Chargeback request processing method, apparatus, device, medium and program product

Abstract

A chargeback request processing method. The method is executed by a payment verification device, and comprises: receiving a payment evidence provision request for a completed payment sent by a chargeback request processing device, wherein the payment evidence provision request carries a payment identifier of the completed payment, the payment evidence provision request is sent by the chargeback request processing device upon reception of a chargeback request carrying the payment identifier, the completed payment is a payment that is made on the basis of a first biometric feature and has been successfully made, and the first biometric feature is a biometric feature of a first portion of a payer acquired during the payment process of the completed payment (S301); on the basis of the payment identifier, acquiring a second biometric feature corresponding to the completed payment, the second biometric feature being a biometric feature of a second portion of the payer acquired during the payment process of the completed payment (S302); and sending to the chargeback request processing device payment evidence information comprising the second biometric feature, such that the chargeback request processing device processes the chargeback request on the basis of the degree of matching between the biometric feature in the payment evidence information and a biometric feature of a chargeback requester (S303).

Description

Methods, apparatus, equipment, media, and procedures for processing chargeback requests.

[0001] Related applications

[0002] This application claims priority to Chinese patent application filed on October 23, 2024, application number 2024114871904, entitled "A method, apparatus, device, medium and procedure product for processing a denial of payment request", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of computer technology, and more specifically, it relates to a method, apparatus, device, medium, and program product for processing a chargeback request. Background Technology

[0004] In today's digital age, electronic payment systems have become an indispensable part of commercial transactions, greatly promoting the convenience and efficiency of global economic activities. Payment, as a core link in the transaction process, involves the transfer of funds from the payer's account to the payee's account, typically through various channels such as bank cards and third-party payment platforms. With technological advancements, payment systems not only require high levels of security and stability but also the flexibility to quickly respond to market changes and user needs.

[0005] However, in practice, the payment process is not always smooth. When disputes arise, such as when the payer believes a payment or transaction may be fraudulent or an incorrect transaction, the payee may face a chargeback request from the payer. A chargeback request is when the payer, through a bank or payment institution, requests the payee to reverse a completed payment transaction. This mechanism aims to protect consumer rights, but it also presents merchants with potential financial risks and operational challenges, especially when chargeback requests are frequent and lack reasonable grounds.

[0006] In the process of handling chargeback requests, evidence plays a crucial role in verifying whether a transaction was initiated by the payer and whether there was any fraudulent or erroneous use of the funds. Therefore, obtaining more reasonable evidence to accurately verify the transactions for which the payer has initiated chargeback requests becomes a key issue. Summary of the Invention

[0007] The purpose of this application is to provide a method, apparatus, device, medium, and program product for processing chargeback requests that can obtain more reasonable evidence to more accurately verify transactions initiated by the payer. To achieve the above objective, the technical solution provided by this application is as follows:

[0008] Firstly, a method for processing chargeback requests is provided, executed by a payment verification device, the method comprising:

[0009] The system receives a payment evidence provision request from a chargeback request processing device for a completed payment, wherein the payment evidence provision request carries a payment identifier indicating that the payment has been completed; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier; the completed payment is a payment made based on a first biometric feature and has been successfully completed; wherein the first biometric feature is a biometric feature of a first part of the payer collected during the payment process of the completed payment;

[0010] Based on the payment identifier, the second biometric feature corresponding to the completed payment is obtained; wherein, the second biometric feature is the biometric feature of the second part of the payer collected during the payment process of the completed payment;

[0011] The payment rejection request processing device sends payment evidence information including the second biometric feature to the payment rejection request processing device, so that the payment rejection request processing device processes the payment rejection request based on the degree of matching between the biometric feature in the payment evidence information and the biometric feature of the payment rejection requester.

[0012] Secondly, a method for handling chargebacks is provided, executed by a chargeback request processing device, the method comprising:

[0013] Send a payment evidence provision request to the payment verification device; wherein the payment evidence provision request carries a payment identifier corresponding to the completed payment; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier; the completed payment is a payment made based on a first biometric feature and has been successfully paid; wherein the first biometric feature is the biometric feature of a first part of the payer collected during the payment process of the completed payment;

[0014] The system receives payment evidence information, including a second biometric feature, sent by the payment verification device. The second biometric feature is obtained by the payment verification device based on the payment identifier. The second biometric feature is a biometric feature of a second part of the body collected during the payment process.

[0015] The degree of matching between the biometric features in the payment evidence information and the biometric features of the chargeback requester is determined, and the chargeback request is processed based on the degree of matching.

[0016] Thirdly, a device for processing chargeback requests is provided, the device being disposed in a payment verification device, the device comprising:

[0017] A payment evidence provision request receiving module is used to receive a payment evidence provision request for a completed payment sent by a chargeback request processing device. The payment evidence provision request carries a payment identifier indicating that the payment has been completed. The payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier. The completed payment is a payment made based on a first biometric feature and has been successfully completed. The first biometric feature is a biometric feature of a first part of the payer collected during the payment process of the completed payment.

[0018] The acquisition module is used to acquire the second biometric feature corresponding to the completed payment based on the payment identifier; wherein the second biometric feature is the biometric feature of the second part of the payer collected during the payment process of the completed payment;

[0019] The payment evidence information sending module is used to send payment evidence information including the second biometric feature to the chargeback request processing device, so that the chargeback request processing device can process the chargeback request based on the degree of matching between the biometric feature in the payment evidence information and the biometric feature of the chargeback requester.

[0020] Fourthly, an apparatus for processing chargebacks is provided, the apparatus being disposed in a chargeback request processing device, the apparatus comprising:

[0021] A payment evidence provision request sending module is used to send a payment evidence provision request to a payment verification device; wherein, the payment evidence provision request carries a payment identifier corresponding to the completed payment; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier; the completed payment is a payment made based on a first biometric feature and has been successfully paid; wherein, the first biometric feature is the biometric feature of a first part of the payer collected during the payment process of the completed payment;

[0022] The payment evidence information receiving module is used to receive payment evidence information including a second biometric feature sent by the payment verification device; the second biometric feature is obtained by the payment verification device based on the payment identifier; wherein, the second biometric feature is a biometric feature of a second part collected during the payment process;

[0023] The matching degree determination module is used to determine the degree of matching between the biometric features in the payment evidence information and the biometric features of the chargeback requester;

[0024] The chargeback request processing module is used to process the chargeback request based on the matching degree.

[0025] Fifthly, embodiments of this application also provide a payment verification device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the payment rejection request processing method provided by any possible implementation of the first aspect.

[0026] In a sixth aspect, embodiments of this application also provide a chargeback request processing device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the chargeback request processing method provided in any possible implementation of the second aspect.

[0027] In a seventh aspect, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements a method for processing a chargeback request provided by any possible implementation of the first or second aspect.

[0028] Eighthly, embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements a method for processing a chargeback request provided by any possible implementation of the first or second aspect.

[0029] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features, objects, and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the published drawings without creative effort.

[0031] Figure 1 is a schematic diagram of a chargeback request processing system according to an embodiment of this application;

[0032] Figure 2 is an example diagram of a chargeback request processing system according to an embodiment of this application;

[0033] Figure 3a is a flowchart of a method for processing a chargeback request in an embodiment of this application;

[0034] Figure 3b is an example diagram of a method for processing a chargeback request in an embodiment of this application;

[0035] Figure 4 is a flowchart of the payment feature collection device performing biometric feature collection in an embodiment of this application;

[0036] Figure 5 is a more detailed flowchart of the payment feature collection device performing biometric collection in the embodiments of this application;

[0037] Figure 6 is a flowchart of another method for processing a chargeback request in an embodiment of this application;

[0038] Figure 7 is a schematic diagram of the structure of a payment rejection request processing device according to an embodiment of this application;

[0039] Figure 8 is a schematic diagram of the structure of another payment rejection request processing device in an embodiment of this application;

[0040] Figure 9 is a schematic diagram of the device structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0041] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0042] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” can be implemented as “A,” or as “B,” or as “A and B.” When describing multiple (two or more) items, if the relationship between the multiple items is not explicitly defined, the multiple items can refer to one, several or all of the multiple items. For example, the description of "parameter A includes A1, A2, A3" can be implemented as parameter A includes A1 or A2 or A3, or it can be implemented as parameter A includes at least two of the three items A1, A2 and A3.

[0043] In related technologies, when a payer makes a payment offline via credit card or other electronic payment methods, the payer's identity can be verified through the following methods to complete the payment:

[0044] 1. After a cardholder swipes their credit card at an offline merchant, they sign the card. The cardholder's identity is verified by checking whether the signature matches the signature on the back of the card or in the bank's records. This verifies the cardholder's identity and prevents fraud.

[0045] 2. User 3D Secure: The user enters the mobile phone SMS verification code used to apply for the card or confirms identity and account information through the issuing bank's mobile banking app.

[0046] The signature verification and appeal process for the method shown in 1 is as follows:

[0047] Signature collection: When a cardholder makes a transaction, their signature is recorded on the transaction receipt. Merchants are responsible for verifying that the cardholder's signature matches the signature on the back of the credit card to initially verify the cardholder's identity.

[0048] Signature archiving: Merchants will keep signed receipts properly, usually for a certain period of time (such as several months to several years), for future verification.

[0049] Dispute Resolution: If a transaction is disputed (e.g., the cardholder denies making a transaction), the cardholder can appeal to the issuing bank. In this case, the issuing bank will require the merchant to provide a signed receipt as evidence.

[0050] Signature Verification: After receiving the signed receipt from the merchant, the issuing bank will verify it against the signature registered with the cardholder to confirm the authenticity of the transaction. If the signatures do not match, the bank may determine that the transaction is fraudulent and take appropriate measures.

[0051] However, this method may have the following drawbacks:

[0052] 1. Ease of forgery: User signatures may be easily forged, especially without strict verification, which means that the accuracy of the same verification is relatively low.

[0053] 2. Inconsistency: A user's signature may differ at different times or under different circumstances, making verification difficult and resulting in low accuracy.

[0054] 3. Poor user experience: Requiring user signatures may increase payment time and negatively impact user experience, especially during peak hours. Therefore, some merchants do not require verification.

[0055] In the method shown in Figure 2, the transaction is verified using 3DS, and the issuing bank will be responsible for fraudulent chargebacks. If the issuer and cardholder cannot resolve the dispute, the card network may intervene to conduct arbitration, making a final ruling based on the evidence provided by both parties, as detailed below:

[0056] 1. The user confirms payment, and the merchant places an order to initiate the transaction;

[0057] 2. The issuing bank requires the user to verify via SMS or authorize verification on the issuing bank's website / app;

[0058] 3. Once verification is successful, the payment will be deducted to complete the transaction;

[0059] 4. Dispute Resolution (Specific handling procedures if the payer believes there is a dispute regarding the payment, i.e., submits a chargeback request): If a transaction is disputed (e.g., the cardholder denies making a transaction), the cardholder can appeal to the issuing bank. In this case, the issuing bank will require the merchant to provide a signed receipt as evidence.

[0060] However, this method (3DS) may have the following drawbacks:

[0061] 1. User experience: 3DS often requires users to enter additional authentication information (such as passwords or one-time verification codes), which may make the payment process cumbersome and affect the user experience;

[0062] 2. It is forgeryable: Malicious users can give the verification information to another person for filling in and verification;

[0063] 3. High abandonment rate: Due to the additional authentication steps, some users may abandon the transaction, resulting in a decrease in conversion rate.

[0064] Before providing a further detailed description of the embodiments of this application, the nouns and terms involved in the embodiments of this application will be explained, and the nouns and terms involved in the embodiments of this application shall be interpreted as follows.

[0065] Chargeback: Also known as a chargeback, this refers to the right of a cardholder to refuse payment for a specific transaction on their statement within a certain period after payment (usually 120 days, but this can be extended to 540 days for some reasons). Chargeback is essentially a right granted to cardholders by credit card companies.

[0066] 3DS (3D Secure): Authenticates the cardholder's identity during transactions, or provides identity verification and account confirmation such as a PIN, SMS verification code, or confirmation via the issuing bank's mobile banking app. Implementation is typically the responsibility of the issuing bank.

[0067] To address the aforementioned technical problems, this application provides a method for processing chargeback requests. This method can be applied to a chargeback request processing system, as shown in Figure 1. The chargeback request processing system may include: a chargeback requester device, a payment feature collection device, a payment verification device, and a chargeback request processing device. The chargeback requester device interacts with the chargeback request processing device, the chargeback request processing device interacts with the payment verification device, and the payment verification device interacts with the payment feature collection device.

[0068] In one possible implementation, as shown in Figure 2, the chargeback request processing device can be: the issuing bank device (i.e., the device of the issuing bank through which the payment is made). The payment system can also include: the acquiring bank device, the merchant device (the device receiving the payment), etc. In this case, the chargeback requesting device interacts with the issuing bank device, the issuing bank device interacts with the acquiring bank device, the acquiring bank device interacts with the merchant device, the merchant device interacts with the payment verification device, and the payment verification device interacts with the payment feature collection device.

[0069] A payment verification device is specifically designed to receive payment evidence requests from the chargeback request processing device during the chargeback request handling process. Based on the payment identifier carried in the request, it retrieves the second biometric feature corresponding to the completed payment from the relevant storage location. This second biometric feature is the biometric signature of the payer's second part during the payment process. The payment verification device then sends the payment evidence information containing the second biometric feature to the chargeback request processing device, thereby assisting the latter in accurately processing the chargeback request. This functionality helps improve the legitimacy and accuracy of payment transaction verification.

[0070] The chargeback request processing device plays a central role in the entire payment chargeback processing system. When it receives a chargeback request carrying a payment identifier from the payer, it quickly generates a payment evidence provision request and sends it to the payment verification device. After receiving the payment evidence information from the payment verification device, the device matches the biometric features in the payment evidence information with the biometric features of the chargeback requester to determine the degree of match. Based on this degree of match, the chargeback request processing device makes an appropriate decision, such as rejecting or accepting the chargeback request, thereby completing the processing of the chargeback request and ensuring the fairness and security of the payment transaction.

[0071] Payment feature collection devices are the source of biometric data collection during the payment process. After the payment process is initiated, it responds to the payment request and uses its own collection function to acquire a biometric video stream containing the payer's first and second biometric features. Upon receiving payment success information, it stores the collected first and second biometric features of the payer in the payment evidence storage device, providing crucial evidence data for any subsequent potential chargeback requests and ensuring the traceability of the payment transaction.

[0072] Payment evidence storage devices are specifically designed to store payment-related biometric data. They associate each payment's identifier with the payer's secondary biometric data, while also storing the payer's primary biometric data. This stored data is encrypted and linked, managed through a specific storage key to ensure security and integrity. When a payment verification device needs to retrieve biometric data indicating a completed payment, the payment evidence storage device provides accurate data based on the corresponding key and identifier, offering robust data support for processing chargeback requests.

[0073] Based on the aforementioned payment system, this application provides a method for handling chargebacks, as shown in Figure 3a. This method is executed by a payment verification device, which can be the payment verification device shown in Figure 1 or Figure 2. The method may include:

[0074] Step S301: Receive a payment evidence provision request sent by the chargeback request processing device for a completed payment, wherein the payment evidence provision request carries a payment identifier for a completed payment; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying a payment identifier; the completed payment is a payment made based on a first biometric feature and has been successfully paid; the first biometric feature is the biometric feature of the first part of the payer collected during the payment process of the completed payment.

[0075] The payment evidence provision request carries a payment identifier indicating that the payment has been completed. This request is sent by the chargeback request processing device upon receiving a chargeback request carrying the payment identifier. In this embodiment, if an individual discovers a problem with a payment associated with their account, or that the payment was not their own, they can initiate a chargeback request. This chargeback request carries a payment identifier, which may include the transaction number corresponding to the completed payment. Furthermore, in addition to the payment identifier, the chargeback request may also carry the identity identifier of the party making the chargeback request.

[0076] A completed payment refers to a payment transaction in which funds have been successfully transferred based on the payer's primary biometric feature. During the payment process, the payment system collects biometric features from the payer's primary biometric feature (such as palm print) for identity verification; once verification is successful, the payment is completed. Simultaneously, the system also collects biometric features from the payer's secondary biometric feature (such as facial features), which will serve as crucial evidence for handling any subsequent chargeback requests.

[0077] A chargeback request is a request made by the payer, through a bank or payment institution, to the payee to cancel a completed payment transaction if the payer believes there is a problem, such as the possibility of fraud or incorrect transaction. This request must include a payment identifier that uniquely identifies the completed payment, and may also contain the payer's identification information, which is a key trigger for initiating the chargeback process.

[0078] Furthermore, the completed payment for the chargeback request initiated by the charging party is a payment made based on the first biometric feature and has been successfully completed; wherein, the first biometric feature is the biometric feature of a first part of the payer collected during the payment process. In this embodiment, the first part can be the palm, that is, the first biometric feature is the palmprint feature of the payer collected during the payment process, that is, the completed payment for the chargeback request initiated by the charging party has been verified through palmprint feature and has been successfully completed.

[0079] In this embodiment of the application, when the chargeback request processing device receives a chargeback request initiated by the chargeback requester, it generates a request to provide payment evidence for completed payment and sends it to the payment verification device.

[0080] Specifically, as shown in Figure 2, the chargeback request processing device can be the device of the issuing bank through which the payment was made. When the issuing bank's device receives the chargeback request, it generates a payment evidence provision request and sends the payment evidence provision request to the payment verification device through the acquiring bank's device and the merchant's device corresponding to the completed payment. Further, in this process, if the merchant's device receives the payment evidence provision request and can learn about the chargeback request from the chargeback requester, and if the merchant accepts the chargeback request, it does not need to send the payment evidence provision request to the payment verification device. Instead, it sends an agreement to the chargeback to the acquiring bank's device. The acquiring bank's device can then inform the issuing bank's device that the merchant agrees to the chargeback request from the chargeback requester, and the issuing bank's device returns the amount deducted from the completed payment, as shown in Figure 3b.

[0081] Acquiring bank equipment is an intermediary device in the payment transaction process. It receives payment evidence requests from chargeback processing devices (such as issuing bank equipment) and forwards them to merchant equipment. Simultaneously, acquiring bank equipment uses a specific matching algorithm to check the matching degree between biometric features in the payment evidence information, and then sends the check results to the chargeback processing device. In the entire chargeback processing flow, it plays a role in information transmission and preliminary verification.

[0082] Merchant equipment is directly related to payment transactions, responsible for receiving payment requests and processing payment transactions during the payment process. In the chargeback request processing flow, the merchant equipment receives a payment evidence provision request forwarded by the acquiring bank equipment. The merchant can then learn about the chargeback request from the requesting party. If the merchant accepts the chargeback request, they will send an agreement to the chargeback to the acquiring bank equipment; if they do not accept it, they will forward the payment evidence provision request to the payment verification equipment.

[0083] Step S302: Based on the payment identifier, obtain the second biometric feature corresponding to the completed payment; wherein, the second biometric feature is the biometric feature of the second part of the payer collected during the payment process of the completed payment.

[0084] The second biometric feature is the biometric feature of a second part of the payer collected during the payment process after payment has been completed. In this embodiment, the biometric feature of the payer's second part can be facial features, iris features, etc., and is not limited in this embodiment.

[0085] In this embodiment of the application, the biometric feature of the second part of the payer is taken as the payer's facial feature as an example. That is, after receiving a request to provide payment evidence carrying a payment identifier (serial number), the payment verification device obtains the facial features collected by the payment feature collection device during the payment process of the completed payment.

[0086] Step S303: Send payment evidence information including the second biometric feature to the payment rejection request processing device, so that the payment rejection request processing device can process the payment rejection request based on the degree of matching between the biometric feature in the payment evidence information and the biometric feature of the payment rejection requester.

[0087] Furthermore, after acquiring the facial features collected by the payment feature acquisition device during the payment process, the payment verification device sends payment evidence information including the facial features to the chargeback request processing device. Upon receiving the payment evidence information including the facial features, the chargeback request processing device matches the received payment evidence information including the facial features with the biometric features of the chargeback requester, and processes the chargeback request based on the degree of matching. In this embodiment, the chargeback request is processed at least based on the degree of matching between the facial features carried in the payment evidence information and the second biometric feature provided by the chargeback requester (i.e., the facial features of the chargeback requester).

[0088] Matching degree is a quantitative indicator that measures the similarity between the biometric features in payment evidence information and the biometric features of the chargeback requester. It comprehensively considers the matching of the second biometric feature (the biometric feature of the payer's second part during the payment process) with the fifth biometric feature of the chargeback requester's second part, and the matching of the third biometric feature (the biometric feature of the first part registered by the object corresponding to the payer's identifier) ​​with the fourth biometric feature of the chargeback requester's first part. The chargeback request processing device uses this matching degree to determine the reasonableness of the chargeback request and then makes an appropriate processing decision.

[0089] Specifically, in this embodiment, the second biometric feature (facial feature of the chargeback requester) of the chargeback requester can be collected or obtained by the chargeback request processing device. The second biometric feature of the chargeback requester can also be obtained from the chargeback request itself; in this case, the chargeback request can carry the second biometric feature of the chargeback requester.

[0090] Specifically, in the system shown in Figure 2, if the merchant does not accept the chargeback request, payment evidence information needs to be obtained from the payment verification device and sent to the acquiring bank device through the merchant device. The acquiring bank device will then check the matching degree between biometric features (such as facial features and palm print features collected during the payment process) in the payment evidence information based on a specific matching algorithm. For example, for facial features, the SIFT (Scale Invariant Feature Transform) algorithm is used to extract feature points, and the Euclidean distance between feature points is calculated to determine the matching degree; for palm print features, a comprehensive score is combined with multiple indicators such as clarity, completeness, distance, and brightness to measure the matching situation.

[0091] The acquiring bank's equipment sends the inspection results to the issuing bank's equipment, which then makes a chargeback decision based on these results. There are two main types of chargeback decisions: one is to reject the chargeback request, which means that the completed payment is determined to be free of fraud or misuse, and the payment status is maintained; the other is to accept the chargeback request, and return the successfully paid amount to the account of the party requesting the chargeback.

[0092] The issuing bank's device sends the processing result (i.e., the chargeback decision) of the chargeback request to the requesting party's device, whereby the requesting party decides whether to accept or reject the chargeback decision. If the requesting party accepts the chargeback decision, for example, by agreeing to reject the chargeback request and acknowledging that the payment was initiated by them, or by accepting the refund, the chargeback process is closed. Conversely, if the requesting party rejects the chargeback decision, for example, by believing that the issuing bank's decision to reject the chargeback request is unreasonable and insisting that there is a problem with the payment, they can resolve the chargeback request through other procedures. These other procedures may include providing further supplementary evidence, applying for arbitration, etc., and the specific methods are not limited, as shown in Figure 3b.

[0093] Furthermore, in some cases, the chargeback request processing device can be the issuing bank's device, or a combination of both issuing and acquiring bank devices. When the acquiring bank's device is included, it acts as a pass-through device, responsible for transmitting the payment evidence provision request and payment evidence, while the biometric matching and processing of the chargeback request based on the matching results are performed by the issuing bank's device, without specific limitations. Moreover, the processing of chargeback requests based on the degree of matching between the biometrics in the payment evidence information and the biometrics of the chargeback requester can also be handled manually by either the issuing bank or the acquiring bank.

[0094] This application provides a method for processing chargeback requests. In this method, when a chargeback request processing device receives a chargeback request carrying a payment identifier, and the completed payment corresponding to the payment identifier is a payment made based on a first biometric feature and has been successfully completed, the chargeback request device sends a request to a payment verification device for providing payment evidence for the completed payment. The payment verification device obtains the biometric feature of the second part of the payer collected during the payment process based on the payment identifier, and sends payment evidence information containing the biometric feature of the second part of the payer to the chargeback request processing device. This allows the chargeback request processing device to process the chargeback request based on the degree of matching between the biometric feature in the payment evidence information and the biometric feature of the chargeback requester. In other words, the payment evidence information obtained by the chargeback request processing device for completed payments carries the biometrics of a second part of the payer's body. This allows the device to match the biometrics of the payer's second part with those of the chargeback requester to determine whether the payer and the chargeback requester are the same. If they are the same, the completed payment was made by the chargeback requester. If they are not the same, the completed payment may not have been made by the chargeback requester. In other words, the evidence provided is the biometrics of another part of the payer's body during the payment process. This makes the evidence more reasonable for verifying whether the transaction for which the payer initiated the chargeback request was made by the payer himself, thus enabling accurate verification of the transaction for which the payer initiated the chargeback request.

[0095] Furthermore, after obtaining the payment identifier indicating completed payment through the payment evidence provision request, the payment verification device acquires the second biometric feature corresponding to the completed payment based on the payment identifier. Specifically, in this embodiment, step S302, acquiring the second biometric feature corresponding to the completed payment based on the payment identifier, may include: sending a biometric feature acquisition request to the payment evidence storage device; and receiving the second biometric feature corresponding to the completed payment sent by the payment evidence storage device.

[0096] The biometric acquisition request includes a payment identifier; the payment evidence storage device stores the biometric features of the second part of the payer corresponding to the payment identifier of each payment.

[0097] As can be seen from the above embodiments, the biometric feature of the second part can be a facial feature, that is, the payment evidence storage device stores the facial features of the payer corresponding to the payment identifier of each payment. Specifically, the facial features of the payer corresponding to the payment identifier of each payment are the facial features of the payer collected by the payment feature collection device during the payment process. In other words, during the payment process of a payment, the payment feature collection device collects not only the payer's palm print features but also their facial features. As mentioned above, collecting the payer's palm print features is to find the payer's identifier so that the corresponding amount can be deducted from the corresponding account; collecting the payer's facial features during the payment process is to provide evidence for the chargeback request, to verify whether the chargeback requester and the payer are consistent, and to determine whether the completed payment corresponding to the chargeback request constitutes fraud or a mistaken transaction.

[0098] Furthermore, for a single payment process, the corresponding payment evidence information is collected by the payment feature collection device. Similarly, for completed payments, the corresponding payment evidence information is also collected by the payment feature collection device. In this embodiment, the payment evidence information corresponding to completed payments is collected by the payment feature collection device through the following methods (steps Sa and Sb) and stored in the payment evidence storage device. In this embodiment, the payment evidence storage device can be a cloud storage device, another storage device, or a storage device within the payment verification device. See Figure 4 for details.

[0099] Step Sa: Receive payment requests for completed payments.

[0100] In this embodiment of the application, the cash register (e.g., POS) initiates payment and transmits a payment identifier (serial number) carrying the completed payment to the payment feature collection device. At this time, the payment feature collection device receives a payment request for the completed payment.

[0101] Step Sb: In response to the payment request, acquire the biometric video stream, and upon receiving the payment success information, store the payer's first and second biometric features in the payment evidence storage device.

[0102] The biometric video stream includes at least the payer's first and second biometric features.

[0103] Specifically, in step Sb, the biometric data acquisition video stream is obtained, and upon receiving the payment success message, the second biometric feature is stored in the payment evidence storage device. This may include steps Sb1, Sb2, Sb3, Sb4, and Sb5, where steps Sb1-Sb5 are not shown in the figure.

[0104] Step Sb1: Acquire the first video frame.

[0105] The first video frame contains the second biometric feature corresponding to the payer.

[0106] In this embodiment of the application, after receiving a payment request from the cash register, the payment feature acquisition device starts shooting and acquires a first video frame containing the second biometric feature corresponding to the payer, that is, before scanning the palm print feature, it acquires the payer's facial features.

[0107] Step Sb2: Output the first prompt message.

[0108] The first prompt message is used to prompt the payer to provide a first biometric feature. In this embodiment, after the payment feature acquisition device acquires the first video frame, it outputs a prompt message to prompt the payer to provide the first biometric feature. That is, when the first video frame containing the payer's facial features is acquired, the payer is reminded to extend their palm and acquire the corresponding palm print feature.

[0109] Step Sb3: Acquire a second video frame containing the first biometric feature. That is, the biometric acquisition device acquires a second video frame containing the payer's palm print features.

[0110] Specifically, when the biometric acquisition device acquires a second video frame containing palmprint features, in order to improve the accuracy of palmprint verification and reduce the storage space required to store the payer's palmprint features, it can extract a preferred frame from the video stream containing the payer's palmprint features as the second video frame. The preferred frame is the video frame containing a clear and complete palmprint. It can also include the distance between the palm and the biometric acquisition device being appropriate, as well as the appropriate brightness of the acquired video frame.

[0111] A multi-index evaluation method is used to extract preferred frames from video streams containing payer palmprint features. Specifically, the following steps can be taken:

[0112] Sharpness assessment: The Laplacian variance is calculated for each frame of the video stream. A larger Laplacian variance indicates a sharper image. The formula is as follows: Where V laplace Represents the Laplace variance. This indicates that a Laplacian transform is performed on image I, and Var indicates the calculation of variance.

[0113] Integrity assessment: Edge detection algorithms (such as the Canny algorithm) are used to detect the edges of the palm print, and the perimeter and area of ​​the edges are calculated. If the perimeter and area are within a preset reasonable range, the palm print is considered complete.

[0114] Distance assessment: The distance between the palm and the biometric acquisition device is measured by a depth sensor. If the distance is within a preset moderate range, a higher score is given.

[0115] Brightness Assessment: The average brightness of the image is calculated. If the average brightness is within a preset suitable range, the brightness is considered appropriate. The scores of the above assessment indicators are weighted and summed to obtain the comprehensive score for each frame of the image. The weights of each assessment indicator are determined as follows: First, a certain number of sample video frames containing palmprint features are collected, and the best frames are manually labeled. Then, these sample data are used to train a linear regression model, with the comprehensive score as the target variable and the scores of each assessment indicator as independent variables. After training, the coefficients of the model are the weights of each assessment indicator. The formula is S. total =w1×S clarity +w2×S integrity +w3×S distance +w4×S brightness S total This represents the overall score, where w1, w2, w3, and w4 represent the weights of the evaluation indicators for sharpness, integrity, distance, and brightness, respectively, and w1 + w2 + w3 + w4 = 1. clarity S represents the sharpness score. integrity S represents the completeness score. distance S represents the distance score. brightness This represents the brightness score. The frame with the highest overall score is selected as the preferred frame and used as the second video frame.

[0116] Step Sb4: If a payment success message is received, and when the first part of the payer is detected to be out of the shooting range, a third video frame including the second biometric feature of the payer is captured.

[0117] In this embodiment of the application, the payment feature acquisition device can send the preferred frame to the payment verification device for matching verification. That is, the payment verification device determines the matching payer from the first biometric features corresponding to each payer to complete the payment. At this time, the payment verification device sends a payment success message to the payment feature acquisition device. When the payment feature acquisition device receives the payment success message, it can output a second prompt message. The second prompt message is used to prompt the payer that the payment verification based on the first biometric feature is successful. At this time, the payer's palm can leave the shooting range. When the payer's palm leaves the shooting range, a third video frame including the payer's second biometric feature (facial feature) is acquired.

[0118] In this embodiment, it should be noted that the first video frame, the second video frame, and the third video frame can all be frame sequences, i.e., multiple frames of images. Of course, they can also be a single frame of images; this is not limited in this embodiment. Furthermore, in this embodiment, the collection of the biometric features of the first and second parts of the payer's body during the payment process is authorized and agreed upon by the payer.

[0119] Step Sb5: Send the first video frame, the third video frame, and the corresponding payment identifier to the payment evidence storage device, so that the payment evidence storage device stores the second biometric feature contained in the first video frame, the second biometric feature contained in the third video frame, and the payment identifier in association.

[0120] Furthermore, it should be noted that the payment evidence storage device may also store the second biometric feature contained in the first video frame, the first biometric feature contained in the second video frame, the second biometric feature contained in the third video frame, and the payment identifier.

[0121] Specifically, after acquiring the first video frame, the second video frame, and the third video frame, the payment acquisition device can extract the corresponding biometric features from each video frame, that is, obtain the second biometric feature from the first video frame, obtain the first biometric feature from the second video frame, and obtain the second biometric feature from the third video frame, and store these biometric features and payment identifiers in the payment evidence storage device. In another possible implementation, the payment evidence storage device or other devices can also extract the corresponding biometric features from each video frame and store these biometric features and payment identifiers in the payment evidence storage device.

[0122] Furthermore, it should be noted that the payment evidence storage device can also directly store video frames, meaning it can directly store the first video frame, the third video frame, and the payment identifier. Specifically, it can also store the second video frame, meaning the payment evidence storage device can also store the first video frame, the second video frame, the third video frame, and the payment identifier. In this embodiment, if the payment evidence storage device stores at least the first video frame, the third video frame, and the payment identifier, then when the payment verification device receives a payment evidence provision request, it retrieves the first and third video frames (and may also include the second video frame) from the payment evidence storage device based on the payment identifier carried in the payment evidence provision request, and sends the first and third video frames (and may also include the second video frame) to the chargeback request processing device.

[0123] The specific method by which the chargeback request processing device extracts the corresponding second biometric features from the first and third video frames is as follows: For the first and third video frames, image preprocessing is first performed, including grayscale conversion, transforming the color image into a grayscale image to reduce data volume and computational complexity; then, histogram equalization is performed to enhance image contrast and make features in the image more prominent. Next, a face detection algorithm (such as a Haar cascade classifier or a deep learning-based face detection algorithm) is used to detect face regions in the preprocessed image. After detecting face regions, a feature extraction algorithm (such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), or a deep learning-based feature extraction network) is used to extract the second biometric features (such as facial feature vectors) from the face regions. Finally, the second biometric features corresponding to the first and third video frames are obtained.

[0124] A specific example of steps Sb1-Sb5 is shown in Figure 5, wherein...

[0125] 1. The POS terminal initiates payment and transmits the transaction number to the swipe terminal (payment feature collection device);

[0126] 2. Take a photo with your palm on the terminal, then be prompted to extend your palm. The photo taken in this step serves as the first frame of the proof, which is the first video frame shown above.

[0127] 3. The palm-scanning terminal continuously captures and detects the palm print; if the palm-scanning terminal does not detect the palm print in this step, return to step 2.

[0128] 4. Select the preferred image from the video stream captured in step 3, and send the preferred image as the intermediate frame of the credential to the backend server (payment verification device) for recognition; if the palm-swiping terminal does not obtain the preferred frame, return to step 3 to repeat capturing the palm print features.

[0129] 5. If the backend server successfully identifies the device, the swipe terminal will display a success message.

[0130] 6. At this point, the swipe terminal needs to search again, take a picture when the palm leaves, and use the frame taken when the palm leaves as the last frame;

[0131] 7. The swipe terminal sends the first frame, preferred frame, and last frame of the credential, along with the serial number, to the cloud device for associated storage. The communication between the swipe terminal and the cloud storage device is encrypted using Transport Layer Security (TLS).

[0132] Furthermore, during each payment process, the biometric data collected by the payment feature collection device is stored in the payment evidence storage device. This means the payment evidence storage device encrypts and associates the biometric data of each payer's second biometric component with a storage key. The biometric data of each payer's second biometric component is encrypted using an encryption algorithm, such as SM4. To further enhance security, the storage key is calculated using a specific algorithm (e.g., SHA64) based on the payment identifier (e.g., transaction number), payer identifier (payer identity ID), device number (device identifier of the payment feature collection device), and an initial key. The initial key is stored in the secure element (SE) of the payment feature collection device. Specifically, the payment feature collection device can also encrypt and associate the biometric data of each payer's video frames (first video frame, second video frame, and third video frame) with the storage key.

[0133] Furthermore, since the second biometric features corresponding to each payer are stored in the payment evidence storage device using the aforementioned encryption method, step S302, which involves obtaining the second biometric feature corresponding to the completed payment based on the payment identifier, may specifically include: determining the payer identifier corresponding to the completed payment based on the payment identifier; obtaining the device identifier and initial key from the payment feature acquisition device corresponding to the completed payment; encrypting the payment identifier, payer identifier, device identifier, and initial key to obtain a biometric feature storage encryption key; and obtaining the second biometric feature corresponding to the completed payment from the payment evidence storage device based on the biometric feature storage encryption key.

[0134] The SHA64 algorithm can be used to encrypt the payment identifier, payer identifier, device identifier, and initial key to obtain the biometric storage encryption key. The specific steps are as follows: First, concatenate the payment identifier, payer identifier, device identifier, and initial key into a new string. Then, input this string into the SHA64 algorithm for hash calculation, obtaining a 64-bit hash value. This hash value is the biometric storage encryption key. The formula is K = sha64(concat(PID, UID, DID, IK)), where K represents the biometric storage encryption key, PID represents the payment identifier, UID represents the payer identifier, DID represents the device identifier, IK represents the initial key, and concat represents the string concatenation operation.

[0135] In this embodiment, the encrypted second biometric feature (the second biometric feature corresponding to the completed payment) is obtained from the payment evidence storage device based on the biometric feature storage encryption key. Of course, the payment evidence storage device may not directly store the second biometric features corresponding to each payer, but instead store video frames (first video frame, second video frame, and third video frame) corresponding to each payer. Based on the above embodiment, specifically, in step S303, the payment verification device sends payment evidence information including the second biometric feature to the chargeback request processing device, which may specifically include: the payment verification device sending payment evidence information including the first video frame and the third video frame to the chargeback request processing device.

[0136] In this process, the payment verification device sends payment evidence information containing a first video frame and a third video frame to the chargeback request processing device. The first and third video frames in the payment evidence information are encrypted, and the chargeback request processing device needs to decrypt them to obtain the decrypted first and third video frames. Alternatively, after obtaining the encrypted first and third video frames from the payment evidence information, the payment verification device may decrypt them before sending them to the chargeback request processing device. It should be noted that the payment evidence information sent by the payment verification device to the chargeback request processing device may also include a related second video frame, or it may not include one; this is not limited in this embodiment. Furthermore, as can be seen from the above embodiments, for a single payment (payment completed), the chargeback request processing device can at least obtain: the second biometric feature corresponding to the first video frame and the second biometric feature corresponding to the third video frame. Under the condition that the second biometric feature contained in the first video frame matches the second biometric feature contained in the third video frame (that is, when the same facial feature exists in the facial features contained in the first and third video frames, i.e., the same face exists), the chargeback request processing device processes the chargeback request in the following manner (steps S1 and S2). Specifically, steps S1 and S2 are not shown in the figure. The features of the chargeback requester mentioned above include: the fifth biometric feature of the second part of the chargeback requester, for example, the fifth biometric feature of the second part of the chargeback requester is also the facial feature of the chargeback requester.

[0137] Step S1: If the fifth biometric feature of the second part of the chargeback requester matches the specified second biometric feature, then the chargeback request is rejected and a first notification message is sent to the chargeback requester.

[0138] Wherein, the second biometric feature is specified as the second biometric feature contained in the first video frame or the third video frame; in this embodiment of the application, if the fifth biometric feature of the second part of the chargeback requester matches the specified second biometric feature, it indicates that the facial features collected during the actual payment process are consistent with the facial features of the chargeback requester, that is, at this time, it indicates that the probability of the completed payment being a fraudulent or erroneous transaction is low. At this time, the chargeback request processing device rejects the above chargeback request and sends a first notification message to the chargeback requester. The first notification message carries the matching result of the second biometric feature and is used to notify the chargeback requester that the chargeback request processing device has rejected the chargeback request.

[0139] Step S2: If the fifth biometric feature of the second part of the chargeback requester does not match the designated second biometric feature, the chargeback request is accepted and the successfully paid amount is returned to the chargeback requester's account.

[0140] In this embodiment of the application, if the fifth biometric feature of the second part of the chargeback requester does not match the designated second biometric feature, it indicates that the facial features collected during the actual payment process are inconsistent with the facial features of the chargeback requester. In other words, the probability of the completed payment being fraudulent or mistaken is high. At this time, the chargeback request processing device agrees to the chargeback request and returns the successfully paid amount to the chargeback requester's account. Of course, to improve security and accuracy, other errors can be used to verify again before making a corresponding chargeback decision (a decision made based on the chargeback request).

[0141] Furthermore, if the second biometric feature contained in the first video frame matches the second biometric feature contained in the third video frame, and the fifth biometric feature of the second part of the chargeback requester does not match the specified second biometric feature, it indicates that the facial features collected during the actual payment process are inconsistent with the facial features of the chargeback requester. This means that the probability of the completed payment being fraudulent or incorrect is high. In this case, the chargeback request processing device executes steps S3, S4, and S5 (not shown in the figure). Steps S3-S5 and steps S1-S2 do not have a strict sequential execution order. Specifically...

[0142] Step S3: Match the second biometric feature of the specified second biometric feature with the second biometric feature of the object that is associated with the chargeback requester.

[0143] In this embodiment of the application, the account of the chargeback requester (the account for which payment has been completed) may be bound not only to the first biometric feature (i.e., palm print feature) of the first part of the chargeback requester's body, but also to the palm print features of other objects with which it is associated, such as the palm print features of relatives. That is, the completed payment may also have been made by an associated object by scanning its palm print. In this case, the facial features of the chargeback requester are inconsistent with the facial features collected during the payment process (facial features in the first and third video frames). At this time, the facial features of objects with which the chargeback requester is associated are obtained (this acquisition function is agreed to by the chargeback requester or provided by the chargeback requester), and then the facial features in the first and third video frames are matched with the facial features of objects with which the chargeback requester is associated.

[0144] For example, objects associated with the party requesting a chargeback may include: object 1 and object 2, which means matching the facial features of object 1 and object 2 with the facial features in the first and third video frames.

[0145] Step S4: If there is an associated matching object among the objects with the same second biometric feature, then send a second notification message carrying the second biometric feature of the associated matching object to the party requesting the chargeback.

[0146] For example, if the facial features of object 1 match the facial features in the first video frame and the third video frame, a second notification message carrying the facial features of object 1 is sent to the party requesting the chargeback.

[0147] The second notification message, which notifies the party requesting the chargeback that payment has been completed, was made by the associated matching object.

[0148] Step S5: Receive the response from the party requesting the chargeback in response to the second notification message, and process the chargeback request based on the response.

[0149] In this embodiment of the application, after receiving the second notification message, if the party requesting the chargeback acknowledges it, it sends a reply message to the chargeback request processing device, indicating that the party accepts the completed payment (or accepts the withdrawal of the chargeback request), at which point the process can end. If the reply message indicates that the party does not accept the chargeback request, the chargeback request processing device can reject the chargeback request, send it to another organization's device for processing, or process it in other ways, without limitation.

[0150] Furthermore, under the condition that the second biometric feature contained in the first video frame does not match the second biometric feature contained in the third video frame, that is, the facial features collected by the payment feature collection device in the video frames before and after payment do not match, that is, the facial features collected in the first video frame and the facial features collected in the third video frame are not the facial features of the same person; in order to reasonably process the submitted biometric features and accurately process the chargeback request, the chargeback request processing device processes the chargeback request through steps S6 and S7 (not shown in the figure), wherein steps S6-S7 and steps S1-S5 above do not have a strict sequential execution order, specifically,

[0151] Step S6: If the second biometric feature contained in the first video frame matches the second biometric feature of the party requesting the chargeback, then according to the payment time corresponding to the completed payment, obtain the seventh biometric feature corresponding to the first party who has completed the payment, and match the seventh biometric feature with the second biometric feature contained in the third video frame, and process the chargeback request based on the matching result.

[0152] In this embodiment of the application, the second biometric feature contained in the first video frame matches the second biometric feature of the chargeback requester. That is, the payment feature acquisition device may have acquired the payer's facial features before the payer makes payment (before the second video frame), but not after the payer makes payment. At this time, the chargeback request processing device obtains the facial features corresponding to the first completed payer from the payment verification device to match the facial features contained in the third video frame.

[0153] Among them, the first completed payer is the payer who completes payment after the previous payment has been completed; and the seventh biometric feature is the biometric feature of the second part corresponding to the first completed payer.

[0154] Furthermore, if the chargeback request processing device obtains the facial features corresponding to the first completed payment party from the payment verification device and matches them with the facial features contained in the third video frame, and the match is successful, it indicates that there was no swiping error. In this case, the chargeback request is rejected, or other measures are taken to process the chargeback request. This is not limited in the embodiments of this application.

[0155] Step S7: If the second biometric feature contained in the third video frame matches the second biometric feature of the chargeback requester, then according to the payment time corresponding to the completed payment, obtain the eighth biometric feature corresponding to the second completed payment party, and match the eighth biometric feature with the second biometric feature contained in the first video frame, and process the chargeback request based on the matching result.

[0156] In this embodiment of the application, the second biometric feature contained in the third video frame matches the second biometric feature of the chargeback requester. That is, the payment feature acquisition device may have acquired the payer's facial features after the payer has made payment (the second video frame), but it did not acquire the payer's facial features before the payer made payment. At this time, the chargeback request processing device obtains the facial features corresponding to the second completed payer from the payment verification device to match the facial features contained in the first video frame.

[0157] Among them, the second completed payer is the payer who completed the payment before the completed payment; and the eighth biometric feature is the biometric feature of the second part corresponding to the second completed payer.

[0158] Furthermore, if the chargeback request processing device obtains the facial features corresponding to the second completed payment party from the payment verification device and matches them with the facial features contained in the first video frame, and the match is successful, it indicates that there was no swiping error. In this case, the chargeback request is rejected, or other measures are taken to process the chargeback request. This is not limited in the embodiments of this application.

[0159] Furthermore, in some cases, the party requesting a chargeback may mistakenly bind the wrong biometric identifier (palmprint) to an account, for example, binding the biometric identifier of someone else. To improve the accuracy of chargeback request processing, after obtaining the payment identifier of a completed payment, the method may further include: determining the payer identifier corresponding to the completed payment based on the payment identifier; and determining the third biometric identifier bound to the payer identifier. Specifically, based on the payment identifier, the payment verification device determines the payer identifier corresponding to the completed payment by querying a pre-built association table of payment identifiers and payer identifiers in a local database. The construction process of this association table is as follows: upon completion of each payment, the payment verification device receives the payment identifier (e.g., transaction number) and payer identifier (e.g., payment recipient identifier) ​​sent by the payment feature collection device and stores the correspondence between these two in the association table of the local database. The association table uses the payment identifier as an index for convenient and fast querying. If no relevant information is found in the local database, a query request is sent to the cloud storage device, which then searches its massive stored transaction data based on the payment identifier. During the search, the cloud storage device partitions the stored data, dividing it according to dimensions such as payment time and payment amount to improve search efficiency. After finding the corresponding payer identifier, it is sent to the payment verification device.

[0160] In this embodiment of the application, after obtaining the payment identifier of the completed payment through the payment evidence provision request, the payer identifier corresponding to the completed payment is determined based on the payment identifier. That is, the payment verification device may store the mapping relationship between the payment identifier and the payer identifier, or it may obtain the mapping relationship between the payment identifier and the payer identifier from other devices (such as cloud storage devices).

[0161] Furthermore, in another possible implementation, the payment verification device carries a payer identifier in the payment evidence provision request received. In this embodiment, the payer identifier carried in the payment evidence provision request can be carried in the chargeback request triggered by the chargeback requesting party, or it can be determined by the chargeback request processing device after receiving the chargeback request based on the payment identifier carried in the chargeback request, and then carried in the payment evidence provision request.

[0162] For example, the payment identifier is the transaction number of a completed payment, and the payer identifier is the identity ID of the actual payer who completed the payment.

[0163] Furthermore, after obtaining the payer identifier (the identity ID of the actual payer who completed the payment) corresponding to the completed payment, the payment verification device determines the third biometric feature bound to the payer identifier. This third biometric feature is the biometric feature of the first part registered by the object corresponding to the payer identifier. As shown in the above embodiments, the first part of the biometric feature can be a palm print, meaning the third biometric feature is the palm print feature registered by the object corresponding to the payer identifier (also known as a payment-associated palm print feature). In other words, for each payment, if the palm print feature collected by the payment collection device matches the payment-associated palm print feature, the verification is successful, allowing the amount corresponding to the payment to be deducted from the account corresponding to the payer identifier. For example, if payer 1 purchases apples for 10 yuan, and payer 1 matches the payment-associated palm print feature by swiping their palm, then 10 yuan will be deducted from the account bound to the payment-associated palm print feature and transferred to the merchant's account. Payment-associated palmprint features are the palmprint features registered by the object corresponding to the payer's identifier. Each time a payment is made, the payment collection device matches the collected palmprint features with these payment-associated palmprint features. If the match is successful, the verification is passed, and the corresponding amount can be deducted from the account corresponding to the payer's identifier. This is one of the important bases for payment verification.

[0164] To enhance the credibility of the evidence provided and to more accurately verify transactions initiating chargeback requests by the payer, the payment verification device may further include the following in the payment evidence provided to the chargeback request processing device: a third biometric feature, namely, the biometric feature of the first part registered by the object corresponding to the payer's identifier. As can be seen from the above embodiments, the biometric feature of the first part can be a palm print feature, and the third biometric feature is the palm print feature (payment-associated palm print feature) of the actual payer who has completed the payment and is bound to a certain electronic account (electronic account 1). In other words, during the payment process, if the payment verification device matches the corresponding palm print feature, it indicates that the verification is successful, and the corresponding amount can be deducted from electronic account 1.

[0165] Furthermore, the biometrics of the chargeback requester include the fourth biometric feature of the first part of the requester's body and the fifth biometric feature of the second part of the body. The matching degree includes the matching degree between the second and fifth biometric features, as well as the matching degree between the third and fourth biometric features. That is to say, in the above embodiment, when processing the chargeback request based on the matching degree between the biometric features in the payment evidence information and the biometric features of the chargeback requester, in addition to matching based on the fifth biometric feature (facial features) and the second biometric feature (facial features collected during the payment process) of the chargeback requester, it is also necessary to match based on the fourth biometric feature (palmprint) of the first part of the requester's body and the fifth biometric feature (palmprint features of the account) bound to the account. If both of the above matching results are higher than the preset matching degree, it indicates that the chargeback requester in the chargeback request and the payer collected during the actual payment process are the same person, that is, there is no case of fraudulent use or wrong transaction (the payer of the subsequent payment or the payer of the previous payment made a wrong transaction), and the chargeback request is rejected; other cases are detailed in the above embodiment and will not be repeated here.

[0166] This application embodiment also provides another method for processing chargeback requests, executed by a chargeback request processing device, as shown in FIG6. The method may include:

[0167] Step S601: Send a payment evidence provision request to the payment verification device; wherein, the payment evidence provision request carries the payment identifier corresponding to the completed payment; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier; the completed payment is a payment based on the first biometric feature and has been successfully paid; the first biometric feature is the biometric feature of the first part of the payer collected during the payment process of the completed payment.

[0168] The payment evidence provision request carries a payment identifier corresponding to the completed payment; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying a payment identifier; the completed payment is a payment made based on the first biometric feature and has been successfully paid; the first biometric feature is the biometric feature of the first part of the payer collected during the payment process of the completed payment.

[0169] Step S602: Receive payment evidence information including a second biometric feature sent by the payment verification device; the second biometric feature is obtained by the payment verification device based on the payment identifier; wherein, the second biometric feature is the biometric feature of the second part collected during the payment process.

[0170] The second biometric feature is obtained by the payment verification device based on the payment identifier; the second biometric feature is the biometric feature of the second part collected during the payment process.

[0171] Step S603: Determine the degree of matching between the biometrics in the payment evidence information and the biometrics of the chargeback requester, and process the chargeback request based on the degree of matching.

[0172] Specifically, the second biometric feature includes: second biometric feature information corresponding to two video frames respectively. One video frame is a video frame collected by the payment feature collection device before collecting the first biometric feature of the payer, and the other video frame is a video frame collected by the payment feature collection device when it detects that the first biometric feature of the payer has left the shooting range.

[0173] In step S603, determining the degree of matching between the biometrics in the payment evidence information and the biometrics of the person requesting the payment refusal, and processing the payment refusal request based on the degree of matching, may specifically include: obtaining the fifth biometric of the second part of the person requesting the payment refusal; determining the degree of matching between the biometrics in the payment evidence information and the biometrics of the person requesting the payment refusal based on the second biometric information and the fifth biometric of the two video frames respectively; and processing the payment refusal request based on the degree of matching.

[0174] One approach is to use a feature point matching algorithm to determine the degree of matching. First, feature extraction is performed on the second and fifth biometric information corresponding to the two video frames, resulting in their respective feature point sets. Then, the SIFT (Scale Invariant Feature Transform) algorithm is used to find matching feature point pairs within these sets. Matching feature point pairs are combinations of corresponding feature points found from their respective feature point sets when matching two biometric information pieces using a feature point matching algorithm (such as SIFT). The Euclidean distance between the feature vectors of these matching feature point pairs is calculated, and the summation and averaging of all matching feature point pairs' Euclidean distances yields the average Euclidean distance. The reciprocal of this average Euclidean distance is then used as the degree of matching to determine the similarity between biometric features.

[0175] For each matching feature point pair, calculate the Euclidean distance between their feature vectors. Sum the Euclidean distances of all matching feature point pairs and take the average to obtain the mean Euclidean distance. Finally, use the reciprocal of the mean Euclidean distance as the degree of matching. The formula is as follows: Where M represents the matching degree, n represents the number of matched feature point pairs, and d i Let represent the Euclidean distance between the i-th matching feature point pair.

[0176] It should be noted that the process executed by the chargeback request processing device in this application embodiment is detailed in the above embodiment and will not be repeated here.

[0177] To better understand and illustrate the practical value of the solutions provided in the embodiments of this application, the optional implementation methods of this application will be described below in conjunction with specific scenario embodiments.

[0178] I. Payment Process:

[0179] 1. The POS terminal sends a payment request to the swipe terminal. The payment request carries the transaction number of the bill being paid. This payment will be referred to as payment 1 in the following text.

[0180] 2. The palm-swiping terminal starts taking pictures and obtains several frames of images before the palm swipe, which are used to capture the facial features of the person to be swiped for payment, as the initial frame.

[0181] 3. Prompt the recipient to extend their palm for fingerprint scanning;

[0182] 4. After the palm-swiping terminal detects the payment palm, it takes a picture of the palm print. Specifically, when the palm-swiping terminal detects the payment palm print, it can take a picture of the palm print for a preset time period and then remind the payment recipient to move their palm. Alternatively, when a clear and complete palm print is detected and captured, it can remind the payment recipient to move their palm. In this case, the clear and complete palm print is selected as the preferred frame.

[0183] 5. The swipe terminal sends the selected frame (preferred frame) to the backend server for identification to determine the identity of the payment recipient, and then sends it to the card issuer so that the card issuer can deduct the payment from the corresponding account;

[0184] 6. When the backend server recognizes a matching palm print, it sends a matching success indication message to the palm-scanning terminal.

[0185] 7. The palm-swiping terminal outputs a prompt message to remind the payee to remove their palm;

[0186] 8. When the palm-swiping terminal detects that the payment recipient has moved their palm away, it takes another picture to capture the facial features of the payment recipient who just swiped their palm, as the last frame.

[0187] 9. The swipe terminal encrypts all frames (initial frame, preferred frame, and tail frame) using a storage key and SM4. The storage key is obtained by encrypting the serial number, the successfully identified user ID (payment object identifier), the device number, and the initial key using SHA64. The initial key is stored in the secure element (SE) of the swipe terminal.

[0188] II. The process of providing evidence to make a decision on a chargeback request when it is detected:

[0189] 1. When the issuing bank's equipment detects a chargeback request for payment 1 sent by the chargeback requester, it generates a payment evidence provision request and sends it to the acquiring bank's equipment. The payment evidence provision request is used to request payment evidence corresponding to payment 1 in order to make a decision on the chargeback request.

[0190] 2. The acquiring bank device sends a payment evidence provision request to the corresponding merchant device; if the merchant device accepts the chargeback, the acquiring bank device can then send the merchant's acceptance of the chargeback message to the issuing bank's device, so that the issuing bank's device can return the amount paid to the chargeback requester's account.

[0191] 3. If the merchant does not accept the chargeback, the merchant device sends a payment evidence provision request carrying a transaction number to the backend server (payment verification device); furthermore, the payment evidence provision request also carries the identity of the chargeback requester, the device identifier of the swipe terminal, and the initial key (obtained from the SE of the swipe terminal).

[0192] 4. The backend server obtains the storage key based on the identity of the party requesting the chargeback, the device identifier of the swiping terminal, the initial key, and the serial number. Based on the storage key, it retrieves the payment evidence corresponding to payment 1 from the cloud storage. The payment evidence may include at least the initial frame and the tail frame.

[0193] 5. The back-end server can transmit payment evidence to the issuing bank's equipment through the acquiring bank's equipment;

[0194] 6. The issuing bank's device can obtain the facial features of the person requesting the chargeback. If the facial features of the person requesting the chargeback match the facial features contained in the initial frame and the facial features contained in the final frame, the chargeback request is rejected. If the facial features of the person requesting the chargeback do not match the facial features contained in either the initial frame or the final frame, the issuing bank's device will return the amount paid to the account of the person requesting the chargeback and notify the corresponding merchant device. Alternatively, if the facial features of the person requesting the chargeback do not match the facial features contained in either the initial frame or the final frame, the evidence and verification results will be sent to the corresponding institution for processing.

[0195] If the facial features of the person requesting the refusal of payment match the facial features contained in the initial frame but do not match the facial features contained in the final frame, or if the facial features of the person requesting the refusal of payment match the facial features contained in the final frame but do not match the facial features contained in the initial frame, other measures may be taken, or the request may be sent to the relevant agency for further processing.

[0196] Furthermore, in addition to these IoT terminal measures, other ways to enhance payment security include:

[0197] Risk control measures: A machine learning-based risk control model is added, employing a random forest algorithm for real-time analysis of transaction data. The specific steps are as follows: First, transaction data is collected, including features such as transaction amount, transaction time, transaction location, and transaction frequency, and divided into training and test sets. Then, the random forest model is trained using the training set. During training, model performance is optimized by adjusting its parameters. For the number of trees, a small value (e.g., 10 trees) is started, and the number of trees is gradually increased. Changes in the model's accuracy, recall, and other metrics on the test set are observed. When these metrics no longer show significant improvement, the appropriate number of trees is determined. For the maximum depth, a gradual approach is also used, starting with a small depth (e.g., 3 layers) and gradually increasing the depth to avoid overfitting. Other parameters, such as the minimum number of splits and the minimum number of leaves, can also be adjusted. In the real-time analysis phase, new transaction data is input into the trained model, which calculates the risk probability of the transaction based on its features. For example, if the same account initiates multiple large transactions in different regions within a short period of time, and the model calculates a risk probability exceeding a preset threshold (e.g., 0.8), it is determined that there may be a risk. When the model identifies a potential risk, additional verification methods are added, such as requiring users to enter additional SMS verification codes, performing facial recognition, or fingerprint recognition, thereby reducing the possibility of fraud.

[0198] Limit Measures: 3DS verification is added for transactions exceeding the limit to ensure responsible transfer of high-risk transactions. The specific method for setting different transaction limits based on the user's historical transaction data and credit rating is as follows: First, the user's historical transaction data is analyzed, including characteristics such as transaction amount distribution, transaction frequency, and transaction stability. Simultaneously, the user's credit rating information is obtained; this can be obtained from a professional credit rating agency or assessed independently based on the user's credit history with the bank. Then, a linear regression model is used to calculate the single transaction limit and the daily cumulative transaction limit. The formula is L... single =α1×A avg +α2×C+β1 and L daily =γ1×A total +γ2×C+β2, where L single Indicates the single transaction limit, L daily Indicates the daily cumulative transaction limit, A avg A represents the average amount of a user's historical transactions. total This represents the user's daily cumulative average transaction amount, C represents the user's credit rating score, α1, α2, γ1, and γ2 are the model coefficients, and β1 and β2 are constants. These coefficients and constants can be obtained by training on a large amount of user data. When the transaction amount exceeds the set limit, 3DS (3D Secure) verification is added. The specific process is as follows: when a transaction triggers the limit, the issuing bank will send a verification code to the user's registered mobile phone. The user needs to enter the verification code on the payment page for verification. At the same time, the user may also need to authorize confirmation on the issuing bank's mobile banking app or website. Only after successful verification can the transaction be completed, thereby ensuring that high-risk transactions are responsibly transferred.

[0199] Equipment and data security: The equipment is deployed at the merchant's end, and it is necessary to ensure that the equipment has extremely high security and cannot be compromised or tampered with.

[0200] The algorithm is reliable: its extremely low false recognition rate and authoritative certification have established reliable expectations in the industry.

[0201] Furthermore, based on the solutions described in the above embodiments, the embodiments of this application can enhance security: palmprint recognition is a biometric technology with uniqueness and difficulty in forgery, which can improve payment security; it can further improve user experience: compared with traditional 3DS authentication (such as entering a password or one-time verification code), palmprint recognition may provide a smoother payment experience and reduce the possibility of users abandoning the transaction; instant verification: biometric technology can quickly verify the user's identity and reduce the risk of payment refusal due to input errors.

[0202] Based on the same principle as the method for processing chargeback requests provided in the embodiments of this application, the embodiments of this application also provide a device for processing chargeback requests, as shown in FIG7. This device 70 can be installed in a payment verification device, wherein the device 70 may include:

[0203] The payment evidence provision request receiving module 71 is used to receive a payment evidence provision request for completed payment sent by the chargeback request processing device. The payment evidence provision request carries a payment identifier indicating that the payment has been completed. The payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying a payment identifier. The completed payment is a payment made based on a first biometric feature and has been successfully made. The first biometric feature is the biometric feature of a first part of the payer collected during the payment process of the completed payment.

[0204] The acquisition module 72 is used to acquire the second biometric feature corresponding to the completed payment based on the payment identifier; wherein, the second biometric feature is the biometric feature of the second part of the payer collected during the payment process of the completed payment;

[0205] The payment evidence information sending module 73 is used to send payment evidence information including a second biometric feature to the chargeback request processing device, so that the chargeback request processing device can process the chargeback request based on the degree of matching between the biometric feature in the payment evidence information and the biometric feature of the chargeback requester.

[0206] In one possible implementation of this application embodiment, the apparatus 70 further includes: a first determining module and a second determining module, wherein...

[0207] The first determining module is used to determine the payer identifier corresponding to the completed payment based on the payment identifier;

[0208] The second determining module is used to determine the third biometric feature bound to the payer identifier; wherein, the third biometric feature is the biometric feature of the first part registered by the object corresponding to the payer identifier;

[0209] The payment evidence information also includes a third biometric feature. The biometric feature of the requester of the chargeback includes the fourth biometric feature of the first part and the fifth biometric feature of the second part. The degree of matching includes the degree of matching between the second biometric feature and the fifth biometric feature, as well as the degree of matching between the third biometric feature and the fourth biometric feature.

[0210] In one possible implementation of this application embodiment, when the acquisition module 72 acquires the second biometric feature corresponding to the completed payment based on the payment identifier, it is specifically used for:

[0211] Send a biometric acquisition request to the payment evidence storage device; wherein the biometric acquisition request includes a payment identifier; the payment evidence storage device stores the biometric features of the second part of the payer corresponding to the payment identifier of each payment;

[0212] Receive the second biometric feature corresponding to the completed payment sent by the payment evidence storage device.

[0213] In another possible implementation of this application embodiment, the payment evidence information is collected by the payment feature collection device in the following manner and stored in the payment evidence storage device:

[0214] Receive payment requests for completed payments;

[0215] In response to a payment request, a biometric video stream is acquired, and upon receiving payment success information, the payer's first and second biometric features are stored in a payment evidence storage device; wherein, the biometric video stream includes at least the payer's first and second biometric features.

[0216] Another possible implementation of this application embodiment involves acquiring a biometric video stream and storing the second biometric feature in a payment evidence storage device upon receiving a payment success message, including:

[0217] The first video frame is captured; wherein the first video frame contains the second biometric feature corresponding to the payer;

[0218] Output the first prompt message, which is used to prompt the payer to provide the first biometric feature;

[0219] Acquire a second video frame containing the first biometric feature;

[0220] If a payment success message is received, and when the first part of the payer is detected to be out of the shooting range, a third video frame including the second biometric feature of the payer is captured;

[0221] Send a first video frame, a third video frame, and the corresponding payment identifier to the payment evidence storage device, so that the payment evidence storage device stores the second biometric feature contained in the first video frame, the second biometric feature contained in the third video frame, and the payment identifier in association.

[0222] In another possible implementation of this application embodiment, the second biometric feature contained in the first video frame matches the second biometric feature contained in the third video frame;

[0223] Specifically, when sending payment evidence information including the second biometric feature to the chargeback request processing device, the payment evidence information sending module 73 is used for:

[0224] Payment evidence information containing the first and third video frames is sent to the chargeback request processing device, so that the chargeback request device can process the chargeback request in the following ways:

[0225] If the fifth biometric feature of the second part of the chargeback requester matches the designated second biometric feature, the chargeback request is rejected and a first notification message is sent to the chargeback requester; wherein, the designated second biometric feature is the second biometric feature contained in the first video frame or the third video frame; the first notification message carries the matching result of the second biometric feature and is used to notify the chargeback requester that the chargeback request processing device has rejected the chargeback request.

[0226] Another possible implementation of this application embodiment involves the chargeback request device processing the chargeback request in the following manner:

[0227] If the fifth biometric feature of the second part of the chargeback requester does not match the specified second biometric feature, the specified second biometric feature will be matched with the second biometric feature of the object that is associated with the chargeback requester.

[0228] If there is a matching object with a matching second biometric among the related objects, a second notification message carrying the second biometric of the matching object is sent to the chargeback requester; wherein, the second notification message is used to notify the chargeback requester that the payment has been completed by the matching object;

[0229] Receive the response from the party requesting the chargeback in response to the second notification message, and process the chargeback request based on the response.

[0230] Another possible implementation of this application embodiment involves the chargeback request device processing the chargeback request in any of the following ways:

[0231] If the fifth biometric feature of the second part of the chargeback requester does not match the designated second biometric feature, the chargeback request is accepted, and the successfully paid amount is returned to the chargeback requester's account.

[0232] In another possible implementation of this application embodiment, the second biometric feature contained in the first video frame does not match the second biometric feature contained in the third video frame;

[0233] Specifically, when sending payment evidence information including the second biometric feature to the chargeback request processing device, the payment evidence information sending module 73 is used for:

[0234] Payment evidence information containing the first and third video frames is sent to the chargeback request processing device, so that the chargeback request device can process the chargeback request in the following ways:

[0235] If the second biometric feature contained in the first video frame matches the second biometric feature of the party requesting a chargeback, then according to the payment time corresponding to the completed payment, the seventh biometric feature corresponding to the first party who has completed payment is obtained, and the seventh biometric feature is matched with the second biometric feature contained in the third video frame. The chargeback request is processed based on the matching result. Here, the first party who has completed payment is the party that completed payment after the first party who has completed payment. Here, the seventh biometric feature is the biometric feature of the second part corresponding to the first party who has completed payment.

[0236] If the second biometric feature contained in the third video frame matches the second biometric feature of the party requesting a chargeback, then according to the payment time corresponding to the completed payment, the eighth biometric feature corresponding to the second party who has completed payment is obtained, and the eighth biometric feature is matched with the second biometric feature contained in the first video frame. The chargeback request is processed based on the matching result. The second party who has completed payment is the party that completed payment before the completed payment. The eighth biometric feature is the biometric feature of the second part corresponding to the second party who has completed payment.

[0237] Another possible implementation of this application embodiment is that the biometric features and storage keys of the second part of each payer are stored together in the payment evidence storage device. The storage key of a payer is obtained by encrypting the payer's payment identifier, payer identifier, initial key and the device identifier of the corresponding payment feature collection device; the initial key is stored in the payment feature collection device.

[0238] Specifically, when obtaining the second biometric feature corresponding to the completed payment based on the payment identifier, the acquisition module 72 is used for:

[0239] Based on the payment identifier, determine the payer identifier corresponding to the completed payment;

[0240] Obtain the device identifier and initial key from the payment feature collection device corresponding to the completed payment;

[0241] The payment identifier, payer identifier, device identifier, and initial key are encrypted to obtain the biometric storage encryption key;

[0242] Based on the biometric storage encryption key, the second biometric feature corresponding to the completed payment is obtained from the payment evidence storage device.

[0243] This application embodiment also provides another apparatus for processing chargeback requests, as shown in FIG8. The apparatus 80 is disposed in the chargeback request processing device, and the apparatus 80 may include:

[0244] The payment evidence provision request sending module 81 is used to send a payment evidence provision request to the payment verification device; wherein, the payment evidence provision request carries a payment identifier corresponding to the completed payment; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying a payment identifier; the completed payment is a payment based on a first biometric feature and has been successfully paid; wherein, the first biometric feature is the biometric feature of the first part of the payer collected during the payment process of the completed payment;

[0245] The payment evidence information receiving module 82 is used to receive payment evidence information including a second biometric feature sent by the payment verification device; the second biometric feature is obtained by the payment verification device based on the payment identifier; wherein, the second biometric feature is the biometric feature of a second part collected during the payment process;

[0246] The matching degree determination module 83 is used to determine the degree of matching between the biometric features in the payment evidence information and the biometric features of the chargeback requester;

[0247] The chargeback request processing module 84 is used to process chargeback requests based on the degree of matching.

[0248] In one possible implementation of this application, the second biometric feature includes: second biometric feature information corresponding to two video frames respectively. One video frame is a video frame collected by the payment feature collection device before collecting the first biometric feature of the payer, and the other video frame is a video frame collected by the payment feature collection device when it detects that the first biometric feature of the payer has left the shooting range.

[0249] Specifically, the matching degree determination module 83, when determining the matching degree between the biometric features in the payment evidence information and the biometric features of the chargeback requester, is used for:

[0250] Obtain the fifth biometric feature of the second part of the chargeback requester;

[0251] The degree of matching between the biometrics in the payment evidence information and the biometrics of the party requesting non-payment is determined based on the second biometric information and the fifth biometric information corresponding to the two video frames respectively.

[0252] This application provides a charging rejection request processing device. In this application embodiment, when the charging rejection request processing device receives a charging rejection request carrying a payment identifier, and the completed payment corresponding to the payment identifier is a payment made based on a first biometric feature and has been successfully completed, the charging rejection request device sends a request to the payment verification device for providing payment evidence for the completed payment. The payment verification device obtains the biometric feature of the second part of the payer collected during the payment process based on the payment identifier, and sends payment evidence information containing the biometric feature of the second part of the payer to the charging rejection request processing device, so that the charging rejection request processing device processes the charging rejection request based on the degree of matching between the biometric feature in the payment evidence information and the biometric feature of the charging rejection requester. In other words, the payment evidence information obtained by the chargeback request processing device for completed payments carries the biometrics of a second part of the payer's body. This allows the device to match the biometrics of the payer's second part with those of the chargeback requester to determine whether the payer and the chargeback requester are the same. If they are the same, the completed payment was made by the chargeback requester. If they are not the same, the completed payment may not have been made by the chargeback requester. In other words, the evidence provided is the biometrics of another part of the payer's body during the payment process. This makes the evidence more reasonable for verifying whether the transaction for which the payer initiated the chargeback request was made by the payer himself, thus enabling accurate verification of the transaction for which the payer initiated the chargeback request.

[0253] Figure 9 shows a schematic diagram of the structure of an electronic device to which an embodiment of the present invention applies. As shown in Figure 9, the electronic device can be the payment verification device, chargeback request processing device, payment feature collection device, etc., as described above. If the electronic device is the payment verification device described above, it can be used to implement the method provided in any embodiment executed by the payment verification device; if the electronic device is the chargeback request processing device described above, it can be used to implement the method provided in any embodiment executed by the chargeback request processing device; if the electronic device is the payment feature collection device described above, it can be used to implement the method provided in any embodiment executed by the payment feature collection device.

[0254] As shown in Figure 9, the electronic device 2000 mainly includes at least one processor 2001 (one is shown in Figure 9), a memory 2002, a communication module 2003, and an input / output interface 2004, etc. Optionally, the components can be connected and communicate with each other through a bus 2005. It should be noted that the structure of the electronic device 2000 shown in Figure 9 is only schematic and does not constitute a limitation on the electronic device to which the method provided in the embodiments of this application is applicable.

[0255] The memory 2002 can be used to store operating systems and applications, etc. The applications can include computer programs that implement the methods shown in the embodiments of the present invention when invoked by the processor 2001, and can also include programs for implementing other functions or services. The memory 2002 can be ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices that can store information and computer programs, or it can be EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0256] Processor 2001 is connected to memory 2002 via bus 2005, and implements corresponding functions by calling application programs stored in memory 2002. Processor 2001 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 2001 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0257] Electronic device 2000 can connect to a network via communication module 2003 (which may include, but is not limited to, components such as a network interface) to communicate with other devices (such as user terminals or servers) through the network and achieve data interaction, such as sending data to or receiving data from other devices. Communication module 2003 may include wired network interfaces and / or wireless network interfaces, meaning the communication module may include at least one of wired or wireless communication modules.

[0258] Electronic device 2000 can connect to required input / output devices, such as keyboards and display devices, via input / output interface 2004. Electronic device 2000 itself may have a display device, and other display devices can also be connected externally via interface 2004. Optionally, storage devices, such as hard drives, can also be connected via interface 2004 to store data from electronic device 2000, retrieve data from storage devices, or store data from storage devices into memory 2002. It is understood that input / output interface 2004 can be a wired interface or a wireless interface. Depending on the actual application scenario, the device connected to input / output interface 2004 can be a component of electronic device 2000 or an external device connected to electronic device 2000 when needed.

[0259] The bus 2005 used to connect the various components may include a pathway for transmitting information between these components. The bus 2005 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Depending on its function, the bus 2005 can be divided into address bus, data bus, control bus, etc.

[0260] Optionally, for the solution provided in the embodiments of the present invention, the memory 2002 can be used to store a computer program that executes the solution of the present invention, and the processor 2001 runs the computer program. When the processor 2001 runs the computer program, it implements the operation of the method or apparatus provided in the embodiments of the present invention.

[0261] Based on the same principle as the method provided in the embodiments of this application, the embodiments of this application provide a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it can implement the corresponding content of the aforementioned method embodiments.

[0262] This application also provides a computer program product, which includes a computer program that, when executed by a processor, can implement the corresponding content of the aforementioned method embodiments.

[0263] In summary, this application provides a method, apparatus, device, computer-readable storage medium, and computer program product for processing chargeback requests. A payment verification device receives a payment evidence provision request from a chargeback request processing device, carrying a payment identifier indicating completed payment. This request is sent when the chargeback request processing device receives a chargeback request carrying the same payment identifier, and the completed payment is based on a first biometric feature of the payer's first location collected during the payment process. Next, the payment verification device obtains a second biometric feature of the payer's second location corresponding to the completed payment based on the payment identifier, and sends payment evidence information containing this second biometric feature to the chargeback request processing device. The chargeback request processing device then processes the chargeback request based on the matching degree between the biometric feature in the payment evidence information and the biometric feature of the chargeback requester. By introducing the biometric feature of the second location as payment evidence, the dimension of biometric verification is increased. Compared to single biometric verification, it can more comprehensively reflect the payer's identity characteristics, thereby improving the accuracy of verifying the payer's chargeback request transaction. Biometric features from different parts of the body have different characteristics. Using them in combination can reduce the probability of misjudgment caused by the ease with which a single biometric feature can be forged or is prone to error, thereby enhancing the reliability of payment verification and ensuring the security of payment transactions.

[0264] Furthermore, upon receiving a payment evidence provision request, the payment verification device also determines the payer's identifier corresponding to the completed payment based on the payment identifier, and identifies the third biometric feature bound to that payer's identifier—that is, the biometric feature of the first part registered by the object corresponding to the payer's identifier. In addition to the second biometric feature, the payment evidence information also includes the third biometric feature. The biometric features of the chargeback requester include the fourth biometric feature of its first part and the fifth biometric feature of its second part. The matching degree comprehensively considers the matching results of the second and fifth biometric features, and the third and fourth biometric features. This multi-dimensional biometric matching method verifies the identities of the payer and the chargeback requester from different perspectives, reducing verification errors caused by individual differences in biometric features or environmental factors. The comprehensive verification of multiple biometric features improves the accuracy and reliability of identity recognition, making the processing of chargeback requests more scientific and reasonable, and reducing the possibility of misjudgment and omission.

[0265] Furthermore, when the payment verification device obtains the second biometric feature corresponding to a completed payment based on the payment identifier, it sends a biometric feature retrieval request containing the payment identifier to the payment evidence storage device. The payment evidence storage device stores the biometric features of the payer's second biometric feature corresponding to the payment identifier for each payment. The payment verification device receives the second biometric feature corresponding to the completed payment sent by this storage device. By centrally storing biometric features in a dedicated payment evidence storage device, unified management of biometric data is achieved. This centralized storage method facilitates data classification, indexing, and retrieval, improving data query efficiency. Simultaneously, centralized storage also facilitates data security protection, employing unified security strategies and technologies to ensure the integrity and confidentiality of biometric data, preventing data leakage and tampering, and providing a reliable data foundation for the accurate processing of subsequent chargeback requests.

[0266] Furthermore, payment evidence information is collected by the payment feature collection device and stored in the payment evidence storage device. The payment feature collection device receives payment requests for completed payments, responds to the request by acquiring a biometric video stream containing at least the payer's first and second biometric features, and stores the payer's first and second biometric features in the payment evidence storage device upon receiving payment success information. Collecting biometric features synchronously during the payment process ensures the timeliness and accuracy of the data. The collected biometric features are acquired in real time when the payment occurs, reflecting the payer's true identity information at that time, avoiding potential information discrepancies or forgery that may occur with post-payment collection. Simultaneously, timely storage of biometric features in the payment evidence storage device facilitates rapid retrieval of relevant data when processing chargeback requests, improving the efficiency of the processing flow.

[0267] Furthermore, the process by which the payment feature acquisition device acquires and stores the biometric video stream includes: acquiring a first video frame containing the payer's second biometrics; outputting a first prompt message asking the payer to provide the first biometrics; acquiring a second video frame containing the first biometrics; and if a payment success message is received and the payer's first body part is detected to have left the shooting range, acquiring a third video frame containing the payer's second biometrics. Then, the first video frame, the third video frame, and the corresponding payment identifier are sent to the payment evidence storage device, enabling the storage device to associate and store this information. Acquiring different video frames in stages comprehensively records the changes in the payer's biometrics during the payment process. The first video frame is acquired before payment, reflecting the payer's initial biometric state; the second video frame acquires the first biometrics for payment authentication; and the third video frame is acquired after payment to verify the continuity of the payer's identity. Associating and storing these video frames and the payment identifier facilitates the rapid and accurate acquisition of relevant biometric information based on the payment identifier when processing chargeback requests, improving the efficiency of evidence acquisition and management, and enhancing the accuracy and reliability of chargeback request processing.

[0268] Furthermore, when the second biometric feature contained in the first video frame matches the second biometric feature contained in the third video frame, the payment verification device sends payment evidence information containing the first and third video frames to the chargeback request processing device. If the fifth biometric feature of the second part of the chargeback requester matches the specified second biometric feature contained in the first or third video frame, the chargeback request processing device rejects the chargeback request and sends a first notification message carrying the second biometric matching result to the chargeback requester. This multi-video frame biometric matching method increases the dimensions and reliability of verification. The biometric features in multiple video frames corroborate each other, improving the accuracy of payer authentication. When a match is successful, it is more confident in determining that the payment was made by the account holder, reducing the possibility of false chargeback requests. Timely notification of the matching result to the chargeback requester increases the transparency of the processing flow, allowing the chargeback requester to understand the processing result promptly and enhancing user trust in the payment system.

[0269] Furthermore, if the fifth biometric feature of the second part of the chargeback requester does not match the designated second biometric feature, the chargeback request processing device has two processing methods. First, it matches the designated second biometric feature with the second biometric feature of an object associated with the chargeback requester. If a matching object exists, a second notification message carrying the second biometric feature of the matching object is sent to the chargeback requester, informing them that the payment was completed by the matching object, and the device receives the chargeback requester's response to this notification message, processing the chargeback request based on the response. Second, it directly approves the chargeback request and returns the successfully paid amount to the chargeback requester's account. These two processing methods consider multiple possible scenarios, increasing the flexibility and accuracy of handling chargeback requests. When the chargeback requester's biometric feature does not match the payment biometric feature, further investigation through matching with associated objects avoids misjudgments caused by situations such as the payer potentially entrusting others to make the payment. If no reasonable association can be found, the chargeback request is processed promptly, protecting the rights of the chargeback requester and improving the fairness of the payment system and user experience.

[0270] Furthermore, the payment evidence storage device associates and stores the biometric features of each payer's second biometric data with its storage key. A payer's storage key is encrypted based on their payment identifier, payer identifier, initial key, and the device identifier of the corresponding payment feature acquisition device. The initial key is stored in the payment feature acquisition device. When the payment verification device retrieves the second biometric feature corresponding to a completed payment based on the payment identifier, it first determines the payer identifier, obtains the device identifier and initial key from the payment feature acquisition device, encrypts this information to obtain the biometric storage encryption key, and then retrieves the second biometric feature from the payment evidence storage device based on this key. This encrypted storage and retrieval of biometric features enhances the security of biometric data. The encryption algorithm encrypts the biometric data, converting it into ciphertext. Only the correct storage key can decrypt and retrieve the original data. Even if the data is intercepted during transmission or storage, attackers cannot obtain valid information, protecting the payer's privacy and the security of payment transactions. Simultaneously, using a storage key generated based on multiple factors increases the key's complexity and randomness, further improving the reliability of the encryption.

[0271] Furthermore, when the chargeback request processing device receives a chargeback request carrying a payment identifier, it sends a request for payment evidence carrying the same payment identifier to the payment verification device. It then receives payment evidence information containing a second biometric feature from the payment verification device and determines the degree of matching between the biometric features in the payment evidence information and the biometric features of the chargeback requester. Based on this matching degree, the chargeback request is processed. The chargeback request processing device plays a core coordinating and decision-making role throughout the entire process. Through information interaction with the payment verification device, it achieves the effective utilization of biometric data. Accurately determining the degree of biometric matching enables a scientific and reasonable assessment of the rationality of the chargeback request, ensuring the normal order of payment transactions. Simultaneously, decision-making based on the degree of matching reduces interference from human factors, improves the objectivity and accuracy of the processing results, and enhances the stability and reliability of the payment system.

[0272] It should be noted that the terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0273] In this application embodiment, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0274] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0275] The technical features of the above embodiments can be combined arbitrarily, and as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

A method for processing a chargeback request, executed by a payment verification device, the method comprising: The system receives a payment evidence provision request from a chargeback request processing device for a completed payment, wherein the payment evidence provision request carries a payment identifier indicating that the payment has been completed; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier; the completed payment is a payment made based on a first biometric feature and has been successfully completed; wherein the first biometric feature is a biometric feature of a first part of the payer collected during the payment process of the completed payment; Based on the payment identifier, a second biometric feature corresponding to the completed payment is obtained; wherein, the second biometric feature is a biometric feature of a second part of the payer collected during the payment process of the completed payment; and The payment rejection request processing device sends payment evidence information including the second biometric feature to the payment rejection request processing device, so that the payment rejection request processing device processes the payment rejection request based on the degree of matching between the biometric feature in the payment evidence information and the biometric feature of the payment rejection requester. The method according to claim 1, further comprising: Based on the payment identifier, determine the payer identifier corresponding to the completed payment; Determine the third biometric feature bound to the payer identifier; wherein, the third biometric feature is the biometric feature of the first part registered by the object corresponding to the payer identifier; The payment evidence information further includes the third biometric feature, and the biometric feature of the chargeback requester includes the fourth biometric feature of the first part and the fifth biometric feature of the second part of the chargeback requester. The matching degree includes the matching degree between the second biometric feature and the fifth biometric feature, and the matching degree between the third biometric feature and the fourth biometric feature. According to the method of claim 1 or 2, obtaining the second biometric feature corresponding to the completed payment based on the payment identifier includes: A biometric feature acquisition request is sent to a payment evidence storage device; wherein the biometric feature acquisition request includes the payment identifier; the payment evidence storage device stores the biometric features of the second part of the payer corresponding to the payment identifier of each payment; Receive the second biometric feature corresponding to the completed payment sent by the payment evidence storage device. According to the method of claim 3, the payment evidence information is collected by the payment feature collection device in the following manner and stored in the payment evidence storage device: Receive payment requests for the completed payments; In response to the payment request, a biometric video stream is acquired, and upon receiving payment success information, the first and second biometric features of the payer are stored in the payment evidence storage device; wherein, The biometric video stream includes at least the first and second biometric features of the payer. According to claim 4, the method of acquiring a biometric video stream and storing the second biometric feature in the payment evidence storage device upon receiving a payment success message includes: A first video frame is captured; wherein the first video frame contains the second biometric feature corresponding to the payer; Output a first prompt message, which prompts the payer to provide a first biometric feature. Acquire a second video frame containing the first biometric feature; If a payment success message is received, and when the first part of the payer is detected to be out of the shooting range, a third video frame including the second biometric feature of the payer is captured; The first video frame, the third video frame, and the corresponding payment identifier are sent to the payment evidence storage device so that the payment evidence storage device stores the second biometric feature contained in the first video frame, the second biometric feature contained in the third video frame, and the payment identifier in association. According to the method of claim 5, the second biometric feature contained in the first video frame matches the second biometric feature contained in the third video frame; in, Sending payment evidence information including the second biometric feature to the chargeback request processing device includes: Payment evidence information containing the first video frame and the third video frame is sent to the chargeback request processing device, so that the chargeback request device can process the chargeback request in the following manner: If the fifth biometric feature of the second part of the chargeback requester matches the specified second biometric feature, the chargeback request is rejected and a first notification message is sent to the chargeback requester; wherein, the specified second biometric feature is the second biometric feature contained in the first video frame or the third video frame; the first notification message carries the matching result of the second biometric feature and is used to notify the chargeback requester that the chargeback request processing device has rejected the chargeback request. According to the method of claim 6, the chargeback request device processes the chargeback request in any of the following ways: If the fifth biometric feature of the second part of the chargeback requester does not match the specified second biometric feature, the specified second biometric feature is matched with the second biometric feature of an object associated with the chargeback requester; if there is an associated matching object among the associated objects that matches the second biometric feature, a second notification message carrying the second biometric feature of the associated matching object is sent to the chargeback requester; the response information from the chargeback requester to the second notification message is received, and the chargeback request is processed based on the response information; wherein, The second notification message is used to notify the party requesting the chargeback that the completed payment was made by the associated matching object; If the fifth biometric feature of the second part of the chargeback requester does not match the designated second biometric feature, the chargeback request is accepted, and the successfully paid amount is returned to the chargeback requester's account. According to any one of claims 3-7, the payment evidence storage device stores the biometric features and storage keys of the second part of each payer in association, and the storage key of a payer is obtained by encrypting the payer's payment identifier, payer identifier, initial key and the device identifier of the corresponding payment feature collection device; the initial key is stored in the payment feature collection device; in, The step of obtaining the second biometric feature corresponding to the completed payment based on the payment identifier includes: Based on the payment identifier, determine the payer identifier corresponding to the completed payment; Obtain the device identifier and initial key from the payment feature collection device corresponding to the completed payment; The payment identifier, payer identifier, device identifier, and initial key are encrypted to obtain a biometric storage encryption key; Based on the biometric storage encryption key, the second biometric corresponding to the completed payment is obtained from the payment evidence storage device. A method for processing a chargeback request, executed by a chargeback request processing device, the method comprising: A payment evidence provision request is sent to the payment verification device; wherein the payment evidence provision request carries a payment identifier corresponding to the completed payment; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier; the completed payment is a payment made based on a first biometric feature and has been successfully paid; the first biometric feature is the biometric feature of a first part of the payer collected during the payment process of the completed payment; The system receives payment evidence information, including a second biometric feature, sent by the payment verification device. The second biometric feature is obtained by the payment verification device based on the payment identifier. The second biometric feature is a biometric feature of a second location collected during the payment process. The degree of matching between the biometric features in the payment evidence information and the biometric features of the chargeback requester is determined, and the chargeback request is processed based on the degree of matching. A payment rejection request processing apparatus, the apparatus being disposed in a payment verification device, the apparatus comprising: A payment evidence provision request receiving module is used to receive a payment evidence provision request for a completed payment sent by a chargeback request processing device. The payment evidence provision request carries a payment identifier indicating that the payment has been completed. The payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier. The completed payment is a payment made based on a first biometric feature and has been successfully completed. The first biometric feature is a biometric feature of a first part of the payer collected during the payment process of the completed payment. The acquisition module is used to acquire the second biometric feature corresponding to the completed payment based on the payment identifier; wherein the second biometric feature is the biometric feature of the second part of the payer collected during the payment process of the completed payment; The payment evidence information sending module is used to send payment evidence information including the second biometric feature to the chargeback request processing device, so that the chargeback request processing device can process the chargeback request based on the degree of matching between the biometric feature in the payment evidence information and the biometric feature of the chargeback requester. A chargeback request processing apparatus, the apparatus being disposed in a chargeback request processing device, the apparatus comprising: A payment evidence provision request sending module is used to send a payment evidence provision request to a payment verification device; wherein, the payment evidence provision request carries a payment identifier corresponding to the completed payment; the payment evidence provision request is sent by the chargeback request processing device when it receives a chargeback request carrying the payment identifier; the completed payment is a payment made based on a first biometric feature and has been successfully paid; wherein, the first biometric feature is the biometric feature of a first part of the payer collected during the payment process of the completed payment; The payment evidence information receiving module is used to receive payment evidence information including a second biometric feature sent by the payment verification device; the second biometric feature is obtained by the payment verification device based on the payment identifier; wherein, the second biometric feature is a biometric feature of a second part collected during the payment process; The matching degree determination module is used to determine the degree of matching between the biometric features in the payment evidence information and the biometric features of the chargeback requester; The chargeback request processing module is used to process the chargeback request based on the matching degree. A payment verification device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the payment rejection request processing method according to any one of claims 1 to 8 when running the computer program. A chargeback request processing device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the chargeback request processing method of claim 9 when running the computer program. A computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for processing a chargeback request as described in any one of claims 1 to 9. A computer program product includes a computer program that, when executed by a processor, implements the method for processing a chargeback request as described in any one of claims 1 to 9.

Images