Account transfer method and device based on multiple identity verification, equipment, medium and product

Abstract

The invention provides a transfer method based on multiple identity verification, which can be applied to the technical field of information security. The transfer method based on multiple identity verification comprises the following steps: in response to a transfer request of a transfer party, executing first identity verification on the transfer party; after the first identity verification is passed, second identity verification of the payee is executed, and after the second identity verification is passed, account transfer operation is completed; presenting an identifier set containing at least one correct payee identifier and at least one interference identifier to the transfer party, and obtaining the accuracy of the transfer party identifying the correct payee identifier from the identifier set; in the process that the transfer party identifies the correct payee identifier, obtaining the interaction behavior characteristics of the transfer party; and when the accuracy is higher than a preset threshold and the interaction behavior characteristics are matched with a preset behavior baseline model, confirming that the second identity verification is passed. The invention further provides a transfer device and equipment based on multiple identity verification, a storage medium and a program product.

Description

Technical Field

[0001] This disclosure relates to the field of information security technology, and specifically to a transfer method, apparatus, device, medium, and program product based on multi-factor authentication. Background Technology

[0002] With the rapid development of internet finance, mobile banking transfers have become the mainstream method for users to conduct financial transactions. However, this convenience is accompanied by increasing cybersecurity risks, especially fraudulent activities targeting the transfer process. Criminals often impersonate the recipient, taking advantage of users' failure to carefully verify information in urgent or negligent situations, posing a serious threat to users' financial security.

[0003] Currently, mobile banking security mechanisms primarily rely on traditional verification methods. The first is password-based and dynamic verification code-based identity verification schemes. This method requires users to enter a static password and receive a dynamic verification code via SMS. While widely adopted, this scheme has significant security vulnerabilities; verification codes are easily obtained through man-in-the-middle attacks, SMS hijacking, or phishing websites, allowing for malicious bypass. Secondly, with advancements in biometric technology, facial recognition-based identity verification schemes are being used in the financial sector. Users complete verification by scanning their facial information using the device's camera. However, facial recognition alone still faces security risks, such as attacks using high-resolution photos, video playback, or 3D masks to forge liveness data. It struggles to effectively counter advanced fraud techniques like deepfakes, and its accuracy and reliability are insufficient in complex scenarios.

[0004] To enhance security, the industry has seen the emergence of multi-factor authentication schemes that combine passwords, CAPTCHAs, and biometrics. While this approach strengthens security through multiple verification methods, it is cumbersome and requires certain user equipment and operational skills. This can lead to a poor user experience, especially for older or less tech-savvy users, potentially reducing the effectiveness of the security measures. Summary of the Invention

[0005] In view of the above problems, this disclosure provides a method, apparatus, device, medium and program product for improving the security of user account transfers based on multi-factor authentication.

[0006] The first aspect of this disclosure provides a multi-factor authentication-based transfer method, the method comprising: in response to a transfer request from a transferor, performing a first authentication of the transferor; after the first authentication is successful, performing a second authentication of the recipient; and after the second authentication is successful, completing the transfer operation; the second authentication comprising: presenting the transferor with an identifier set containing at least one correct recipient identifier and at least one interfering identifier; obtaining the accuracy rate at which the transferor identifies the correct recipient identifier from the identifier set; wherein the number of correct recipient identifiers and interfering identifiers and the similarity between the interfering identifiers and the correct recipient identifiers are positively correlated with the risk level of the transfer request; during the process of the transferor identifying the correct recipient identifier, obtaining the transferor's interactive behavior characteristics; and confirming that the second authentication is successful based on the accuracy rate and the interactive behavior characteristics.

[0007] In this embodiment of the disclosure, the condition for triggering the first identity verification of the transferor is that the number of transfers made by the transferor within a preset period reaches a preset threshold.

[0008] In this embodiment of the disclosure, the first identity verification of the transferor in response to the transfer request includes: obtaining a static portrait photo pre-stored in the transferor's account and a real-time face image of the transferor; dynamically configuring the weights of each facial region in the static portrait photo and the real-time face image based on imaging environment interference factors in the real-time face image; calculating the weighted similarity between the static portrait photo and the real-time face image based on the weights of each facial region; and confirming the identity of the transferor based on the weighted similarity.

[0009] In this embodiment of the disclosure, the dynamic configuration of the weights of each facial region in the static portrait photo and the real-time face image based on the imaging environment interference factors in the real-time face image includes: when insufficient lighting is detected in the real-time face image, increasing the weight of a preset facial region, which includes at least the image regions of the forehead, eyes, nose, mouth, and chin contours; and when facial occlusion is detected in the real-time face image, increasing the weight of the unoccluded region.

[0010] In this embodiment of the disclosure, confirming the identity of the transferor based on the weighted similarity includes: comparing the weighted similarity with a dynamic threshold; wherein the dynamic threshold is adaptively adjusted based on the severity of the imaging environment interference factors.

[0011] In this embodiment of the disclosure, presenting the transferor with an identifier set containing at least one correct recipient identifier and at least one interfering identifier, and obtaining the accuracy rate at which the transferor identifies the correct recipient identifier from the identifier set, includes: determining the risk level of the transfer request based on one or more of the transfer amount, the closeness between the transferor and the recipient, and the transferor's transaction method; generating the identifier set based on the risk level; presenting the identifier set in a randomly shuffled order to the transferor; and confirming the accuracy rate at which the transferor identifies the correct recipient identifier in response to the transferor's selection result in the identifier set.

[0012] In this embodiment of the disclosure, the correct payee identifier is the entire image or a partial image of the payee preset image, and the interference identifier is an image generated by artificial intelligence that is similar to the correct payee identifier.

[0013] In this embodiment of the disclosure, confirming the second authentication is successful based on the accuracy and the interaction behavior features includes: confirming the second authentication is successful when the accuracy is higher than a first preset threshold and the interaction behavior features match a preset behavior baseline model with a degree higher than a second preset threshold.

[0014] A second aspect of this disclosure provides a multi-factor authentication-based transfer device, the device comprising: a first authentication module for performing a first authentication of the transferor in response to a transfer request; a second authentication module for performing a second authentication of the recipient after the first authentication is successful, the second authentication comprising: presenting the transferor with a set of identifiers including a correct recipient identifier and at least one interfering identifier, and confirming whether the transferor has identified the correct recipient identifier based on a selection made by the transferor from the set of identifiers; and a transfer execution module for completing the transfer operation after the second authentication is successful.

[0015] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the method described above.

[0016] A fourth aspect of this disclosure also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0017] The fifth aspect of this disclosure also provides a computer program product, including a computer program or instructions that, when executed by a processor, implement the steps of the above-described method. Attached Figure Description

[0018] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0019] Figure 1 The illustration shows an application scenario of a transfer method and apparatus based on multi-factor authentication according to embodiments of the present disclosure;

[0020] Figure 2 A flowchart illustrating a multi-factor authentication-based transfer method according to an embodiment of the present disclosure is shown schematically;

[0021] Figure 3 The schematic diagram illustrates a flow chart of a multi-factor authentication-based transfer method according to an embodiment of the present disclosure;

[0022] Figure 4 A schematic diagram illustrating a multi-factor authentication-based money transfer device according to an embodiment of the present disclosure is shown; and

[0023] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a multi-factor authentication-based transfer method according to an embodiment of the present disclosure. Detailed Implementation

[0024] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0027] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0028] It should be noted that the multi-factor authentication-based transfer method and device provided in this disclosure can be used in the financial field for transfer business applications, and can also be used in any field other than the financial field. The application field of the multi-factor authentication-based transfer method and device disclosed in this disclosure is not limited.

[0029] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, they do not mean that the applicant has used or necessarily used the solution.

[0030] In the technical solution disclosed herein, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with relevant laws, regulations, and standards, and necessary measures have been taken to ensure that they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0031] This disclosure provides a multi-factor authentication-based transfer method that significantly enhances fund security by constructing a dual security defense. The method includes: responding to a transfer request from a transferor, performing a first authentication of the transferor; after the first authentication is successful, performing a second authentication of the recipient, the second authentication including: presenting the transferor with a set of identifiers containing at least one correct recipient identifier and at least one interfering identifier, and obtaining the accuracy rate at which the transferor identifies the correct recipient identifier from the identifier set; during the process of the transferor identifying the correct recipient identifier, obtaining the transferor's interactive behavior characteristics; confirming the second authentication is successful based on the accuracy rate and interactive behavior characteristics; and completing the transfer operation after the second authentication is successful.

[0032] Figure 1 The illustration shows an application scenario of a transfer method and apparatus based on multi-factor authentication according to an embodiment of the present disclosure.

[0033] like Figure 1As shown, application scenario 100 according to this embodiment may include a bank transfer business scenario. Network 104 is used as a medium to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0034] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0035] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0036] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0037] It should be noted that the multi-factor authentication-based transfer method provided in this disclosure embodiment can generally be executed by server 105. Correspondingly, the multi-factor authentication-based transfer device provided in this disclosure embodiment can generally be located in server 105. The multi-factor authentication-based transfer method provided in this disclosure embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the multi-factor authentication-based transfer device provided in this disclosure embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0038] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0039] The following will be based on Figure 1 The described scene, through Figures 2-3 The multi-factor authentication-based transfer method of the disclosed embodiments is described in detail.

[0040] Figure 2 A flowchart illustrating a multi-factor authentication-based transfer method according to an embodiment of this disclosure is shown schematically.

[0041] like Figure 2 As shown, the multi-factor authentication-based transfer method of this embodiment includes operations S210 to S230, which can be executed sequentially.

[0042] In operation S210, in response to the transfer request from the transferor, the first authentication of the transferor is performed.

[0043] In this operation, the first identity verification process for the transferor can be triggered in the transfer system when the transfer process is initiated, i.e., when the transfer request is generated. This first identity verification process is used to confirm whether the operator of the current transfer is the legitimate holder of the account.

[0044] In the embodiments of this disclosure, the first authentication can be biometric authentication based on facial recognition. The transfer system guides the user to capture a real-time facial image through a camera. Simultaneously, the system retrieves a pre-stored static standard portrait photo of the user's face from the backend server, used for comparison; for example, a photo taken when opening the account. Subsequently, the system uses a built-in facial recognition algorithm to extract and compare facial feature points from the two images, such as the relative positions and contours of the eyes, nose, and mouth, and calculates a similarity score. If the score is higher than a preset fixed threshold, for example, 95%, the first authentication is considered successful, and the process proceeds to the next step. If authentication fails, the system terminates the transfer operation and displays a verification failure message to the user.

[0045] In embodiments of this disclosure, the transferor's consent or authorization can be obtained before acquiring the transferor's identity information. For example, before operation S210, a request to acquire a facial image can be sent to the transferor. If the transferor consents or authorizes the acquisition of its static facial image and real-time facial image, operation S210 is performed.

[0046] In operation S220, after the first authentication is successful, a second authentication is performed on the payee.

[0047] The second authentication is a second security verification stage before the transfer. The transfer system initiates the second authentication of the recipient. The second authentication includes: presenting the transferor with a set of identifiers containing the correct recipient identifier and at least one interfering identifier, and obtaining the accuracy rate at which the transferor identifies the correct recipient identifier from the set of identifiers.

[0048] For example, the system interface will pop up a prompt box displaying 10 photos of people. Three of these are the verified profile pictures of User B (the correct recipient of this transfer), while the remaining seven are randomly selected or generated photos of unrelated individuals. User A must identify and select the correct photo of User B from this set of photos. This step aims to verify that the sender is indeed aware of the recipient's identity and that the transfer was not accidental or involuntary.

[0049] In the embodiments disclosed herein, if user A's accuracy rate reaches 100%, the system's built-in algorithm determines that the verification is successful, and the interface displays "Image verification successful." If user A makes an incorrect selection, the system determines that the verification fails, and the interface prompts "Incorrect selection, please re-identify." Subsequently, the system will dynamically refresh the set of photos, that is, provide 4 correct and 6 new misleading photos, increasing the verification difficulty by adjusting the image proportions, requiring user A to re-select. As a security restriction, if user A makes three consecutive incorrect selections, the system will automatically terminate the current transfer process to prevent potential fraud or malicious operations, and will suggest that the user verify the recipient's information and re-initiate the transaction.

[0050] In some embodiments, the second authentication further includes: acquiring the transferor's interactive behavior characteristics during the process of the transferor identifying the correct recipient's identifier. For example, using a camera on the device the transferor uses to operate the transfer, such as a mobile phone, computer, or self-service transfer machine, to collect the transferor's interactive behavior; based on a pre-built artificial intelligence model on the device, identifying the interactive behavior characteristics, which include multimodal characteristics such as biometrics and operating habits reflected by the transferor when performing the verification operation. After the user completes the identification of the correct recipient's identifier, the second authentication is confirmed to be successful based on the accuracy rate and interactive behavior characteristics. Specifically, when the accuracy rate is higher than a preset threshold and the interactive behavior characteristics match preset behavior characteristics, the second authentication is confirmed to be successful. In embodiments of this disclosure, the recipient's consent or authorization can be obtained before executing the transfer. For example, when the recipient activates the payment collection function, a request is sent to the recipient to obtain their correct recipient identifier, which can be the recipient's signature, image, preset identifier code, etc. With the recipient's consent or authorization, the identifier set is generated.

[0051] After the second identity verification is successful, the transfer operation is completed in the S230 operation.

[0052] In this operation, once the transfer system confirms that the user has correctly selected the recipient's identifier from the identifier set, the second identity verification is considered successful. At this point, the system generates the final transfer execution instruction. This instruction triggers the background fund processing flow, including: deducting a specified amount from the transferor's account, adding the corresponding amount to the recipient's account, updating the account balance records of both parties, and generating an electronic transfer voucher with a unique number.

[0053] Once the S230 operation is completed, this two-factor authentication-based transfer process is finished. The user will receive clear feedback that the operation was successful, the funds transfer is effective, and all relevant records are properly stored. If a rare system error occurs during the S230 fund transfer process (such as network timeout, database abnormality, etc.), the system will not display "transfer successful" to the user. Instead, it will trigger the exception handling mechanism, suspend the transaction, return the funds to the sender's account, and prompt "Transaction processing failed, please try again later or contact customer service."

[0054] The transfer method based on multi-factor authentication provided in this disclosure constructs a dual security defense, jointly preventing issues from both the identity of the transferor and the identity of the recipient. This fundamentally solves the problem that a single verification step is easily bypassed, and significantly improves the overall security of the transfer operation.

[0055] The following is combined Figure 3 The detailed flowchart shown below illustrates the multi-factor authentication-based transfer method provided in this disclosure.

[0056] In the embodiments of this disclosure, before operating S210, the transfer system monitors the transfer behavior of the transferor within a preset period in real time, and uses this as a smart condition to trigger the first identity verification. The condition for triggering the first identity verification of the transferor is: the number of transfers by the transferor within the preset period reaches a preset threshold.

[0057] For example, a transfer system sets a rolling statistical period, such as 24 hours or 30 calendar days, and sets a limit on the number of transfers within that period, such as 20. The transfer system's backend continuously counts the transfer transactions of each user and maintains a counter associated with that rolling period. When a user (the transferor) initiates a new transfer request, the system first checks the number of transfers they have successfully completed within the current calendar day. If the number has not reached the 20 threshold, the system allows the transaction to proceed directly to the regular password or SMS verification process without forcibly initiating a high-security first-level identity verification. If the number has reached or exceeded the 20 threshold, the system will automatically trigger operation S210 in the process, which forces the transferor to complete the first-level identity verification based on facial recognition. The system may prompt the user, "To ensure the security of your account, you have made too many transfers today and need to perform facial recognition verification."

[0058] This identity verification triggering mechanism ensures a smooth user experience for infrequent, small-amount transfers; when transactions become more frequent and potential risks increase, this identity verification mechanism helps the transfer system and users automatically upgrade their security level, effectively preventing the transfer of funds in bulk after the account has been stolen.

[0059] In operation S210, in response to the transfer request from the transferor, the first authentication of the transferor is performed. The core of this first authentication lies in an intelligent facial recognition algorithm that can adapt to changes in the environment.

[0060] Operation S210 includes operations S211 to S214.

[0061] In operation S211, the static portrait photo and the real-time facial image of the transferor are obtained from the account of the transferor.

[0062] In this embodiment, the transfer system first retrieves a pre-stored static portrait photo of the transferor's account from the secure storage of the backend server, such as a high-resolution ID photo taken when opening a bank account. This photo serves as the comparison benchmark. Simultaneously, the system guides the user to capture a real-time facial image using their camera.

[0063] In operation S212, the weights of each facial region in the static portrait photo and the real-time face image are dynamically configured based on the imaging environment interference factors in the real-time face image.

[0064] In this embodiment, the transfer system preprocesses the acquired real-time face images and analyzes the imaging environment interference factors. These factors may include lighting conditions, occlusions, shooting angle, motion blur, etc. Specifically, when insufficient lighting is detected in the real-time face image, the weight of a preset facial region is increased. The preset facial region includes at least the image regions of the forehead, eyes, nose, mouth, and chin contours. When facial occlusion is detected in the real-time face image, the weight of the unoccluded areas is increased. The system dynamically configures the weight of each facial region in the static portrait photo and the real-time face image, with the basic principle of reducing the weight of severely interfered areas and increasing the weight of clear and stable areas.

[0065] For example, if strong sidelight is detected in a real-time image, causing the left side of the user's face to be too dark and lack detail, the system will temporarily reduce the weight of feature points in the left cheek area in the similarity calculation, while correspondingly increasing the weight of the right side of the face and the forehead area, which are less affected by lighting. As another example, if the user is wearing glasses, causing glare or distortion in the eye contour and surrounding areas, the system will reduce the weight of the periorbital area while increasing the weight of the bridge of the nose, mouth, and the overall facial contour.

[0066] In operation S213, the weighted similarity between the static portrait photo and the real-time face image is calculated based on the weights of each facial region.

[0067] In this embodiment, the face recognition algorithm extracts facial feature points, such as inter-eye distance, nasal wing width, and mouth corner contour, from two images based on dynamically configured region weights. Subsequently, the algorithm calculates the weighted similarity between the static portrait photograph and the real-time face image based on the weights of each facial region. This is a precise calculation process that integrates multiple feature points and performs a weighted average according to their importance.

[0068] In operation S214, the identity of the transferor is confirmed based on weighted similarity.

[0069] In this embodiment of the disclosure, the transfer system compares the calculated weighted similarity with a preset general threshold. If the weighted similarity is higher than the threshold, the system confirms the legitimacy of the transferor's identity, the first identity verification is successful, and the process proceeds to S220. If the threshold is not met, the verification fails, the system terminates the transfer and prompts the user.

[0070] In some embodiments of this disclosure, the weighted similarity can also be compared with a dynamic threshold. The dynamic threshold is adaptively adjusted based on the severity of interference factors in the imaging environment. The system calculates an interference score for the current imaging environment; for example, 0.0 represents no interference, and 1.0 represents severe interference. This score is determined by multiple sub-factors such as uneven illumination, occlusion area, and pose angle. The dynamic threshold is positively correlated with the interference score. That is, the more severe the environmental interference, the more relaxed the required threshold should be. For example, under ideal indoor lighting, the interference score is low, and the dynamic threshold may be set to a strict 95%. When significant sidelight is detected or the user is wearing ordinary glasses, the interference score becomes "moderate," and the dynamic threshold may be adaptively adjusted to 92%. If in a low-light environment and slight motion blur is detected, the interference score is high, and the threshold may be further adjusted to 90%. Simultaneously, the system sets an absolute lower limit, such as 88%, to prevent excessive reduction of safety standards under extremely harsh conditions. When the weighted similarity is greater than the dynamic threshold, the identity of the transferor is confirmed.

[0071] This method, by introducing environmental awareness and dynamic weight configuration, significantly improves the accuracy and robustness of facial recognition in real-world, complex application scenarios. It effectively mitigates verification failures caused by temporary environmental factors, significantly improving user experience while ensuring security, and reducing the rejection of legitimate users due to objective reasons such as poor lighting or wearing glasses.

[0072] In operation S220, in response to the successful completion of the first authentication, the transfer system performs a second authentication of the recipient. The core purpose of this authentication is to confirm that the transferor is consciously aware of and acknowledges the recipient of the transaction. The transfer system presents the transferor with a set of identifiers containing the correct recipient identifier and at least one distractor identifier, and confirms whether the transferor has identified the correct recipient identifier based on their selection from the identifier set. Furthermore, the interactive behavior characteristics of the transferor in identifying the correct recipient identifier are verified to further enhance the security of the second authentication.

[0073] In some embodiments of this disclosure, the number of correct payee identifiers and interfering identifiers in the identifier set, as well as the similarity between interfering identifiers and correct payee identifiers, are positively correlated with the risk level of the transfer request. Specifically, the higher the risk of the transfer request, the more difficult and numerous the correct payee identifiers are to identify, and the higher the number of interfering identifiers and their similarity to the correct payee identifiers.

[0074] In some embodiments of this disclosure, the risk level of a transfer request is determined based on one or more of the following: the transfer amount, the closeness between the transferor and the recipient, and the transferor's transaction method. For example, if the amount exceeds a preset security limit or exceeds the amount of a user's historical transaction habits, or if the current transfer is the first transfer or the recipient is a new account in the model, or if the transaction is executed on an uncommon device, in an uncommon region, or in an unfamiliar Wi-Fi network environment, then the current transfer request is deemed to have a risk. The specific risk level is determined comprehensively based on the severity of each risk item. Based on the risk level, an identifier set is generated; the randomly shuffled identifier set is presented to the transferor so that the transferor can confirm the correct recipient identifier. In response to the transferor's selection result in the identifier set, the accuracy rate of the transferor in identifying the correct recipient identifier is confirmed.

[0075] In some embodiments of this disclosure, the correct payee identifier in the identifier set is all or partial images of a preset payee image. This preset image is, for example, a portrait photo of the payee, which is a static standard photo actively provided and explicitly authorized for use in such identity verification scenarios when the payee performs real-name authentication or activates the payment function in this system. This preset image is shared in advance when a connection is established between the payee and the transferor. For example, when the payee and the transferor first establish trusted communication through a secure channel, the preset image is shared, and this sharing operation is performed on the basis of complete trust between the transferor and the payee. The system selects all or partial images from the preset image to generate the correct payee identifier. This correct payee identifier can be the original image of all or partial images, or it can be an image identifier formed after the system processes a portion of the all or partial image by marking, occluding, blurring, adding watermarks, etc. Interference identifiers are images generated by artificial intelligence that are similar to the correct payee identifier and originate from a preset material library. The portrait data stored in the material library are either data with authorized portrait rights or virtual portraits generated entirely by artificial intelligence.

[0076] In one embodiment of this disclosure, when generating the identifier set, the system does not select interfering identifiers completely randomly. Instead, it selects multiple interfering identifiers from a material library that have a preset similarity to the correct recipient identifier in global or local features, mixes them with the correct recipient identifier, and presents them in a random layout. The system randomly sorts the layout of all identifiers in this set to ensure that the correct identifier's position is not fixed each time it is presented, and then displays it to the transferor for selection.

[0077] In this embodiment, dynamically selecting interfering identifiers that meet a preset similarity level from a material library based on at least one facial feature of the correct recipient identifier is a core step in enhancing the security of the second identity verification. Specifically, the system first performs multi-dimensional facial feature analysis on the correct recipient identifier, extracting its global features (such as gender, age group, and facial contour) and local features (such as hairstyle, glasses style, and facial features). Then, according to preset similarity level rules, it filters out interfering options that are highly similar to the correct identifier in specified feature dimensions from a compliant material library containing authorized portraits or AI-generated virtual avatars. For example, when verifying a short-haired female recipient wearing glasses, the system dynamically generates a set of interfering identifiers that also possess the characteristics of "wearing glasses + short hair + female," forcing the transferor to identify the recipient based on precise memory of their specific appearance rather than generalized features. This method, by increasing the specificity of the interfering items, effectively prevents verification from being cracked through simple elimination, thus strengthening the reliability of cognitive verification and ensuring the compliance of the material source.

[0078] In the embodiments of this disclosure, during the process of the transferor identifying the correct recipient identifier, the system acquires the transferor's interactive behavior characteristics. These interactive behavior characteristics refer to the multi-dimensional quantitative data set generated by the transferor through the human-computer interaction interface during the identification task. This data can deeply reflect their cognitive decision-making process, operating habits, and potential physiological reactions. This feature system covers the following levels: At the visual attention level, the system acquires its characteristics by analyzing the transferor's eye-tracking data, including a heatmap of the distribution of gaze points across the identifier set, the path and speed of the gaze scanning between different options, the pupil dilation response that may occur when the correct option is identified, and the gaze stability pattern during the confirmation phase. At the operational behavior level, the system captures and analyzes the microscopic characteristics of its manual interaction, including the trajectory efficiency and tortuosity of the cursor or finger moving from the starting position to the final selection point, the hesitation points revealed by the speed change curve during the movement, the distribution of hovering time before selection, and whether there is repeated behavior of correction after clicking. At the biomechanical level, the system collects the physiological characteristics of its touch through device sensors, such as the pressure and contact area when clicking the screen, the micro-vibration patterns generated when holding the mobile device, and changes in the device's holding posture. Furthermore, the system analyzes these features within a time series to construct temporal behavioral patterns. For example, it categorizes and quantifies behavioral markers for different cognitive stages such as searching, confirming, and making decisions, and compares the overall pattern of the current interaction with the user's historical behavioral baseline. These multimodal interactive behavioral features collectively constitute a dynamic, continuous, and difficult-to-forge behavioral biometric. Its core innovative value lies in simultaneously transforming an explicit identity verification choice into an implicit, deep behavioral identity verification, thereby effectively resisting spying attacks, automated script attacks, and coerced transactions, significantly improving the security and reliability of the identity verification process.

[0079] In some embodiments of this disclosure, the second authentication is confirmed to be successful when the accuracy rate is higher than a first preset threshold and the matching degree between the interaction behavior features and the preset behavior baseline model is higher than a second preset threshold. Specifically, the system calculates two independent confidence scores in parallel: the first score is based on the accuracy rate of the selection result, which may take into account factors such as selection speed and whether the first selection is correct; the second score is based on the matching degree between the user's interaction behavior feature vector and the preset behavior baseline model built for them personally. Only when the accuracy rate is higher than the first preset threshold (e.g., 90%, indicating reliable cognitive results) and the matching degree between the interaction behavior features and the behavior baseline is higher than the second preset threshold (e.g., 85%, indicating credible behavior patterns), does the system finally confirm that the second authentication is successful overall.

[0080] After confirming the recipient's identity, execute operation S230 to complete the transfer.

[0081] In the embodiments disclosed herein, after successfully verifying the identities of the transferor and the recipient through dual authentication, a transfer operation page is displayed to the transferor, providing them with information such as the transfer amount and transfer method. After the transferor confirms the transfer operation, the transfer system immediately enters the core processing stage, executing operation S230 to complete the transfer. First, the system backend receives the final request sent by the frontend, containing all verification information, and initiates a critical database transaction. Within this transaction, the system atomically executes three core operations: precisely deducting the transfer amount from the transferor's account balance, simultaneously adding an equivalent amount to the recipient's account balance, and generating an immutable formal transaction record with a "success" status. Only after all these steps are completed without errors will the system commit the entire transaction, ensuring that the fund changes are permanently and securely updated to the database. Successful transaction commit signifies that the transfer transaction has been substantially completed. Subsequently, the system asynchronously triggers a notification mechanism to send a transaction success notification to both the transferor and the recipient. Simultaneously, a clear "transfer successful" signal and transaction serial number will be returned to the user interface, informing the user that the transfer operation has been successfully completed and the funds transfer has been confirmed. At this point, the entire process of operating S230 is complete.

[0082] Based on the aforementioned multi-factor authentication-based transfer method, this disclosure also provides a multi-factor authentication-based transfer device. The following will combine... Figure 4 The device is described in detail.

[0083] Figure 4 A schematic block diagram of a multi-factor authentication-based money transfer device according to an embodiment of the present disclosure is shown.

[0084] like Figure 4 As shown, the multi-factor authentication-based transfer device 400 of this embodiment includes a first authentication module 410, a second authentication module 420, and a transfer execution module 430.

[0085] The first authentication module 410 is used to perform a first authentication of the transferor in response to the transfer request. In one embodiment, the first authentication module 410 can be used to perform the operation S210 described above, which will not be repeated here.

[0086] The second authentication module 420 is used to perform a second authentication of the payee after the first authentication is successful. The second authentication includes: presenting the transferor with an identifier set containing at least one correct payee identifier and at least one interfering identifier; obtaining the accuracy rate at which the transferor identifies the correct payee identifier from the identifier set; finding that the number of correct payee identifiers and interfering identifiers, as well as the similarity between interfering identifiers and correct payee identifiers, are positively correlated with the risk level of the transfer request; obtaining the transferor's interaction behavior characteristics during the process of the transferor identifying the correct payee identifier; and confirming that the second authentication is successful based on the accuracy rate and interaction behavior characteristics. In one embodiment, the second authentication module 420 can be used to perform the operation S220 described above, which will not be repeated here.

[0087] The transfer execution module 430 is used to complete the transfer operation after the second authentication is successful. In one embodiment, the transfer execution module 430 can be used to perform the operation S230 described above, which will not be repeated here.

[0088] According to embodiments of this disclosure, any plurality of modules among the first authentication module 410, the second authentication module 420, and the transfer execution module 430 may be combined into one module, or any one of these modules may be split into multiple modules. Alternatively, at least a portion of the functionality of one or more of these modules may be combined with at least a portion of the functionality of other modules and implemented in one module. According to embodiments of this disclosure, at least one of the first authentication module 410, the second authentication module 420, and the transfer execution module 430 may be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, at least one of the first authentication module 410, the second authentication module 420, and the transfer execution module 430 may be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0089] Figure 5 A block diagram schematically illustrates an electronic device suitable for implementing a multi-factor authentication-based transfer method according to an embodiment of the present disclosure.

[0090] like Figure 5As shown, an electronic device 500 according to an embodiment of the present disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0091] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0092] According to embodiments of this disclosure, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.

[0093] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0094] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 502 and / or RAM 503 and / or one or more memories other than ROM 502 and RAM 503 described above.

[0095] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the multi-factor authentication-based transfer method provided in embodiments of this disclosure.

[0096] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0097] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0098] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0099] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0100] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0101] Those skilled in the art will understand that the features described in the various embodiments of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0102] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A transfer method based on multi-factor authentication, characterized in that, The method includes: In response to a transfer request from the transferor, perform the first authentication of the transferor; After the first authentication is successful, a second authentication is performed on the payee; After the second identity verification is successful, the transfer operation is completed; The second authentication includes: Present the transferor with a set of identifiers containing at least one correct recipient identifier and at least one interfering identifier, and obtain the accuracy rate at which the transferor identifies the correct recipient identifier from the identifier set. The number of correct recipient identifiers and interfering identifiers, as well as the similarity between the interfering identifier and the correct recipient identifier, are positively correlated with the risk level of the transfer request. During the process of the transferor identifying the correct recipient identifier, the interactive behavior characteristics of the transferor are obtained; Based on the accuracy rate and the interaction behavior characteristics, the second authentication is confirmed to be successful.

2. The method according to claim 1, characterized in that, The condition for triggering the first identity verification of the transferor is that the number of transfers made by the transferor within a preset period reaches a preset threshold.

3. The method according to claim 1, characterized in that, The first authentication of the transferor in response to the transfer request includes: Obtain the static portrait photo and the real-time facial image of the transferor's account that are pre-stored in the transferor's account; Based on the imaging environment interference factors in the real-time face image, the weights of each facial region in the static portrait photo and the real-time face image are dynamically configured; Based on the weights of each facial region, the weighted similarity between the static portrait photo and the real-time facial image is calculated; The identity of the transferor is confirmed based on the weighted similarity.

4. The method according to claim 3, characterized in that, The dynamic configuration of weights for each facial region in the static portrait photo and the real-time face image based on imaging environment interference factors in the real-time face image includes: When insufficient lighting is detected in the real-time face image, the weight of a preset facial region is increased. The preset facial region includes at least the image regions of the forehead, eyes, nose, mouth, and chin contours. When facial occlusion is detected in the real-time face image, the weight of the unoccluded area is increased.

5. The method according to claim 3, characterized in that, The step of confirming the identity of the transferor based on the weighted similarity includes: The weighted similarity is compared with a dynamic threshold; The dynamic threshold is adaptively adjusted based on the severity of the interference factors in the imaging environment.

6. The method according to claim 1, characterized in that, The step of presenting the transferor with a set of identifiers containing at least one correct recipient identifier and at least one interfering identifier, and obtaining the accuracy rate at which the transferor identifies the correct recipient identifier from the set of identifiers, includes: The risk level of the transfer request is determined based on one or more of the following: the amount transferred by the transferor, the closeness between the transferor and the recipient, and the transferor's transaction method. Based on the risk level, the identifier set is generated; Present the set of identifiers in a randomly shuffled order to the transferor; In response to the transferor's selection result in the set of identifiers, the accuracy of the transferor's identification of the correct recipient identifier is confirmed.

7. The method according to claim 1, characterized in that, The correct recipient identifier is generated based on the full or partial image of a preset image of the recipient, which is shared in advance between the transferor and the recipient. The interference identifier is an image generated by artificial intelligence that is similar to the correct recipient identifier.

8. The method according to claim 6, characterized in that, The step of confirming the second authentication pass based on the accuracy and the interaction behavior characteristics includes: When the accuracy rate is higher than the first preset threshold and the matching degree between the interaction behavior features and the preset behavior baseline model is higher than the second preset threshold, the second authentication is confirmed to be successful.

9. A transfer device based on multi-factor authentication, characterized in that, The device includes: The first authentication module is used to perform the first authentication of the transferor in response to the transfer request. The second authentication module is used to perform a second authentication of the payee after the first authentication is successful; The transfer execution module is used to complete the transfer operation after the second identity verification is passed; The second authentication includes: Present the transferor with a set of identifiers containing at least one correct recipient identifier and at least one interfering identifier, and obtain the accuracy rate at which the transferor identifies the correct recipient identifier from the identifier set. The number of correct recipient identifiers and interfering identifiers, as well as the similarity between the interfering identifier and the correct recipient identifier, are positively correlated with the risk level of the transfer request. During the process of the transferor identifying the correct recipient identifier, the interactive behavior characteristics of the transferor are obtained; Based on the accuracy rate and the interaction behavior characteristics, the second authentication is confirmed to be successful.

10. An electronic device, comprising: One or more processors; Memory, used to store one or more computer programs. The characteristic feature is that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by a processor, they implement the steps of the method according to any one of claims 1 to 8.

Images