Trading Risk Control Methods and Devices
By combining transaction monitoring models with facial recognition, the risk control problem in bank client transactions has been solved, improving security and user experience while reducing costs.
Patent Information
- Application Number
- CN202210809043.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-07-11
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2042-07-11
AI Technical Summary
There are system vulnerabilities and fund security risks in the process of bank client transactions. Existing technologies rely on human experience or rule-based judgment, which has low accuracy and poor user experience.
Risk prediction is performed using a transaction monitoring model, and facial recognition is used when a risk warning is issued. Transaction progress is synchronized across different bank clients through cross-platform collaboration.
It improves the security and user experience of bank client transactions and reduces transaction risk control costs.
Smart Images

Figure CN115187398B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of artificial intelligence technology, and more particularly to a method and apparatus for controlling trading risks. It should be noted that the trading risk control method and apparatus of this invention can be used in the field of artificial intelligence, as well as in any field other than artificial intelligence; the application areas of the trading risk control method and apparatus of this invention are not limited. Background Technology
[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.
[0003] Currently, people frequently conduct transactions through bank clients. However, bank client transactions involve various risks, such as system vulnerability risks and fund security risks. Anyone can conduct transactions anytime, anywhere, and bank client transaction risks may occur at any time. However, most existing technologies rely on human experience or rule-based judgment, which is labor-intensive and has low accuracy. Once a transaction security problem occurs, the user experience is also poor. Summary of the Invention
[0004] This invention provides a transaction risk control method to improve the security of bank client transactions, enhance the user experience of bank client transactions, and reduce the cost of bank client transaction risk control. The method is applied to a first bank client and includes:
[0005] Receive a transaction request submitted by a user, the transaction request including user identity information and transaction data;
[0006] User identity information and transaction data are input into the transaction monitoring model to obtain the risk prediction result of the transaction request; the transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data and corresponding historical transaction risk results.
[0007] When the risk prediction results indicate that a transaction request is risky, obtain the user's facial image;
[0008] The user's uploaded facial image is submitted to the bank's back-end server for facial verification;
[0009] After facial recognition is successful, continue processing the transaction request;
[0010] If facial recognition fails, the transaction request will be refused.
[0011] During the processing of the transaction request, the processing progress is synchronized to the user's second bank client so that the second bank client can continue processing the transaction request if the first bank client interrupts the processing of the transaction request.
[0012] This invention also provides a transaction risk control device to improve the security of bank client transactions, enhance the user experience of bank client transactions, and reduce the cost of bank client transaction risk control. The device includes:
[0013] The transaction request receiving module is used to receive transaction requests submitted by users, the transaction requests including user identity information and transaction data;
[0014] The risk prediction module is used to input user identity information and transaction data into the transaction monitoring model to obtain the risk prediction result of the transaction request; the transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data and corresponding historical transaction risk results.
[0015] The facial recognition module is used to obtain the user's facial image when the risk prediction result indicates that the transaction request is risky; and submit the user's uploaded facial image to the bank's back-end server for facial recognition.
[0016] The transaction processing module is used to continue processing the transaction request after the face authentication is successful; and to refuse to process the transaction request if the face authentication fails.
[0017] The transaction progress synchronization module is used to synchronize the processing progress to the user's second bank client during the processing of the transaction request, so that the second bank client can continue processing the transaction request after the first bank client interrupts the processing of the transaction request.
[0018] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described transaction risk control method.
[0019] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described transaction risk control method.
[0020] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described transaction risk control method.
[0021] In this embodiment of the invention, a first bank client receives a transaction request submitted by a user, the transaction request including user identity information and transaction data; the user identity information and transaction data are input into a transaction monitoring model to obtain a risk prediction result for the transaction request; the transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data, and corresponding historical transaction risk results; when the risk prediction result indicates that the transaction request is risky, the user's facial image is acquired; the user's uploaded facial image is submitted to the bank's backend server for facial authentication; after successful facial authentication, the transaction request continues to be processed; if facial authentication fails, the transaction request is rejected; wherein, during the processing of the transaction request, the processing progress is synchronized to the user's second bank client, so that the second bank client can continue processing the transaction request after the first bank client interrupts processing the transaction request. Compared to existing technologies that rely on manual experience or rule-based judgment to determine transaction risks, this invention first utilizes a transaction monitoring model to predict the risk of transaction requests. Upon identifying a risk, it then adds facial recognition authentication to further ensure transaction security. Simultaneously, it enables cross-platform collaboration between different bank clients to synchronize the processing progress of transaction requests. Users can monitor and process transactions anytime, anywhere, experiencing full controllability and security, thus simplifying user operations. Therefore, this invention effectively controls transaction risks through monitoring, improves the security of bank client transactions, enhances user experience, and reduces the cost of transaction risk control for bank clients. Attached Figure Description
[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:
[0023] Figure 1 This is a flowchart illustrating the transaction risk control method applied to the first client in an embodiment of the present invention.
[0024] Figure 2 This is a specific example of the transaction risk control method applied to a first client in an embodiment of the present invention;
[0025] Figure 3 This is a specific example of the transaction risk control method applied to a first client in an embodiment of the present invention;
[0026] Figure 4 This is a schematic diagram of a transaction risk control device applied to a first client in an embodiment of the present invention;
[0027] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention. Detailed Implementation
[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.
[0029] The inventors discovered that more and more users are conducting transactions through bank clients. However, various risks often exist in the process of bank client transactions, such as system vulnerability risks and fund security risks. Anyone can conduct transactions anytime, anywhere, and risks may arise at any time during the transaction process. Therefore, it is very important to help users control the risks in transactions. However, most existing technologies rely on human experience or rule-based judgment, which is costly in terms of manpower and resources and has a low accuracy rate. Once a transaction security problem occurs, the user experience is also poor.
[0030] Therefore, the inventors proposed a method for controlling transaction risks. Figure 1 This is a flowchart illustrating the transaction risk control method applied to the first client in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes:
[0031] Step 101: Receive a transaction request submitted by the user, the transaction request including user identity information and transaction data;
[0032] Step 102: Input user identity information and transaction data into the transaction monitoring model to obtain the risk prediction result of the transaction request; the transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data and corresponding historical transaction risk results.
[0033] Step 103: When the risk prediction result indicates that the transaction request is risky, obtain the user's facial image;
[0034] Step 104: Submit the user-uploaded facial image to the bank's back-end server for facial verification;
[0035] Step 105: After the face authentication is successful, continue processing the transaction request;
[0036] Step 106: If face authentication fails, refuse to process the transaction request;
[0037] During the processing of the transaction request, the processing progress is synchronized to the user's second bank client so that the second bank client can continue processing the transaction request if the first bank client interrupts the processing of the transaction request.
[0038] from Figure 1 As shown in the process, compared with existing technologies that rely on manual experience or rule-based judgment to determine transaction risks, this invention first utilizes a transaction monitoring model to obtain risk prediction results for transaction requests. After predicting the existence of risk, it adds facial recognition authentication to further ensure transaction security. Simultaneously, it enables cross-platform collaboration between different bank clients to synchronize the progress of transaction requests. Users can monitor and process transactions anytime, anywhere, allowing them to fully experience the controllability and security of transactions, thus facilitating user operation. Therefore, this invention effectively controls transaction risks through monitoring, improves the security of bank client transactions, enhances user experience, and reduces the cost of transaction risk control for bank clients.
[0039] Each step is explained in detail below.
[0040] Step 101: The first bank client first receives the transaction request submitted by the user, which includes user identity information and transaction data.
[0041] For example, when a user conducts wealth management business on the bank's mobile app, such as purchasing funds or government bonds, the app first receives the purchase request submitted by the user. The purchase request includes the user's identity information, such as ID card information, registered mobile phone number information, and wealth management risk tolerance level information. The purchase request also includes transaction data, such as the product, amount, and time that the user intends to purchase.
[0042] It should be noted that all data acquisition, storage, use, and processing in this embodiment of the invention comply with the relevant provisions of national laws and regulations. For example, the acquisition of user identity information and transaction processing are performed with the full authorization of the user.
[0043] In one embodiment, a transaction request includes: a transfer transaction request, or a bulk transfer transaction request.
[0044] For example, when a user executes a transfer transaction or a batch transfer transaction in the web banking client, the web banking client receives the transfer transaction request.
[0045] In one embodiment, transaction data includes: user network access data for transactions, and / or user transaction behavior data.
[0046] For example, a bank's client-side application receives network access data related to user transactions, which can be used to analyze recently viewed keywords and web pages. The client-side application also receives user transaction behavior data, such as transfers, batch transfers, and related details, to prepare as much analytical data as possible for subsequent transaction risk monitoring. Those skilled in the art should understand that transaction types, transaction requests, transaction data, and user identity information are not limited to the above-mentioned items; the embodiments of this invention are merely examples and not intended to limit the scope.
[0047] In step 102, user identity information and transaction data are input into the transaction monitoring model to obtain the risk prediction result of the transaction request. The transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data and corresponding historical transaction risk results.
[0048] In this embodiment of the invention, online analysis of bank client transactions is performed based on big data and artificial intelligence technologies to predict their risk. Specifically, based on massive big data storage, user blacklists / whitelists, historical transaction data, and corresponding historical transaction risk results are obtained from relevant databases to construct sample data. A machine learning model for transaction risk monitoring is built based on artificial intelligence technology. The machine learning model is trained and tested to obtain the final transaction monitoring model. After receiving a transaction request, the bank client sends the user identity information and transaction data corresponding to the transaction request to the transaction monitoring model for risk prediction and outputs the risk prediction result for the transaction request. In addition, the user blacklists / whitelists, historical transaction data, and corresponding historical transaction risk result sample data are regularly updated to periodically train and update the transaction monitoring model.
[0049] In one embodiment, after obtaining the risk prediction result of the transaction request, the risk prediction result of the transaction request is displayed to the user.
[0050] For example, if a user makes a transfer transaction on the bank's mobile app, the transaction monitoring model will warn that the user has been blacklisted, and the results page on the bank's mobile app will indicate that the user has been identified as having a transaction risk.
[0051] For example, if a user makes an investment transaction on a web banking client, the transaction monitoring model may warn that the transaction carries a risk of telecommunications fraud. The web banking client's results page will then notify the user that the transaction risk has been identified.
[0052] The transaction monitoring model identifies transaction risk types including suspicious identity and suspicious transaction. Suspicious identity is predicted by updating the blacklist statistically analyzed across the entire network, while suspicious transaction can be predicted by information such as amount, time, location, and network access records. The transaction monitoring model can issue early warnings for these similar suspicious factors, freeing up manual judgment, quickly and accurately obtaining risk prediction results, and then intercepting risky transactions to improve the security of bank client transactions and effectively protect user assets.
[0053] In step 103, when the risk prediction result indicates that the transaction request is risky, the user's facial image is obtained; in step 104, the facial image uploaded by the user is submitted to the bank's back-end server for facial authentication.
[0054] Figure 2 This is a specific example diagram of the transaction risk control method applied to a first client in an embodiment of the present invention, as shown below. Figure 2 As shown, in one implementation, step 103 may include:
[0055] Step 201: Show the user a QR code for facial recognition scanning, wherein the QR code carries a transaction serial number and user identity information;
[0056] Step 202: Receive the facial image uploaded by the user by scanning the QR code.
[0057] For example, when a user makes a transfer transaction on the Web banking client, the transaction monitoring model detects that the transaction is risky. The Web banking client then notifies the user of the risk on the results page and displays a QR code for facial recognition scanning, prompting the user to scan the QR code for facial recognition authentication. The Web banking client receives the user's uploaded facial image through facial scanning, and then uploads the facial image to the bank's back-end server for comparison and authentication with the facial information that the user previously registered in the bank's system.
[0058] Figure 3 This is a specific example diagram illustrating the application of the transaction risk control method in a first client according to an embodiment of the present invention. Figure 3The diagram illustrates an interface requiring facial recognition authentication. If the user does not have the banking app installed on their phone, they need to install it before proceeding. If the user has the banking app installed, they can simply open it and use the "scan" function to scan the second QR code for facial recognition. The banking app obtains the transaction serial number and user identity information carried in the QR code by scanning it, and requests relevant transaction data from the backend so that the user can view the transaction details. It should be noted that the QR code has an expiration period, for example, 10 minutes. If the user does not scan the QR code within the expiration period—meaning the client does not receive the facial image uploaded by the user through scanning the QR code—or if the user scanned the QR code but failed facial recognition authentication, the transaction will be reverted to its original state.
[0059] In step 105, after facial recognition is successful, the transaction request continues to be processed; in step 106, if facial recognition fails, the transaction request is rejected.
[0060] It should be noted that, in this embodiment of the invention, during the processing of the transaction request, the first bank client synchronizes the processing progress to the user's second bank client, so that the second bank client can continue processing the transaction request after the first bank client interrupts the processing of the transaction request.
[0061] In one embodiment, in the transaction risk control method of this invention, the first bank client is a Web banking client and the second bank client is an APP banking client; or, the first bank client is an APP banking client and the second bank client is a Web banking client.
[0062] For example, if a user processes a transaction on the mobile banking app, the transaction monitoring model predicts the transaction risk. If no risk is predicted, the system skips the risk prediction results and proceeds directly to the next step. If a risk is predicted, the system notifies the user that the risk has been identified and directly invokes the facial recognition interface, prompting the user to complete facial recognition authentication. If authentication is successful, the transaction continues; if authentication fails or is not completed within the validity period, the transaction is rejected. The web banking client synchronizes the transaction progress with the mobile banking app in real time. Transactions without predicted risk can skip the risk prediction results and proceed directly to the next step, displayed to the user. Transactions with predicted risk display the risk prediction results and remind the user to complete enhanced identity authentication. This filtering mechanism ensures transaction security while providing users with a margin of error, improving the user experience.
[0063] For example, if a user processes a transaction on the web banking client, the transaction monitoring model predicts the transaction risk. If no risk is predicted, the system skips the risk prediction results screen and proceeds directly to the next step. If a risk is predicted, the system notifies the user that the risk has been identified and displays an enhanced identity authentication interface containing a QR code for facial recognition scanning. The user is prompted to complete facial recognition authentication. If authentication is successful, the transaction continues; if authentication fails or is not completed within the validity period, the transaction is rejected. The transaction progress is synchronized in real time between the mobile banking app and the web banking client. It should be noted that for rejected transactions, users can expand the results screen or click a link to view the transaction results and information about the predicted risks during the transaction.
[0064] In other words, during transaction processing on one bank's client app, users can monitor and process transactions through another bank's client app. If a transaction occurs on one bank's client app that goes against the user's wishes, the user can directly intervene on the other bank's client app. Throughout the entire transaction process, the two clients collaborate across platforms, updating synchronously to maintain consistent transaction progress. Users can monitor and receive alerts for suspicious transactions in real time without waiting. For example, when a user is not near their computer, they can open the mobile banking app; the risk transaction identification information from the web banking app will be synchronized to the mobile banking app, allowing the user to identify, verify, and intervene anytime, anywhere. Similarly, if a transaction request on the web banking app is predicted to be risky, the user will be prompted to perform facial recognition authentication, which can be done through the mobile banking app. This cross-platform collaboration enhances the security of bank client transactions, significantly improves the user experience, and increases the accuracy and efficiency of transaction control.
[0065] This invention also provides a transaction risk control device, as described in the following embodiments. Since the principle by which this device solves the problem is similar to that of the transaction risk control method, the implementation of this device can refer to the implementation of the transaction risk control method; repeated details will not be elaborated further.
[0066] Figure 4 This is a schematic diagram of a transaction risk control device applied to a first client in an embodiment of the present invention, as shown below. Figure 4 As shown, the device includes:
[0067] The transaction request receiving module 401 is used to receive a transaction request submitted by a user, the transaction request including user identity information and transaction data;
[0068] The risk prediction module 402 is used to input user identity information and transaction data into the transaction monitoring model to obtain the risk prediction result of the transaction request; the transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data and corresponding historical transaction risk results.
[0069] The facial recognition authentication module 403 is used to obtain the user's facial image when the risk prediction result indicates that there is a risk in the transaction request; and submit the facial image uploaded by the user to the bank's back-end server for facial authentication.
[0070] The transaction processing module 404 is used to continue processing the transaction request after the face authentication is successful; and to refuse to process the transaction request if the face authentication fails.
[0071] The transaction progress synchronization module 405 is used to synchronize the processing progress to the user's second bank client during the processing of the transaction request, so that the second bank client can continue to process the transaction request after the first bank client interrupts the processing of the transaction request.
[0072] In one embodiment, the transaction data in the transaction risk control device of this invention includes:
[0073] User network access data for transactions, and / or user transaction behavior data.
[0074] In one embodiment, the transaction request in the transaction risk control device of this invention includes:
[0075] Transfer transaction request, or batch transfer transaction request.
[0076] In one embodiment, the face recognition authentication module 403 is specifically used for:
[0077] Show the user a QR code for facial recognition scanning, the QR code carrying a transaction serial number and user identity information;
[0078] Receive facial images uploaded by users by scanning the QR code.
[0079] In one embodiment, the risk prediction module 402 is further configured to:
[0080] Display the risk prediction results of the transaction request to the user.
[0081] In one embodiment, in the transaction risk control device of this invention, the first bank client is a Web banking client, and the second bank client is an APP banking client;
[0082] Alternatively, the first bank client may be an APP banking client, and the second bank client may be a Web banking client.
[0083] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention, such as... Figure 5 As shown, this embodiment of the invention also provides a computer device 500, including a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, it implements the above-mentioned transaction risk control method.
[0084] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described transaction risk control method.
[0085] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-described transaction risk control method.
[0086] In this embodiment of the invention, a first bank client receives a transaction request submitted by a user, the transaction request including user identity information and transaction data; the user identity information and transaction data are input into a transaction monitoring model to obtain a risk prediction result for the transaction request; the transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data, and corresponding historical transaction risk results; when the risk prediction result indicates that the transaction request is risky, the user's facial image is acquired; the user's uploaded facial image is submitted to the bank's backend server for facial authentication; after successful facial authentication, the transaction request continues to be processed; if facial authentication fails, the transaction request is rejected; wherein, during the processing of the transaction request, the processing progress is synchronized to the user's second bank client, so that the second bank client can continue processing the transaction request after the first bank client interrupts processing the transaction request. Compared to existing technologies that rely on manual experience or rule-based judgment to determine transaction risks, this invention first utilizes a transaction monitoring model to predict the risk of transaction requests. Upon identifying a risk, it then adds facial recognition authentication to further ensure transaction security. Simultaneously, it enables cross-platform collaboration between different bank clients to synchronize the processing progress of transaction requests. Users can monitor and process transactions anytime, anywhere, experiencing full controllability and security, thus simplifying user operations. Therefore, this invention effectively controls transaction risks through monitoring, improves the security of bank client transactions, enhances user experience, and reduces the cost of transaction risk control for bank clients.
[0087] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0088] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0089] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0090] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0091] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are 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 within the scope of protection of the present invention.
Claims
1. A method for controlling transaction risk, characterized in that, The method is applied to the client of the first bank, and the method includes: Receive a transaction request submitted by a user, the transaction request including user identity information and transaction data; User identity information and transaction data are input into the transaction monitoring model to obtain the risk prediction result of the transaction request; the transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data and corresponding historical transaction risk results; the transaction risk types identified by the transaction monitoring model include suspicious identity and suspicious transaction, suspicious identity is predicted by updating the blacklist statistically analyzed across the entire network, and suspicious transaction is predicted by amount, time, location and network access record information. When the risk prediction results indicate that a transaction request is risky, obtain the user's facial image; The user's uploaded facial image is submitted to the bank's back-end server for facial verification; After facial recognition is successful, continue processing the transaction request; If facial recognition fails, the transaction request will be refused. In the process of processing the transaction request, the processing progress is synchronized to the second bank client to which the user belongs, so that the second bank client can continue to process the transaction request after the first bank client interrupts the processing of the transaction request; The first bank client is a web banking client, and the second bank client is an app banking client; or, the first bank client is an app banking client, and the second bank client is a web banking client; In this process, while a transaction is being processed on one bank's client, the user monitors and processes it through another bank's client. If a transaction is processed against the user's will on one bank's client, the user can directly intervene on the other bank's client. From the beginning to the end of the entire transaction process, the two clients collaborate across platforms, update synchronously, and always keep the transaction progress consistent. During the transaction operation, the user can monitor and alert on suspicious transactions in real time.
2. The method as described in claim 1, characterized in that, Transaction data includes: User network access data for transactions, and / or user transaction behavior data.
3. The method as described in claim 1, characterized in that, The transaction request includes: Transfer transaction request, or batch transfer transaction request.
4. The method as described in claim 1, characterized in that, Obtain the user's facial image, including: Show the user a QR code for facial recognition scanning, the QR code carrying a transaction serial number and user identity information; Receive facial images uploaded by users by scanning the QR code.
5. The method as described in claim 1, characterized in that, After obtaining the risk prediction result of the transaction request, the method further includes: Display the risk prediction results of the transaction request to the user.
6. A transaction risk control device, characterized in that, The device is applied to a first bank client, and the device includes: The transaction request receiving module is used to receive transaction requests submitted by users, the transaction requests including user identity information and transaction data; The risk prediction module is used to input user identity information and transaction data into the transaction monitoring model to obtain the risk prediction result of the transaction request. The transaction monitoring model is trained on a machine learning model based on a preset user blacklist / whitelist, historical transaction data and corresponding historical transaction risk results. The transaction risk types identified by the transaction monitoring model include suspicious identity and suspicious transaction. Suspicious identity is predicted by updating the blacklist statistically analyzed across the entire network, while suspicious transaction is predicted by amount, time, location and network access record information. The facial recognition authentication module is used to obtain the user's facial image when the risk prediction result indicates that the transaction request is risky; and submit the user's uploaded facial image to the bank's back-end server for facial authentication. The transaction processing module is used to continue processing the transaction request after the face authentication is successful; and to refuse to process the transaction request if the face authentication fails. The transaction progress synchronization module is used to synchronize the processing progress to the user's second bank client during the processing of the transaction request, so that the second bank client can continue processing the transaction request after the first bank client interrupts the processing of the transaction request; the first bank client is a web banking client and the second bank client is an APP banking client; or, the first bank client is an APP banking client and the second bank client is a web banking client; In this process, while a transaction is being processed on one bank's client, the user monitors and processes it through another bank's client. If a transaction is processed against the user's will on one bank's client, the user can directly intervene on the other bank's client. From the beginning to the end of the entire transaction process, the two clients collaborate across platforms, update synchronously, and always keep the transaction progress consistent. During the transaction operation, the user can monitor and alert on suspicious transactions in real time.
7. The apparatus as claimed in claim 6, characterized in that, Transaction data includes: User network access data for transactions, and / or user transaction behavior data.
8. The apparatus as claimed in claim 6, characterized in that, The transaction request includes: Transfer transaction request, or batch transfer transaction request.
9. The apparatus as claimed in claim 6, characterized in that, The facial recognition authentication module is specifically used for: Show the user a QR code for facial recognition scanning, the QR code carrying a transaction serial number and user identity information; Receive facial images uploaded by users by scanning the QR code.
10. The apparatus as claimed in claim 6, characterized in that, The risk prediction module is also used for: Display the risk prediction results of the transaction request to the user.
11. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.
12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.
13. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 5.
Citation Information
Patent Citations
Self-service terminal account transfer verification method, device and equipment and storage medium
CN112053148A
Safe payment method, device and equipment and readable medium
CN112184239A
Mobile banking business handling method, ATM and bank background system
CN113487305A
