to determine that there is no risk in the transaction when the new first identification information matches the preset identification information.

5. A device for determining transaction risk, characterized in that, include: Memory and processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method for determining transaction risk as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method for determining transaction risk as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method for determining transaction risk as described in any one of claims 1-3.

Images