Risky transaction identification method, device and system

Abstract

The present invention provides a risky transaction identification method, device and system, which belongs to the field of artificial intelligence technology. The risky transaction identification method includes: obtaining current transaction data in a payment request from an acquiring system, and constructing current transaction features according to the current transaction data; inputting the current transaction features into a risky transaction identification model created based on historical transaction features to obtain risky transaction identification results; wherein the risky transaction identification results include risky merchant identification results and risky customer identification results; generating target transaction risk identification results according to the risky merchant identification results and risky customer identification results; and sending the target transaction risk identification results to the acquiring system, so that the acquiring system processes the current transaction according to the target transaction risk identification results. The present invention can effectively improve the efficiency of risky transaction identification and avoidance, and reduce the compliance risk of acquiring institutions.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device and system for identifying risky transactions. Background Art

[0002] The current method of identifying risky transactions is for acquiring institutions to use image processing technology to verify the merchant's business information in the payment request. This method is suitable for solving the access control problem of small and micro merchants under the Internet model and reducing the review and account opening costs of acquiring institutions.

[0003] With the popularization of Internet finance and QR code acquiring, the merchant acquiring costs are getting lower and lower, while the number of merchants, management costs and regulatory costs are also increasing, which in turn increases the compliance risk of acquiring institutions. At present, it is necessary to manually review and analyze the transaction data in the payment request, which is inefficient and has a low recognition rate. Even if the specific risk is located, it is often impossible to avoid and stop the loss in time. In addition, the existing merchant profiling method is that the acquiring institution uses image processing technology to verify the merchant's business information in the payment request, which is suitable for solving the access control problem of small and micro merchants under the Internet model, but cannot solve the transaction risk control problem in the actual operation process. Summary of the invention

[0004] The main purpose of the embodiments of the present invention is to provide a method, device and system for identifying risky transactions, so as to effectively improve the efficiency of identifying and avoiding risky transactions and reduce the compliance risk of acquiring institutions.

[0005] In order to achieve the above object, an embodiment of the present invention provides a risky transaction identification method, comprising:

[0006] Obtain current transaction data in the payment request from the acquiring system, and construct current transaction features based on the current transaction data;

[0007] Input the current transaction features into the risk transaction identification model created based on the historical transaction features to obtain the risk transaction identification results; wherein the risk transaction identification results include the risk merchant identification results and the risk customer identification results;

[0008] Generate target transaction risk identification results based on risk merchant identification results and risk customer identification results;

[0009] The target transaction risk identification result is sent to the acquiring system so that the acquiring system processes the current transaction according to the target transaction risk identification result.

[0010] The embodiment of the present invention further provides a risky transaction identification device, comprising:

[0011] A current transaction feature building module is used to obtain current transaction data in a payment request from an acquiring system and build current transaction features based on the current transaction data;

[0012] A risky transaction identification module is used to input current transaction features into a risky transaction identification model created based on historical transaction features to obtain risky transaction identification results; wherein the risky transaction identification results include risky merchant identification results and risky customer identification results;

[0013] A target transaction risk identification module is used to generate a target transaction risk identification result based on the risk merchant identification result and the risk customer identification result;

[0014] The sending module is used to send the target transaction risk identification result to the acquiring system, so that the acquiring system processes the current transaction according to the target transaction risk identification result.

[0015] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of the risk transaction identification method when executing the computer program.

[0016] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the risky transaction identification method are implemented.

[0017] The embodiment of the present invention further provides a risky transaction identification system, including:

[0018] The risky transaction identification device as described above;

[0019] The acquiring system is used to send a payment request to a risky transaction identification device and process the transaction according to a target transaction risk identification result from the risky transaction identification device.

[0020] The risky transaction identification method, device and system of the embodiments of the present invention first construct current transaction features based on current transaction data and input the current transaction features into a risky transaction identification model to obtain a risky transaction identification result, and then generate a target transaction risk identification result based on the risky merchant identification result and the risky customer identification result and send it, so that the acquiring system processes the current transaction according to the target transaction risk identification result, which can effectively improve the efficiency of risky transaction identification and avoidance and reduce the compliance risk of the acquiring institution. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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 description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only 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.

[0022] Figure 1 is a flow chart of a method for identifying risky transactions in one embodiment of the present invention;

[0023] Figure 2 is a flow chart of a method for identifying risky transactions in another embodiment of the present invention;

[0024] Figure 3 is a flow chart of S101 in an embodiment of the present invention;

[0025] Figure 4 is a flow chart of creating a risky transaction identification model in one embodiment of the present invention;

[0026] Figure 5 is a flow chart of creating a risky transaction identification model in another embodiment of the present invention;

[0027] Figure 6 is a structural block diagram of a risky transaction identification device in an embodiment of the present invention;

[0028] Figure 7 is a structural block diagram of a risky transaction identification device in another embodiment of the present invention;

[0029] Figure 8 is a structural block diagram of a computer device in an embodiment of the present invention;

[0030] Fig. 9 Schematic diagram of a risky transaction identification system in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0032] Those skilled in the art will appreciate that the embodiments of the present invention may be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure may be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0033] In view of the fact that the prior art requires manual review and analysis of transaction data in payment requests, which is inefficient and has a low recognition rate, and cannot solve the problem of transaction risk control in the actual operation process, the embodiment of the present invention provides a risk transaction identification method, which is simple to implement, has low implementation cost, and has adaptive capabilities. It can effectively prevent malicious operations by bad merchants and malicious transactions by bad customers, effectively improve the efficiency of risk transaction identification and avoidance, and reduce the compliance risk of acquiring institutions.

[0034] Figure 1 It is a flow chart of a method for identifying risky transactions in one embodiment of the present invention. Figure 2 FIG. 1 is a flow chart of a method for identifying risky transactions in another embodiment of the present invention. Figure 1-Figure 2 As shown, the risk transaction identification method includes:

[0035] S101: Acquire current transaction data in a payment request from an acquiring system, and construct current transaction features based on the current transaction data.

[0036] Figure 3 is a flow chart of S101 in an embodiment of the present invention. Figure 3 As shown, S101 includes:

[0037] S201: Searching for corresponding merchant data and customer data according to current transaction data.

[0038] The merchant data includes merchant business information such as merchant business type, merchant region, business scale, legal person information, number of transactions and transaction amount in each dimension, as well as merchant account information such as deposit and loan balances, receipts and payments, and account flow of merchant-related accounts. In specific implementation, merchant business information can be found from an external merchant management system based on current transaction data, and merchant account information can be found from an external account system.

[0039] S202: Construct current transaction features based on current transaction data, merchant data and customer data.

[0040] Among them, transaction data includes payment channels and transaction amounts, etc. The current transaction features are processed and cleaned data.

[0041] S102: Inputting current transaction features into a risky transaction identification model created based on historical transaction features to obtain risky transaction identification results; wherein the risky transaction identification results include risky merchant identification results and risky customer identification results.

[0042] In one embodiment, S102 includes: inputting current transaction features into a risky transaction identification model created based on historical transaction features according to a preset merchant risk type corresponding to merchant data and a preset customer risk type corresponding to customer data, to obtain a risky transaction identification result.

[0043] For example, the preset merchant risk types include normal merchants, collection merchants, and risky merchants. The preset customer risk types include normal customers, collection customers, and risky customers. When the preset merchant risk type is a risky merchant or the preset customer risk type is a risky customer, the current transaction is determined to be a risky transaction, and the risky transaction is sent to the acquiring system as the target transaction risk identification result. After receiving the target transaction risk identification result determined to be a risky transaction, the acquiring system intercepts the current transaction and the transaction is terminated; otherwise, the current transaction features are input into the risky transaction identification model created based on historical transaction features.

[0044] S103: Generate a target transaction risk identification result according to the risk merchant identification result and the risk customer identification result.

[0045] In specific implementation, the highest risk type among the risk merchant identification results and the corresponding preset merchant risk types can be determined as the target merchant risk identification results, and then the highest risk type among the risk customer identification results and the corresponding preset customer risk types can be determined as the target customer risk identification results, and finally the highest risk type among the target merchant risk identification results and the target customer risk identification results can be determined as the target transaction risk identification results. Among them, the risk level in the risk type is risk>collection>normal.

[0046] For example, if the risk merchant identification result is a normal merchant and the preset merchant risk type is a collection merchant, then the target merchant risk identification result is a collection merchant. If the risk customer identification result is a risk customer and the preset customer risk type is a collection customer, then the target customer risk identification result is a risk customer.

[0047] When the target customer risk identification result is a risky customer and the target merchant risk identification result is a collection merchant, the risk level (risk) of the target customer risk identification result is greater than the target merchant risk identification result (collection), and the target transaction risk identification result is a risky transaction.

[0048] When the target customer risk identification result is a collection customer and the target merchant risk identification result is a normal merchant, the risk level of the target customer risk identification result (collection) is greater than the target merchant risk identification result (normal), and the target transaction risk identification result is a collection transaction.

[0049] When the target customer risk identification result is a normal customer and the target merchant risk identification result is a normal merchant, the target transaction risk identification result is a normal transaction.

[0050] S104: Send the target transaction risk identification result to the acquiring system, so that the acquiring system processes the transaction according to the target transaction risk identification result.

[0051] For example, when the target transaction risk identification result is a normal transaction, the acquiring system allows the current transaction to proceed normally; when the target transaction risk identification result is a collection transaction, the acquiring system performs collection processing on the current transaction; when the target transaction risk identification result is a risky transaction, the acquiring system intercepts the current transaction and the transaction is terminated.

[0052] In one embodiment, the target transaction risk identification result can also be sent to an external front-end control system and displayed. When the target transaction risk identification result is a risky transaction, a risk verification task is triggered and pushed to the external front-end control system to improve the subsequent risk verification efficiency.

[0053] Figure 1 The execution subject of the risk transaction identification method shown can be a computer. Figure 1 As can be seen from the process shown, the risky transaction identification method of the embodiment of the present invention first constructs the current transaction features based on the current transaction data and inputs the current transaction features into the risky transaction identification model to obtain the risky transaction identification results, and then generates the target transaction risk identification results based on the risky merchant identification results and the risky customer identification results and sends them, so that the acquiring system processes the current transaction according to the target transaction risk identification results, which can effectively improve the efficiency of risky transaction identification and avoidance and reduce the compliance risks of acquiring institutions.

[0054] Figure 4 It is a flow chart of creating a risky transaction identification model in one embodiment of the present invention. Figure 5 FIG. 1 is a flowchart of creating a risky transaction identification model in another embodiment of the present invention. Figure 4-Figure 5 As shown in the figure, creating a risky transaction identification model based on historical transaction characteristics includes:

[0055] Perform the following iterative processing:

[0056] S301: Input historical transaction features into the initial recognition model to obtain risky transaction prediction results.

[0057] Among them, the initial recognition model comes from the external front-end control system, which can construct historical transaction features based on current historical transaction data, merchant data and customer data.

[0058] S302: Determine a loss function according to the risk transaction prediction result and the corresponding risk transaction actual result.

[0059] S303: Determine whether the loss function is less than a preset threshold.

[0060] S304: When the loss function is less than a preset threshold, determining that the initial recognition model in the current iteration is a risky transaction recognition model.

[0061] S305: When the loss function is greater than or equal to a preset threshold, the initial recognition model is updated according to the loss function, and the iterative process continues.

[0062] The specific process of the embodiment of the present invention is as follows:

[0063] 1. Input historical transaction features into the initial recognition model to obtain risky transaction prediction results.

[0064] 2. Determine the loss function based on the risk transaction prediction results and the corresponding risk transaction actual results. When the loss function is less than the preset threshold, determine the initial recognition model in the current iteration as the risk transaction recognition model. Otherwise, update the initial recognition model according to the loss function and return to step 1.

[0065] 3. Obtain the current transaction data in the payment request from the acquiring system, and search for the corresponding merchant data and customer data based on the current transaction data.

[0066] 4. Build current transaction features based on current transaction data, merchant data, and customer data.

[0067] 5. According to the preset merchant risk type corresponding to the merchant data and the preset customer risk type corresponding to the customer data, the current transaction characteristics are input into the risk transaction identification model created based on the historical transaction characteristics to obtain the risk transaction identification results, which include the risk merchant identification results and the risk customer identification results.

[0068] 6. Generate target transaction risk identification results based on risk merchant identification results and risk customer identification results, and send the target transaction risk identification results to the acquiring system.

[0069] 7. The acquiring system processes the current transaction based on the target transaction risk identification results.

[0070] In summary, the risky transaction identification method provided by the embodiment of the present invention has the following beneficial effects:

[0071] (1) Use machine learning algorithms to train samples of historical transaction data to derive a risky transaction identification model to further obtain risky transaction identification results.

[0072] (2) Utilize computer data transmission technology to apply current transaction data, merchant data, and customer data to the transaction process in real time or quasi-real time, replacing manual identification and post-interception methods, and improving the efficiency of risk identification and avoidance.

[0073] (3) Automatically trigger risk verification tasks for risky transactions to improve the efficiency of subsequent risk verification.

[0074] Based on the same inventive concept, an embodiment of the present invention further provides a risky transaction identification device. Since the principle of solving the problem by the device is similar to that of the risky transaction identification method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0075] Figure 6 It is a structural block diagram of a risky transaction identification device in an embodiment of the present invention. Figure 7 FIG. 1 is a structural block diagram of a risky transaction identification device in another embodiment of the present invention. Figure 6-Figure 7 As shown, the risk transaction identification device includes:

[0076] A current transaction feature building module is used to obtain current transaction data in a payment request from an acquiring system and build current transaction features based on the current transaction data;

[0077] A risky transaction identification module is used to input current transaction features into a risky transaction identification model created based on historical transaction features to obtain risky transaction identification results; wherein the risky transaction identification results include risky merchant identification results and risky customer identification results;

[0078] A target transaction risk identification module is used to generate a target transaction risk identification result based on the risk merchant identification result and the risk customer identification result;

[0079] The sending module is used to send the target transaction risk identification result to the acquiring system, so that the acquiring system processes the current transaction according to the target transaction risk identification result.

[0080] In one embodiment, the current transaction feature building module includes:

[0081] A data search unit, used to search for corresponding merchant data and customer data according to current transaction data;

[0082] The current transaction feature building unit is used to build the current transaction feature according to the current transaction data, merchant data and customer data.

[0083] In one embodiment, the invention further comprises: a risky transaction identification model creation module, which is used to perform the following iterative processing:

[0084] Input historical transaction features into the initial recognition model to obtain risky transaction prediction results;

[0085] Determine the loss function based on the risk transaction prediction results and the corresponding risk transaction actual results;

[0086] When the loss function is less than a preset threshold, the initial recognition model in the current iteration is determined to be a risky transaction recognition model; otherwise, the initial recognition model is updated according to the loss function, and the iterative process is continued.

[0087] In one embodiment, the risky transaction identification module is specifically used to:

[0088] According to the preset merchant risk type corresponding to the merchant data and the preset customer risk type corresponding to the customer data, the current transaction features are input into the risk transaction identification model created based on the historical transaction features to obtain the risk transaction identification result.

[0089] like Figure 7 As shown, in actual application, the product risk warning device includes a data receiving and transmitting module, a data acquisition and processing module, a risk identification module, a risk task triggering module and a model training module.

[0090] The data receiving and transmitting module includes a sending module, which is used to receive the initial recognition model from the front-end control system, the current transaction data in the payment request from the acquiring system, the merchant operation information from the merchant management system and the merchant account information from the account system; and send the target transaction risk identification result to the acquiring system.

[0091] The data collection and processing module includes a current transaction feature construction module, which is used to process and clean the current transaction data, merchant data and customer data according to business rules to construct current transaction features.

[0092] The risk identification module includes a risk transaction identification module and a target transaction risk identification module.

[0093] The risk task trigger module is used to extract key risk verification information (such as merchant region, customer information, payment channel and transaction amount, etc.) when the target transaction risk identification result is a risky transaction, convert the key risk verification information into business language according to the risk task allocation rules set in the system, and trigger and push the risk verification task to the external front-end control system.

[0094] The model training module includes a risk transaction identification model creation module.

[0095] In summary, the risk transaction identification device of the embodiment of the present invention first constructs the current transaction features according to the current transaction data and inputs the current transaction features into the risk transaction identification model to obtain the risk transaction identification results, and then generates the target transaction risk identification results according to the risk merchant identification results and the risk customer identification results and sends them, so that the acquiring system processes the current transaction according to the target transaction risk identification results, which can effectively improve the efficiency of risk transaction identification and avoidance and reduce the compliance risks of acquiring institutions.

[0096] The embodiment of the present invention also provides a specific implementation of a computer device capable of implementing all the steps in the risky transaction identification method in the above embodiment. Figure 8 is a block diagram of a computer device in an embodiment of the present invention, see Figure 8 , the computer equipment specifically includes the following contents:

[0097] Processor (processor) 801 and memory (memory) 802.

[0098] The processor 801 is used to call the computer program in the memory 802. When the processor executes the computer program, all steps in the risk transaction identification method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0099] Obtain current transaction data in the payment request from the acquiring system, and construct current transaction features based on the current transaction data;

[0100] Input the current transaction features into the risk transaction identification model created based on the historical transaction features to obtain the risk transaction identification results; wherein the risk transaction identification results include the risk merchant identification results and the risk customer identification results;

[0101] Generate target transaction risk identification results based on risk merchant identification results and risk customer identification results;

[0102] The target transaction risk identification result is sent to the acquiring system so that the acquiring system processes the current transaction according to the target transaction risk identification result.

[0103] In summary, the computer device of the embodiment of the present invention first constructs the current transaction features according to the current transaction data and inputs the current transaction features into the risk transaction identification model to obtain the risk transaction identification results, and then generates the target transaction risk identification results according to the risk merchant identification results and the risk customer identification results and sends them, so that the acquiring system processes the current transaction according to the target transaction risk identification results, which can effectively improve the efficiency of risk transaction identification and avoidance and reduce the compliance risks of acquiring institutions.

[0104] The embodiment of the present invention also provides a computer-readable storage medium capable of implementing all the steps of the risky transaction identification method 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 of the risky transaction identification method in the above embodiment are implemented. For example, when the processor executes the computer program, the following steps are implemented:

[0105] Obtain current transaction data in the payment request from the acquiring system, and construct current transaction features based on the current transaction data;

[0106] Input the current transaction features into the risk transaction identification model created based on the historical transaction features to obtain the risk transaction identification results; wherein the risk transaction identification results include the risk merchant identification results and the risk customer identification results;

[0107] Generate target transaction risk identification results based on risk merchant identification results and risk customer identification results;

[0108] The target transaction risk identification result is sent to the acquiring system so that the acquiring system processes the current transaction according to the target transaction risk identification result.

[0109] In summary, the computer-readable storage medium of the embodiment of the present invention first constructs the current transaction characteristics according to the current transaction data and inputs the current transaction characteristics into the risk transaction identification model to obtain the risk transaction identification result, and then generates the target transaction risk identification result according to the risk merchant identification result and the risk customer identification result and sends it, so that the acquiring system processes the current transaction according to the target transaction risk identification result, which can effectively improve the efficiency of risk transaction identification and avoidance and reduce the compliance risk of the acquiring institution.

[0110] Based on the same inventive concept, an embodiment of the present invention also provides a risky transaction identification system. Since the principle of solving the problem by the system is similar to that of the risky transaction identification method, the implementation of the system can refer to the implementation of the method, and the repeated parts will not be repeated.

[0111] Fig. 9 Schematic diagram of a risky transaction identification system according to an embodiment of the present invention. Fig. 9 As shown, the risk transaction identification system includes:

[0112] The risk transaction identification device 1 as described above is a large computer or a small or medium-sized computer deployed in the background of the acquiring institution, and is also used to receive the initial identification model from the front-end control system, the merchant business information from the merchant management system 4 and the merchant account information from the account system 5.

[0113] The acquiring system 2 is used to send a payment request to the risky transaction identification device and process the transaction according to the target transaction risk identification result from the risky transaction identification device.

[0114] In one embodiment, the risky transaction identification system further includes: a front-end control system 3 , a merchant management system 4 and an account system 5 .

[0115] The front-end control system 3 is used to support system users to input and modify the initial recognition model. It is connected to the risk transaction recognition device 1 through a dedicated network 6 to complete operations such as front-end page display and initial recognition model input.

[0116] The dedicated line network 6 refers to a dedicated line deployed by a telecommunications operator, connecting the front-end control system 3 and the risk transaction identification device 1.

[0117] The telecommunication network 7 refers to the telephone network, wireless GPRS, 3G communication network, 4G communication network or Internet network deployed by telecommunication operators. The risk transaction identification device 1, the acquiring system 2, the merchant management system 4 and the account system 5 communicate data through the telecommunication network 7.

[0118] In summary, the risk transaction identification system of the embodiment of the present invention first constructs the current transaction features based on the current transaction data and inputs the current transaction features into the risk transaction identification model to obtain the risk transaction identification results, and then generates the target transaction risk identification results based on the risk merchant identification results and the risk customer identification results and sends them, so that the acquiring system processes the current transaction according to the target transaction risk identification results, which can effectively improve the efficiency of risk transaction identification and avoidance and reduce the compliance risks of acquiring institutions.

[0119] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0120] Those skilled in the art may also understand that the various illustrative logical blocks, units, and steps listed in the embodiments of the present invention may be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly demonstrate the interchangeability of hardware and software, the various illustrative components, units, and steps described above have generally described their functions. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present invention.

[0121] The various illustrative logic blocks, or units, or devices described in the embodiments of the present invention can be implemented or operated by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field programmable gate array or other programmable logic device, a discrete gate or transistor logic, a discrete hardware component, or any combination of the above. The general-purpose processor can be a microprocessor, and optionally, the general-purpose processor can also be any conventional processor, controller, microcontroller or state machine. The processor can also be implemented by a combination of computing devices, such as a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration.

[0122] The steps of the method or algorithm described in the embodiments of the present invention can be directly embedded in hardware, a software module executed by a processor, or a combination of the two. The software module can be stored in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or other storage media of any form in the art. Exemplarily, the storage medium can be connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be arranged in an ASIC, and the ASIC can be arranged in a user terminal. Optionally, the processor and the storage medium can also be arranged in different components in the user terminal.

[0123] In one or more exemplary designs, the above functions described in the embodiments of the present invention can be implemented in hardware, software, firmware or any combination of the three. If implemented in software, these functions can be stored on a computer-readable medium, or transmitted in the form of one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media that facilitate the transfer of computer programs from one place to another. The storage medium can be any available medium that can be accessed by any general or special computer. For example, such computer-readable media can include but are not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store program codes in the form of instructions or data structures and other forms that can be read by general or special computers, or general or special processors. In addition, any connection can be appropriately defined as a computer-readable medium, for example, if the software is transmitted from a website site, server or other remote resource through a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL) or wirelessly, such as infrared, wireless and microwave, it is also included in the defined computer-readable medium. The disk and disc include compact disk, laser disk, optical disk, DVD, floppy disk and blue-ray disk. Disks usually copy data magnetically, while discs usually copy data optically with lasers. The above combination can also be included in computer readable media.

Claims

1. A method for identifying risky transactions, characterized in that: include: Acquire current transaction data in a payment request from an acquiring system, and construct current transaction features based on the current transaction data; Inputting the current transaction features into a risky transaction identification model created based on historical transaction features to obtain a risky transaction identification result; wherein the risky transaction identification result includes a risky merchant identification result and a risky customer identification result; Generate a target transaction risk identification result according to the risk merchant identification result and the risk customer identification result; Sending the target transaction risk identification result to the acquiring system, so that the acquiring system processes the current transaction according to the target transaction risk identification result; Generating a target transaction risk identification result according to the risk merchant identification result and the risk customer identification result includes: Determine the highest risk type among the risk merchant identification results and the corresponding preset merchant risk types as the target merchant risk identification result; Determine the highest risk type among the risk customer identification results and the corresponding preset customer risk types as the target customer risk identification result; Determine the highest risk type in the target merchant risk identification results and the target customer risk identification results as the target transaction risk identification result; wherein the preset merchant risk types include normal merchants, collection merchants and risky merchants; the preset customer risk types include normal customers, collection customers and risky customers; and the risk levels in the risk types are risk>collection>normal; Constructing the current transaction feature according to the current transaction data includes: Searching for corresponding merchant data and customer data according to the current transaction data; constructing a current transaction feature based on the current transaction data, the merchant data and the customer data; Inputting the current transaction features into a risky transaction identification model created based on historical transaction features to obtain risky transaction identification results includes: According to the preset merchant risk type corresponding to the merchant data and the preset customer risk type corresponding to the customer data, the current transaction feature is input into a risk transaction identification model created based on historical transaction features to obtain a risk transaction identification result.

2. The risky transaction identification method according to claim 1, characterized in that: Creating a risky transaction identification model based on historical transaction characteristics includes: Perform the following iterative processing: Input historical transaction features into the initial recognition model to obtain risky transaction prediction results; Determine a loss function based on the risk transaction prediction result and the corresponding risk transaction actual result; When the loss function is less than a preset threshold, the initial recognition model in the current iteration is determined to be the risky transaction recognition model; otherwise, the initial recognition model is updated according to the loss function, and the iterative process is continued.

3. A risky transaction identification device, characterized in that: include: A current transaction feature building module, used to obtain current transaction data in a payment request from an acquiring system, and build current transaction features according to the current transaction data; A risky transaction identification module, used to input the current transaction features into a risky transaction identification model created based on historical transaction features to obtain a risky transaction identification result; wherein the risky transaction identification result includes a risky merchant identification result and a risky customer identification result; A target transaction risk identification module, used to generate a target transaction risk identification result according to the risk merchant identification result and the risk customer identification result; A sending module, used for sending the target transaction risk identification result to the acquiring system, so that the acquiring system processes the current transaction according to the target transaction risk identification result; The target transaction risk identification module is specifically used for: Determine the highest risk type among the risk merchant identification results and the corresponding preset merchant risk types as the target merchant risk identification result; Determine the highest risk type among the risk customer identification results and the corresponding preset customer risk types as the target customer risk identification result; Determine the highest risk type in the target merchant risk identification results and the target customer risk identification results as the target transaction risk identification result; wherein the preset merchant risk types include normal merchants, collection merchants and risky merchants; the preset customer risk types include normal customers, collection customers and risky customers; and the risk level in the risk type is risk>collection; The current transaction feature building module includes: A data search unit, used to search for corresponding merchant data and customer data according to the current transaction data; A current transaction feature construction unit, configured to construct a current transaction feature according to the current transaction data, the merchant data and the customer data; The risk transaction identification module is specifically used for: According to the preset merchant risk type corresponding to the merchant data and the preset customer risk type corresponding to the customer data, the current transaction feature is input into a risk transaction identification model created based on historical transaction features to obtain a risk transaction identification result.

4. The risk transaction identification device according to claim 3, characterized in that: It also includes: a risk transaction identification model creation module, which is used to perform the following iterative processing: Input historical transaction features into the initial recognition model to obtain risky transaction prediction results; Determine a loss function based on the risk transaction prediction result and the corresponding risk transaction actual result; When the loss function is less than a preset threshold, the initial recognition model in the current iteration is determined to be the risky transaction recognition model; otherwise, the initial recognition model is updated according to the loss function, and the iterative process is continued.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the risky transaction identification method according to any one of claims 1 to 2 are implemented.

6. 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 risk transaction identification method according to any one of claims 1 to 2 are implemented.

7. A risky transaction identification system, characterized in that: include: The risk transaction identification device as described in any one of claims 3-4; The acquiring system is used to send a payment request to the risky transaction identification device and process the transaction according to the target transaction risk identification result from the risky transaction identification device.

Images