Payment method and device, equipment and medium

Abstract

The invention provides a payment method which can be applied to the technical field of financial science and technology. The payment method is applied to a server and comprises the steps that current biological recognition features and current payment scene recognition features from a user side are received, and the current payment scene recognition features are collected in the current biological recognition feature collection process at the same time; recognizing a user identity based on the current biological recognition feature; recognizing a current payment scene based on the current payment scene recognition feature under the condition that the user identity recognition is passed; and payment is completed based on the payment rule determined by the current payment scene. The invention further provides a payment device, equipment and a medium.

Description

Technical Field

[0001] The present disclosure relates to the field of financial technology, specifically to the field of artificial intelligence and information security technology, and more specifically to a payment method, device, equipment and medium. Background Art

[0002] With the increasing popularity of biometric technology for user identity verification and payment, various fields have increasingly higher requirements for the security of biometric information and the accuracy of verification.

[0003] Relevant personnel are aware that even though there are numerous biometric technologies to achieve identity verification, there are still some scenarios where, after confirming the biometric collection and passing the identity verification, the payment behavior made by the user is still not his or her true intention. Therefore, how to further ensure the safety of users' lives and property and improve the security of biometric technologies is still an urgent task. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a payment method, device, equipment and medium for improving the security of biometric payment.

[0005] According to the first aspect of the present disclosure, a payment method is provided, which is applied in a server, and the method includes: receiving a current biometric feature and a current payment scenario identification feature from a user end, wherein the current payment scenario identification feature is collected simultaneously during the collection process of the current biometric feature; identifying a user identity based on the current biometric feature; identifying a current payment scenario based on the current payment scenario identification feature when the user identity is identified; and completing payment based on a payment rule determined based on the current payment scenario.

[0006] According to an embodiment of the present disclosure, the current biometric feature exists in a ciphertext form, and identifying the user identity based on the current biometric feature includes: obtaining a preset biometric feature, the preset biometric feature exists in a ciphertext form, and the preset biometric feature and the current biometric feature are homomorphically encrypted; and matching the current biometric feature and the preset biometric feature.

[0007] According to an embodiment of the present disclosure, the current payment scenario identification feature exists in a ciphertext form, and identifying the current payment scenario based on the current payment scenario identification feature includes: obtaining a preset payment scenario identification feature set, the preset payment scenario identification feature set includes preset payment scenario identification features corresponding to N different payment scenarios, N is a positive integer, the preset payment scenario identification feature exists in a ciphertext form, and the preset payment scenario identification feature and the current payment scenario identification feature are homomorphically encrypted; based on the current payment scenario identification feature, matching the preset payment scenario identification feature in the preset payment scenario identification feature set; and determining the corresponding current payment scenario when any one of the preset payment scenario identification features in the preset payment scenario identification feature set matches successfully.

[0008] According to an embodiment of the present disclosure, the biometric feature includes: a palm print image feature and a palm vein image feature, and the matching of the current biometric feature and the preset biometric feature includes: when the current biometric feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric feature is the preset palm print image feature and the preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature, the preset palm print image feature and the preset palm print image feature are matched in parallel, wherein when the current palm print image feature matches the preset palm print image feature and the current palm vein image feature, and when the current palm vein image feature matches the preset palm vein image feature, it is determined that the match is successful; or when the current biometric feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric feature is the preset palm print image feature and the preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature, matching the preset palm print image feature and the preset palm print image feature, wherein, when the current palm print image feature and the preset palm print image feature are matched, or when the current palm vein image feature and the preset palm vein image feature are matched, it is determined that the match is successful; or when the current biometric feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric feature is the preset palm print image feature and the preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature, a matching result is output by a multimodal model; or when the current biometric feature is the current fused image feature, and when the preset biometric feature is the preset fused image feature, based on the current fused image feature, matching the preset fused image feature, wherein, when the current fused image feature and the preset fused image feature are matched, it is determined that the match is successful.

[0009] According to an embodiment of the present disclosure, the payment scenario recognition feature includes a gesture image feature, and identifying the current payment scenario based on the current payment scenario recognition feature includes: matching a preset gesture image feature in the preset payment scenario recognition feature set based on the current gesture image feature.

[0010] According to an embodiment of the present disclosure, the payment scenarios include: normal payment willingness scenarios, abnormal payment willingness scenarios and abnormal scenarios, and the payment is completed based on the payment rules determined based on the current payment scenario, including: when the current payment scenario is a normal payment willingness scenario, completing payment according to the first payment amount; when the current payment scenario is an abnormal payment willingness scenario, completing payment according to the second payment amount; and when the current payment scenario is an abnormal scenario, completing payment according to the third payment amount and / or triggering a background alarm.

[0011] According to a second aspect of the present disclosure, a payment method is provided, which is applied to a user terminal, and includes: collecting current biometric information and current payment scenario identification information from a user, wherein the current payment scenario identification feature is collected simultaneously during the current biometric feature collection process; extracting features from the current biometric information and the current payment scenario identification information to obtain current biometric features and current payment scenario identification features; and sending the current biometric features and the current payment scenario identification features to a server.

[0012] According to an embodiment of the present disclosure, the extracting features from the current biometric information and the current payment scenario identification information to obtain the current biometric features and the current payment scenario identification features includes: extracting features from the current biometric information and the current payment scenario identification information to obtain the current biometric feature plaintext and the current payment scenario identification feature plaintext; and encrypting the current biometric feature plaintext and the current payment scenario identification feature plaintext to obtain the current biometric feature ciphertext and the current payment scenario identification feature ciphertext.

[0013] According to an embodiment of the present disclosure, before the current biometric information and the current payment scenario identification information are collected from the user, the current payment scenario identification feature is collected simultaneously during the current biometric feature collection process, and the method further includes: extracting features from the entered biometric information and the entered payment scenario identification information to obtain a preset biometric feature plaintext and a preset payment scenario identification feature plaintext; encrypting the preset biometric feature plaintext and the preset payment scenario identification feature plaintext to obtain the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext, the preset biometric feature ciphertext and the current biometric feature ciphertext are homomorphically encrypted, and the preset payment scenario identification feature ciphertext and the current payment scenario identification feature ciphertext are homomorphically encrypted; and sending the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext to a server.

[0014] According to an embodiment of the present disclosure, the biometric identification feature includes: a palm print image feature and a palm vein image feature, and the payment scenario identification feature includes: a gesture image feature.

[0015] The third aspect of the present disclosure provides a payment device, which is configured in a server, and includes: a feature receiving module, used to receive a current biometric feature and a current payment scenario identification feature from a user end, wherein the current payment scenario identification feature is collected simultaneously during the current biometric feature collection process; an identity recognition module, used to identify a user identity based on the current biometric feature; a payment scenario identification module, used to identify a current payment scenario based on the current payment scenario identification feature when the user identity recognition passes; and a payment rule determination module, used to complete payment based on a payment rule determined by the current payment scenario.

[0016] According to an embodiment of the present disclosure, the current biometric feature exists in a ciphertext form, and the identity recognition module includes: a preset biometric feature acquisition unit and a biometric feature matching unit, the preset biometric feature acquisition unit is used to acquire a preset biometric feature, the preset biometric feature exists in a ciphertext form, and the preset biometric feature and the current biometric feature are homomorphically encrypted; and the biometric feature matching unit is used to match the current biometric feature and the preset biometric feature.

[0017] According to an embodiment of the present disclosure, the current payment scenario identification feature exists in the form of ciphertext, and the payment rule determination module includes: a preset scenario feature acquisition unit, a scene feature matching unit and a scene determination unit, the preset scene feature acquisition unit is used to obtain a preset payment scenario identification feature set, the preset payment scenario identification feature set includes preset payment scenario identification features corresponding to N different payment scenarios, N is a positive integer, the preset payment scenario identification feature exists in the form of ciphertext, and the preset payment scenario identification feature and the current payment scenario identification feature are homomorphically encrypted; the scene feature matching unit is used to match the preset payment scenario identification feature in the preset payment scenario identification feature set based on the current payment scenario identification feature; and the scene determination unit is used to determine the corresponding current payment scenario when any preset payment scenario identification feature in the preset payment scenario identification feature set is successfully matched.

[0018] According to an embodiment of the present disclosure, the biometric identification feature includes: a palm print image feature and a palm vein image feature, and the biometric identification feature matching unit is specifically used to, when the current biometric identification feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric identification feature is the preset palm print image feature and the preset palm vein image feature, in parallel match the preset palm print image feature and the preset palm vein image feature based on the current palm print image feature and the current palm vein image feature, wherein, when the current palm print image feature matches the preset palm print image feature and the current palm vein image feature, and the current palm vein image feature matches the preset palm vein image feature, it is determined that the match is successful; or when the current biometric identification feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric identification feature is the preset palm print image feature and the preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature The method comprises the steps of: selecting a palm print image feature and a preset palm vein image feature, matching the preset palm print image feature and the preset palm print image feature, wherein, when the current palm print image feature and the preset palm print image feature are matched, or the current palm vein image feature and the preset palm vein image feature are matched, it is determined that the match is successful; or when the current biometric feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric feature is the preset palm print image feature and the preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature, a matching result is output through a multimodal model; or when the current biometric feature is the current fused image feature, and when the preset biometric feature is the preset fused image feature, matching the preset fused image feature based on the current fused image feature, wherein, when the current fused image feature and the preset fused image feature are matched, it is determined that the match is successful.

[0019] According to an embodiment of the present disclosure, the payment scenario recognition feature includes a gesture image feature, and the scenario feature matching unit is specifically configured to match a preset gesture image feature in the preset payment scenario recognition feature set based on the current gesture image feature.

[0020] According to an embodiment of the present disclosure, the payment scenarios include: normal payment willingness scenarios, abnormal payment willingness scenarios and abnormal scenarios, and the payment rule determination module is specifically used to complete payment according to the first payment amount when the current payment scenario is a normal payment willingness scenario; to complete payment according to the second payment amount when the current payment scenario is an abnormal payment willingness scenario; and to complete payment according to the third payment amount and / or trigger a background alarm when the current payment scenario is an abnormal scenario.

[0021] The fourth aspect of the present disclosure provides a payment device, characterized in that the device is configured in a user terminal, and the device includes: an image acquisition module, used to collect current biometric information and current payment scenario identification information from the user, and the current payment scenario identification feature is collected simultaneously during the current biometric feature acquisition process; a feature extraction module, used to extract features from the current biometric information and the current payment scenario identification information to obtain the current biometric feature and the current payment scenario identification feature; and a feature uploading module, used to upload the current biometric feature and the current payment scenario identification feature to a server.

[0022] According to an embodiment of the present disclosure, the feature extraction module includes: a feature extraction unit and an encryption unit, the feature extraction unit is used to extract features from the current biometric information and the current payment scenario identification information to obtain the current biometric feature plaintext and the current payment scenario identification feature plaintext; and the encryption unit is used to encrypt the current biometric feature plaintext and the current payment scenario identification feature plaintext to obtain the current biometric feature ciphertext and the current payment scenario identification feature ciphertext.

[0023] According to an embodiment of the present disclosure, the feature extraction unit is also used to extract features from the entered biometric information and the entered payment scenario identification information to obtain a preset biometric feature plaintext and a preset payment scenario identification feature plaintext; the encryption unit is also used to encrypt the preset biometric feature plaintext and the preset payment scenario identification feature plaintext to obtain the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext, the preset biometric feature ciphertext and the current biometric feature ciphertext are homomorphically encrypted, and the preset payment scenario identification feature ciphertext and the current payment scenario identification feature ciphertext are homomorphically encrypted; and the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext are sent to the server.

[0024] According to an embodiment of the present disclosure, the biometric identification feature includes: a palm print image feature and a palm vein image feature, and the payment scenario identification feature includes: a gesture image feature.

[0025] A fifth aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned payment method.

[0026] The sixth aspect of the present disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the above-mentioned payment method.

[0027] The seventh aspect of the present disclosure also provides a computer program product, including a computer program, which implements the above-mentioned payment method when executed by a processor.

[0028] In order to solve the technical problem of insufficient payment security in the prior art, in the embodiments disclosed herein, not only the importance of user identity authentication security during payment is taken into account, but also the importance of the security of the payment scene in which the user is located during payment is taken into account. By separately collecting biometric features for identity authentication and payment scene identification features for payment scene determination, the payment rules for the current payment are determined, which greatly improves the security verification level and plays a positive role in protecting personal and property safety. In addition, considering the concealment and imperceptibility of the collection of payment scene identification features, a consistent collection method can be used to collect biometric features and payment scene features respectively, so as to collect the corresponding information in a concealed and imperceptible manner, thereby improving the security of payment. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0030] Figure 1 The application scenario diagram of the payment method according to the embodiment of the present disclosure is schematically shown;

[0031] Figure 2 A flowchart schematically shows a payment method according to an embodiment of the present disclosure;

[0032] Figure 3 A flowchart of an identity recognition method according to an embodiment of the present disclosure is schematically shown;

[0033] Figure 4 A flow chart of a scene recognition method according to an embodiment of the present disclosure is schematically shown;

[0034] Figure 5A flowchart of a payment rule determination method according to an embodiment of the present disclosure is schematically shown;

[0035] Figure 6 A flowchart schematically shows a payment method according to an embodiment of the present disclosure;

[0036] Figure 7 The structure block diagram of the payment device according to the embodiment of the present disclosure is schematically shown;

[0037] Figure 8 A schematic diagram of a payment device according to an embodiment of the present disclosure is shown; and

[0038] Fig. 9 A block diagram of an electronic device suitable for implementing a payment method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0039] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0040] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0041] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0042] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0043] In the technical solution of the present invention, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0044] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present invention provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating an individual's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0045] In the prior art, when making transaction payments, the security of the transaction is only considered from the identity verification side, but the security of the transaction scenario is ignored. The inventors found that in some payment scenarios, the user's payment behavior does not match his or her willingness to pay, which will also greatly reduce the security of the payment.

[0046] In order to solve the technical problems existing in the prior art, an embodiment of the present disclosure provides a payment method, which is applied to a server, and the method includes: receiving a current biometric feature and a current payment scenario identification feature from a user end, wherein the current payment scenario identification feature is collected simultaneously during the collection process of the current biometric feature; identifying the user identity based on the current biometric feature; identifying the current payment scenario based on the current payment scenario identification feature when the user identity is identified; and completing the payment based on the payment rules determined by the current payment scenario.

[0047] In order to solve the technical problem of insufficient payment security in the prior art, in the embodiments disclosed herein, not only the importance of user identity authentication security during payment is taken into account, but also the importance of the security of the payment scene in which the user is located during payment is taken into account. By separately collecting biometric features for identity authentication and payment scene identification features for payment scene determination, the payment rules for the current payment are determined, which greatly improves the security verification level and plays a positive role in protecting personal and property safety. In addition, considering the concealment and imperceptibility of the collection of payment scene identification features, a consistent collection method can be used to collect biometric features and payment scene features respectively, so as to collect the corresponding information in a concealed and imperceptible manner, thereby improving the security of payment.

[0048] Figure 1 The application scenario diagram of the payment method according to the embodiment of the present disclosure is schematically shown.

[0049] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a user terminal device 101 and a server 102 .

[0050] The terminal device 101 may be provided with devices that support various types of biometric feature information collection. For example, the terminal device 101 may support one or more biometric feature information collection devices such as voice recognition equipment, high-definition CCD lens, DC automatic iris lens, placement platform, LED light source, multi-spectral palm print collector, and touch screen.

[0051] The server 102 may be a server that provides computing and storage services, such as a background management server that provides support for websites browsed by users using the terminal device 101 (for example only). The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device. For example, the biometric features collected and entered by the user using the terminal device 101 may be uploaded and stored in the server 102.

[0052] It should be noted that the payment method provided in the embodiment of the present disclosure can generally be executed by the server 102 or the terminal device 101. Accordingly, the payment device provided in the embodiment of the present disclosure can generally be set in the server 102 or the terminal device 101. For the server 102, the payment method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 102 and can communicate with the terminal device 101 and / or the server 102. Accordingly, the payment device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 102 and can communicate with the terminal device 101 and / or the server 102.

[0053] It should be understood that Figure 1 The number of terminal devices and servers in the embodiment is only for illustration. Any number of terminal devices and servers may be provided according to implementation requirements.

[0054] The following will be based on Figure 1 The scene described by Figure 2 to Figure 6 The payment method of the disclosed embodiment is described in detail.

[0055] Figure 2 The flowchart of the payment method according to the embodiment of the present disclosure is schematically shown.

[0056] like Figure 2 As shown, the payment of this embodiment includes operations S210 to S240 , and the payment method can be executed by the server 102 .

[0057] In operation S210, a current biometric identification feature and a current payment scenario identification feature are received from a user terminal, where the current payment scenario identification feature is collected simultaneously during the current biometric identification feature collection process.

[0058] The above-mentioned “simultaneous collection” means that the current biometric identification feature and the current payment scene identification feature are collected simultaneously in the same time period. It should be noted that the above-mentioned payment scene identification feature can be an objective identification feature, such as external objective identification features such as ambient sound, or the above-mentioned payment scene identification feature can also be a subjective identification feature, such as a user's specific gesture.

[0059] The collection methods for biometric features and payment scenario identification features can be the same. For example, when the collection method is to collect facial images, the biometric feature can be the user's facial recognition feature, and the payment environment identification feature can be the surrounding environment during the current user's operation or the user's specific facial expression in the same picture as the facial recognition feature. For example, when the collection method is to collect audio features, the biometric feature can be the user's specific audio (for example, "I agree"), and the payment environment identification feature can be the surrounding environment background sound (for example, whether it is noisy) during the user's operation in the same audio segment as the specific audio or the user's specific tone.

[0060] The means of collecting biometric features and payment scenario identification features may be inconsistent. For example, at the same moment, the biometric feature may be the user's facial recognition feature, while the payment environment identification feature may be the user's audio feature.

[0061] It is understandable that by collecting multiple features for identification at one time, it is possible to covertly collect payment environment identification features. For example, in a scenario where the user is not willing to pay (such as under coercion by criminals), while the image acquisition device on the user side is collecting normal identity recognition features, the image acquisition device on the user side is also collecting payment scene identification features.

[0062] In addition, the current biometric identification feature and the current payment scenario identification feature received from the terminal device 101 on the user side may be plain text data or ciphertext data. Specifically, the current biometric identification feature and the current payment scenario identification feature include plain text data or ciphertext data. In an embodiment of the present disclosure, before obtaining the user's information, the user's consent or authorization may be obtained. For example, before operation S210, a request to obtain the user's information may be issued to the user. When the user agrees or authorizes that the user's information may be obtained, the operation S210 is performed.

[0063] In the embodiments of the present disclosure, a corresponding operation entry may be provided for the user to choose to agree or reject the automated decision result. That is, before the user information is collected and processed / decision-making is performed, the user's instruction to agree or reject the processing / decision-making input through the corresponding operation entry may be obtained. If the user agrees to perform the processing / decision-making, the user information is collected and processed / decision-making is performed, that is, step S210 is executed. If the user refuses to perform the processing / decision-making, the expert decision-making process is entered.

[0064] In operation S220, the user identity is identified based on the current biometric feature.

[0065] Specifically, the biometric identification may be any one or more of the identification methods such as fingerprint identification, palm print identification, palm vein identification, facial recognition, iris recognition, and voice recognition.

[0066] The following will disclose the identity recognition and scene recognition of the embodiment of the present disclosure in detail in the computing mode of multi-party secure computing, as shown below:

[0067] Among them, MPC-Secure Multi-Party Computation is a new type of secure computing model that can achieve secure computing and data sharing among multiple parties without leaking privacy information. In the financial field, banks can achieve secure sharing and risk assessment of customer data through MPC.

[0068] Figure 3 The flowchart of the identity recognition method according to the embodiment of the present disclosure is schematically shown.

[0069] like Figure 3As shown, the identity recognition method of this embodiment includes operations S310 to S320, and the operations S310 to S320 can at least partially execute the above-mentioned operation S220.

[0070] According to an embodiment of the present disclosure, the current biometric feature exists in a ciphertext form.

[0071] In the scenario of multi-party secure computing, the current biometric feature received from the terminal device 101 is an encrypted ciphertext.

[0072] In operation S310, a preset biometric feature is obtained, where the preset biometric feature is in a ciphertext form, and the preset biometric feature and the current biometric feature are homomorphically encrypted.

[0073] The preset biometric features are pre-entered by the user and stored in the server 102, and are used for verification and comparison during identity verification. Specifically, after the user signs a payment agreement with the relevant institution, the relevant institution is allowed to make payment deductions, and the user provides information required for payment verification, such as palm print information, palm artery information, and hand gestures and other biometric information.

[0074] Among them, homomorphic encryption means that the encryption method used for the preset biometric feature and the current biometric feature is the same.

[0075] It can be understood that the ciphertext of the preset biometric feature is consistent with the ciphertext of the current biometric feature collected in terms of encryption method, which ensures the security of user information while performing identity verification directly through the ciphertext data.

[0076] In operation S320, the current biometric feature and the preset biometric feature are matched.

[0077] Specifically, the acquired biometric features are compared with the original template (i.e., the above-mentioned preset biometric features) to verify personal identity. A high degree of feature matching similarity indicates that the features are from the same person as the corresponding original template.

[0078] It is understandable that, since the biometric identification feature can be a single-mode identification feature or a multi-mode identification feature, there are also multiple options for the corresponding matching rules, as shown below:

[0079] Optionally, according to an embodiment of the present disclosure, the biometric feature includes: a palm print image feature and a palm vein image feature, and the matching of the current biometric feature and the preset biometric feature includes: when the current biometric feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric feature is the preset palm print image feature and the preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature, matching the preset palm print image feature and the preset palm print image feature in parallel, wherein when the current palm print image feature and the preset palm print image feature are matched successfully, and the current palm vein image feature and the preset palm vein image feature are matched successfully, it is determined that the match is successful.

[0080] It is understandable that in recent years, there has been an increasing demand for the use of biometric technology for user identity verification and payment. Biometric technologies such as fingerprint recognition and face recognition are constantly developing and updating, and their application scenarios are becoming more and more abundant. The AI ​​composite recognition technology that combines palm prints with palm veins is a relatively new biometric recognition technology. It mainly extracts the texture features of the user's palm image and the palm vein distribution map for identity recognition. With its advantages over other biometric features such as face and fingerprint, it has quickly gained widespread attention. Compared with face recognition technology, palm print and palm vein recognition technology has fast recognition speed, high accuracy, good user experience, strong privacy, and higher acceptance. Compared with fingerprint recognition, it will not wear out and is more difficult to forge. The fingerprint recognition process does not require the user to touch the scanning device, and has the advantage of non-contact.

[0081] Specifically, palm print recognition and palm vein recognition are used in parallel, and when both are passed (for example, the similarity is greater than a preset threshold), it is determined to be a successful match. This solution can improve recognition accuracy and reliability.

[0082] Optionally, according to an embodiment of the present disclosure, the matching of the current biometric feature and the preset biometric feature includes: when the current biometric feature is a current palm print image feature and a current palm vein image feature, and when the preset biometric feature is a preset palm print image feature and a preset palm vein image feature, matching the preset palm print image feature and the preset palm print image feature based on the current palm print image feature and the current palm vein image feature, wherein when the current palm print image feature and the preset palm print image feature are matched successfully, or when the current palm vein image feature and the preset palm vein image feature are matched successfully, it is determined that the match is successful.

[0083] Specifically, palm print recognition and palm vein recognition are used. If one of the two passes, it is determined to be a successful match, thereby improving recognition accuracy and reliability. For example, palm print recognition is used as the main verification method, and palm vein recognition is used as an auxiliary verification method. When the palm print recognition result is questionable or uncertain, palm vein recognition is performed to further confirm the identity, as a complementary verification solution.

[0084] Optionally, according to an embodiment of the present disclosure, the matching of the current biometric feature and the preset biometric feature includes: when the current biometric feature is a current palm print image feature and a current palm vein image feature, and when the preset biometric feature is a preset palm print image feature and a preset palm vein image feature, outputting a matching result through a multimodal model based on the current palm print image feature and the current palm vein image feature.

[0085] Specifically, the palm vein image features and the palm print image features can be used as the input of the multimodal model, and then the matching results can be output to determine whether the match is successful. For example, the palm vein image features and the palm print image features can be given certain weights and used as the input of the multimodal model, and the results of the two output technologies are comprehensively scored. If the comprehensive score is greater than a preset threshold, the match is determined to be successful.

[0086] Optionally, according to an embodiment of the present disclosure, the matching of the current biometric feature and the preset biometric feature includes: when the current biometric feature is a current fusion image feature and when the preset biometric feature is a preset fusion image feature, matching the preset fusion image feature based on the current fusion image feature, wherein when the current fusion image feature matches the preset fusion image feature, it is determined that the match is successful.

[0087] Specifically, the palm vein image features and the palm print image features may be fused into fused image features and matched with preset fused image features, which may improve the discrimination ability and anti-interference of recognition.

[0088] In operation S230, when the user identity recognition is successful, the current payment scenario is identified based on the current payment scenario recognition feature.

[0089] Specifically, the current payment scenario is determined by matching the pre-set payment scenario identification features with the current payment scenario identification features. For example, different gestures correspond to different payment scenarios, and the gesture that should be used in the current payment scenario is determined by comparing the similarity between the pre-stored gestures and the currently acquired gestures.

[0090] Figure 4The flowchart of the scene recognition method according to the embodiment of the present disclosure is schematically shown.

[0091] like Figure 4 As shown, the scene recognition method of this embodiment includes operations S410 to S430, and operations S410 to S430 can at least partially perform the above-mentioned operation S230.

[0092] According to an embodiment of the present disclosure, the current payment scenario identification feature exists in a ciphertext form.

[0093] In operation S410, a preset payment scenario identification feature set is obtained, and the preset payment scenario identification feature set includes preset payment scenario identification features corresponding to N different payment scenarios, where N is a positive integer, and the preset payment scenario identification feature exists in ciphertext form, and the preset payment scenario identification feature and the current payment scenario identification feature are homomorphically encrypted.

[0094] Among them, the preset payment scene recognition feature set is pre-stored by the user in the server 102 and used for verification and comparison during scene recognition. Specifically, after the user signs a payment agreement with the relevant institution, the relevant institution is allowed to make payment deductions, and the user provides payment scene information. For example, one gesture corresponds to one payment scene, and multiple payment scenes corresponding to multiple gestures can be customized. Of course, in addition to gestures, it also includes payment scene recognition features such as expressions and voices, which are not specifically limited here.

[0095] Among them, homomorphic encryption means that the encryption method used for the preset biometric feature and the current biometric feature is the same.

[0096] It can be understood that the ciphertext obtained by obtaining the preset payment scenario identification feature is consistent with the ciphertext of the current payment scenario identification feature collected in terms of encryption method, which ensures the security of user information while directly performing payment scenario identification through ciphertext data.

[0097] It should also be emphasized that the combination of other biometric technologies such as fingerprint, face, voiceprint recognition and gestures, gesture recognition and verification require separate authentication steps to be performed. Compared with the above biometric technologies, the combination of palm print, palm vein recognition and gestures can simultaneously perform multi-modal authentication of palm print + palm vein + gesture combination, which has good concealment and has great advantages and irreplaceability.

[0098] In operation S420, based on the current payment scenario identification feature, the preset payment scenario identification feature in the preset payment scenario identification feature set is matched.

[0099] The preset payment scene identification feature set includes multiple different payment scenes defined by the user, each payment scene corresponds to a payment scene identification feature (e.g., gesture), and the current payment scene identification feature is matched with one of the multiple reserved payment scene identification features. For example, if the similarity between the features of the currently collected gesture and a gesture in the pre-stored gesture feature set is greater than a preset threshold, then the corresponding preset payment scene identification feature can be determined.

[0100] In operation S430, when any one of the preset payment scenario identification features in the preset payment scenario identification feature set is matched successfully, the corresponding current payment scenario is determined.

[0101] Since the pre-stored payment scenario identification features are set with a corresponding relationship with the corresponding payment scenario, the corresponding payment scenario can be found directly through the matching successfully pre-stored payment scenario identification features.

[0102] According to an embodiment of the present disclosure, the payment scenario recognition feature includes a gesture image feature, and identifying the current payment scenario based on the current payment scenario recognition feature includes: matching a preset gesture image feature in the preset payment scenario recognition feature set based on the current gesture image feature.

[0103] Since the pre-stored payment scenario identification features are set with a corresponding relationship with the corresponding payment scenario, the corresponding payment scenario can be found directly through the matching successfully pre-stored payment scenario identification features.

[0104] In a typical scenario, the palm print, palm vein and gesture image data (data entered during registration) collected by the terminal device 101 at the user end through a composite scanner are recorded as A. The data A is processed by the server 102 through an encryption algorithm and stored as A′ (the terminal device 101 at the user end can also convert A into A′ and send it to the server 102). When the palm print, palm vein and gesture information B are read on the front end of the terminal device 101 at the user end, B is encrypted and transmitted to the server 102, and the data is B′. The server 102 uses homomorphic encryption technology to compare and calculate the data A′ and B′. Homomorphic encryption is a type of encryption method with special natural properties, which can perform data operations in the ciphertext domain. Compared with general encryption algorithms, homomorphic encryption can not only realize basic encryption operations, but also realize a variety of calculation functions between ciphertexts. Through multi-party secure computing technology, the use value of data can be obtained without leaking the original collected biometric data content. After comparing and calculating the A′ and B′ data, the identity recognition match is verified and the corresponding system prompt information is returned to the front-end locally according to the customer's customized gesture.

[0105] In operation S240, payment is completed based on the payment rule determined based on the current payment scenario.

[0106] Specifically, the payment scenarios correspond one-to-one to the payment rules, and the payment rules are used to limit the payment limit in the current scenario, the real limit or false limit of the account in the current scenario, and whether the background triggers a security alarm.

[0107] It should be noted that the inventors have found that in some special payment scenarios, no matter what type of identity authentication and biometric technology the customer performs, identity security verification cannot actually avoid the customer's losses. At this time, the customer's personal willingness to purchase and pay is contrary to the actual payment scenario. For example: 1. The customer is hijacked, his personal safety is threatened, and he is coerced to make large payments or transfers; 2. The merchant forces the customer to buy or sell, and the customer does not want to buy the product, but cannot refuse the transaction.

[0108] Figure 5 The flowchart of the payment rule determination method according to the embodiment of the present disclosure is schematically shown.

[0109] like Figure 5 As shown, the payment rule determination method of this embodiment includes operations S510 to S530, and operations S510 to S530 can at least partially execute the above-mentioned operation S240.

[0110] According to an embodiment of the present disclosure, the payment scenarios include: normal willingness to pay scenarios, abnormal willingness to pay scenarios and abnormal scenarios.

[0111] Generally speaking, payment rules are divided into the above three categories: normal willingness to pay scenario, abnormal willingness to pay scenario and abnormal scenario. Among them, the normal willingness to pay scenario refers to the scenario where the payment scenario has no security risk and does not need to limit the payment amount; the abnormal willingness to pay scenario refers to the scenario where the payment scenario has no security risk, but due to abnormal willingness to pay, a certain payment amount needs to be limited; the abnormal scenario refers to the payment scenario where there is a security risk.

[0112] In operation S510, when the current payment scenario is a normal payment willingness scenario, payment is completed according to the first payment amount.

[0113] Generally, the first payment amount is the normal account balance.

[0114] In operation S520, when the current payment scenario is an abnormal payment willingness scenario, payment is completed according to the second payment amount.

[0115] Generally, the second payment amount is defined by the user.

[0116] In a typical scenario, a customer enters a beauty salon and is offered a membership card for a 20,000 yuan recharge. If the customer does not want to buy but cannot refuse, the system can trigger the abnormal payment intention scene gesture of "do not want to buy" through gesture recognition, and the system will return an error message "Insufficient available balance" to the screen and end the transaction. This error message can be personalized according to customer needs during the entry stage.

[0117] In operation S530, when the current payment scenario is an abnormal scenario, payment is completed according to the third payment amount and / or a background alarm is triggered.

[0118] Generally, the third payment limit is defined by the user.

[0119] In a typical scenario, a customer is hijacked in extreme circumstances and his personal safety is threatened. The hijacker takes the customer to a bank branch and asks him to initiate an inter-bank transfer, and confiscates his mobile phone to avoid calling the police. At this time, gesture recognition is used to trigger the dangerous scene gesture of "personal threat". The background alarm logic can also be set according to different customer gestures: 1. The system can return an "appropriate" error and the transaction ends; 2. The system can send a warning SMS and current location information to the third party pre-set by the customer; 3. According to the urgency of the situation at the time, the system can continue to enter the information collection process while sending the warning information, delaying and buying time to rescue the coerced customer.

[0120] In the embodiments of the present disclosure, not only the importance of user identity authentication security during payment is taken into account, but also the importance of the security of the payment scene in which the user is located during payment. By separately collecting biometric features for identity authentication and payment scene identification features for payment scene determination, the payment rules for the current payment are determined, which greatly improves the security verification level and plays a positive role in protecting personal and property safety. In addition, considering the concealment and imperceptibility of the collection of payment scene identification features, a consistent collection method can be used to collect biometric features and payment scene features respectively, so as to collect the corresponding information in a concealed and imperceptible manner, thereby improving the security of payment.

[0121] Figure 6 The flowchart of the payment method according to the embodiment of the present disclosure is schematically shown.

[0122] like Figure 6 As shown, the payment of this embodiment includes operations S610 to S630 , and the payment method can be executed by the terminal device 101 .

[0123] The terminal device 101 is used to collect biometric information of the customer and send the collected information to the server 102 for storage and calculation. For example, the terminal device 101 may include any one or more of biometric information collection devices such as a high-definition CCD lens, a DC automatic iris lens, a placement platform, an LED light source, and a multi-spectral palm print collector. The application scenarios of the terminal device 101 include but are not limited to bank financial purchases, traffic passages, cash registers in shopping malls and hotels, and self-service payment terminals.

[0124] In operation S610, current biometric identification information and current payment scenario identification information are collected from the user, and the current payment scenario identification feature is collected simultaneously during the current biometric identification feature collection process.

[0125] Specifically, for example, biometric information and payment scenario identification information are collected through any one or more of biometric feature information collection devices such as a high-definition CCD lens, a DC automatic iris lens, a placement platform, an LED light source, and a multi-spectral palm print collector.

[0126] According to an embodiment of the present disclosure, the biometric identification feature includes: a palm print image feature and a palm vein image feature, and the payment scenario identification feature includes: a gesture image feature.

[0127] Specifically, the palm vein image is acquired by utilizing the property of hemoglobin in human blood to absorb near-infrared light, and the palm print image is acquired by utilizing a lens.

[0128] In operation S620, features in the current biometric identification information and the current payment scenario identification information are extracted to obtain current biometric identification features and current payment scenario identification features.

[0129] In a typical scenario, the palm print image is preprocessed. For example, the preprocessing process of the palm print image is also called the extraction of the region of interest of the palm print. The commonly used algorithm is the reference coordinate system algorithm. The reference coordinate system is established using the valley points between the fingers, and then the ROI palm print information is extracted according to a certain distance criterion.

[0130] Feature extraction is performed on the preprocessed information, for example, through positioning, enhancement, feature extraction and other algorithms. Feature extraction based on feature learning algorithms mainly use deep neural networks to learn more complex filter structures from data to achieve automatic extraction of palmprint features. After the deep neural network model is processed by multiple layers of neural networks, the feature vector of the corresponding image is finally extracted.

[0131] According to an embodiment of the present disclosure, the extracting features from the current biometric information and the current payment scenario identification information to obtain the current biometric features and the current payment scenario identification features includes: extracting features from the current biometric information and the current payment scenario identification information to obtain the current biometric feature plaintext and the current payment scenario identification feature plaintext; and encrypting the current biometric feature plaintext and the current payment scenario identification feature plaintext to obtain the current biometric feature ciphertext and the current payment scenario identification feature ciphertext.

[0132] Among them, homomorphic encryption means that the encryption method used for the preset biometric feature and the current biometric feature is the same.

[0133] According to an embodiment of the present disclosure, before the above-mentioned operation S610, it also includes: extracting features from the entered biometric information and the entered payment scenario identification information to obtain a preset biometric feature plaintext and a preset payment scenario identification feature plaintext; encrypting the preset biometric feature plaintext and the preset payment scenario identification feature plaintext to obtain the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext, the preset biometric feature ciphertext and the current biometric feature ciphertext are homomorphically encrypted, and the preset payment scenario identification feature ciphertext and the current payment scenario identification feature ciphertext are homomorphically encrypted; and sending the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext to the server.

[0134] Among them, homomorphic encryption means that the encryption method used for the preset biometric feature and the current biometric feature is the same.

[0135] In a typical scenario, the method of entering biometric features and payment scenario features by the customer is as follows: Before making a payment operation, the customer needs to register in the system in advance, sign a payment agreement with the payment company corresponding to the server, and enter the biometric information such as palm print information, palm artery information, and hand gestures required for payment verification. At the same time, the payment limit and gesture processing for different abnormal scenarios can also be personalized in the system. For example, a customer registers as a new user. The customer fills in personal information such as personal name, identity authentication information, address, contact number, and email address online. Sign an agent payment agreement with the payment company corresponding to the storage and processing server, bind bank account and bank card information, and set up password-free payment. The multimodal payment method is successfully opened. Enter the information entry stage. The customer's palm print and palm vein image information are collected through the scanner, stored in the server, and the original data template of the customer is created. On the composite scanner or device that collects palm print + palm vein + gesture, you can touch the screen to prompt: Palm print and palm vein image information collection is completed, do you want to set palm print + gesture double verification. If you choose no, the collection setting is completed. If you select Yes, you can choose to set the payment limit for starting gesture verification or set abnormal scene gestures. If you choose to set a payment limit, you need to enter the specific amount of the payment limit on the touch screen (for example, 10,000 yuan). When the transaction amount is greater than or equal to the set limit, the additional gesture verification process is automatically started. If you choose to set abnormal scene gestures, the customer can choose to set a dangerous gesture warning or set a special gesture. Among them, setting a special gesture 1-"Don't want to buy". In the scenario where the customer has no willingness to pay but cannot refuse, the customer can set the system to return an error "Insufficient available balance" and then exit, which is used as a way to escape from the merchant's marketing. Customers can also continue to set special gestures according to personal needs; 2-You can personalize the system error and system processing actions corresponding to abnormal scene gestures. Customers choose to set a dangerous gesture warning. When the customer's personal safety is threatened, 1. You can choose to exit after setting a system error prompt. 2. You can set the mobile phone number for sending warning information and edit the content of the warning information. 3. You can also choose to set the transaction without exiting the payment process. Save the settings and continue to enter the various gesture action information collection processes. According to the different scenarios selected, different gesture images can be set. The customer's gesture image can be captured and recorded through the scanner. The system can confirm, modify or delete the set gesture image. After the customer confirms that the setting is correct, the collection setting is completed.

[0136] In operation S630, the current biometric identification feature and the current payment scenario identification feature are sent to a server.

[0137] In the embodiments of the present disclosure, not only the importance of user identity authentication security during payment is taken into account, but also the importance of the security of the payment scene in which the user is located during payment. By separately collecting biometric features for identity authentication and payment scene identification features for payment scene determination, the payment rules for the current payment are determined, which greatly improves the security verification level and plays a positive role in protecting personal and property safety. In addition, considering the concealment and imperceptibility of the collection of payment scene identification features, a consistent collection method can be used to collect biometric features and payment scene features respectively, so as to collect the corresponding information in a concealed and imperceptible manner, thereby improving the security of payment.

[0138] Based on the above payment method, the present disclosure also provides a payment device. Figure 7 and Figure 8 The device is described in detail.

[0139] Figure 7 The structural block diagram of a payment device according to an embodiment of the present disclosure is schematically shown.

[0140] like Figure 7 As shown, the payment device 700 of this embodiment includes a feature receiving module 710 , an identity recognition module 720 , a payment scenario recognition module 730 and a payment rule determination module 740 .

[0141] The feature receiving module 710 is used to receive the current biometric feature and the current payment scenario identification feature from the user end, wherein the current payment scenario identification feature is collected simultaneously during the current biometric feature collection process. In one embodiment, the feature receiving module 710 can be used to perform the operation S210 described above, which will not be repeated here.

[0142] The identity recognition module 720 is used to recognize the user's identity based on the current biometric identification feature. In one embodiment, the identity recognition module 720 can be used to perform the operation S220 described above, which will not be described in detail here.

[0143] The payment scenario recognition module 730 is used to recognize the current payment scenario based on the current payment scenario recognition feature when the user identity recognition passes. In one embodiment, the payment scenario recognition module 730 can be used to perform the operation S230 described above, which will not be repeated here.

[0144] The payment rule determination module 740 is used to complete the payment based on the payment rule determined by the current payment scenario. In one embodiment, the payment rule determination module 740 can be used to perform the operation S240 described above, which will not be described in detail here.

[0145] In the embodiments of the present disclosure, not only the importance of user identity authentication security during payment is taken into account, but also the importance of the security of the payment scene in which the user is located during payment. By separately collecting biometric features for identity authentication and payment scene identification features for payment scene determination, the payment rules for the current payment are determined, which greatly improves the security verification level and plays a positive role in protecting personal and property safety. In addition, considering the concealment and imperceptibility of the collection of payment scene identification features, a consistent collection method can be used to collect biometric features and payment scene features respectively, so as to collect the corresponding information in a concealed and imperceptible manner, thereby improving the security of payment.

[0146] According to an embodiment of the present disclosure, the current biometric feature exists in a ciphertext form, and the identity recognition module includes: a preset biometric feature acquisition unit and a biometric feature matching unit, the preset biometric feature acquisition unit is used to acquire a preset biometric feature, the preset biometric feature exists in a ciphertext form, and the preset biometric feature and the current biometric feature are homomorphically encrypted; and the biometric feature matching unit is used to match the current biometric feature and the preset biometric feature.

[0147] According to an embodiment of the present disclosure, the current payment scenario identification feature exists in the form of ciphertext, and the payment rule determination module includes: a preset scenario feature acquisition unit, a scene feature matching unit and a scene determination unit, the preset scene feature acquisition unit is used to obtain a preset payment scenario identification feature set, the preset payment scenario identification feature set includes preset payment scenario identification features corresponding to N different payment scenarios, N is a positive integer, the preset payment scenario identification feature exists in the form of ciphertext, and the preset payment scenario identification feature and the current payment scenario identification feature are homomorphically encrypted; the scene feature matching unit is used to match the preset payment scenario identification feature in the preset payment scenario identification feature set based on the current payment scenario identification feature; and the scene determination unit is used to determine the corresponding current payment scenario when any preset payment scenario identification feature in the preset payment scenario identification feature set is successfully matched.

[0148] According to an embodiment of the present disclosure, the biometric identification feature includes: a palm print image feature and a palm vein image feature, and the biometric identification feature matching unit is specifically used to, when the current biometric identification feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric identification feature is the preset palm print image feature and the preset palm vein image feature, in parallel match the preset palm print image feature and the preset palm vein image feature based on the current palm print image feature and the current palm vein image feature, wherein, when the current palm print image feature matches the preset palm print image feature and the current palm vein image feature, and the current palm vein image feature matches the preset palm vein image feature, it is determined that the match is successful; or when the current biometric identification feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric identification feature is the preset palm print image feature and the preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature The method comprises the steps of: selecting a palm print image feature and a preset palm vein image feature, matching the preset palm print image feature and the preset palm print image feature, wherein, when the current palm print image feature and the preset palm print image feature are matched, or the current palm vein image feature and the preset palm vein image feature are matched, it is determined that the match is successful; or when the current biometric feature is the current palm print image feature and the current palm vein image feature, and when the preset biometric feature is the preset palm print image feature and the preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature, a matching result is output through a multimodal model; or when the current biometric feature is the current fused image feature, and when the preset biometric feature is the preset fused image feature, matching the preset fused image feature based on the current fused image feature, wherein, when the current fused image feature and the preset fused image feature are matched, it is determined that the match is successful.

[0149] According to an embodiment of the present disclosure, the payment scenario recognition feature includes a gesture image feature, and the scenario feature matching unit is specifically configured to match a preset gesture image feature in the preset payment scenario recognition feature set based on the current gesture image feature.

[0150] According to an embodiment of the present disclosure, the payment scenarios include: normal payment willingness scenarios, abnormal payment willingness scenarios and abnormal scenarios, and the payment rule determination module is specifically used to complete payment according to the first payment amount when the current payment scenario is a normal payment willingness scenario; to complete payment according to the second payment amount when the current payment scenario is an abnormal payment willingness scenario; and to complete payment according to the third payment amount and / or trigger a background alarm when the current payment scenario is an abnormal scenario.

[0151] According to an embodiment of the present disclosure, any multiple modules of the acquisition module 710, the identity recognition module 720, the payment scenario recognition module 730 and the payment rule determination module 740 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the acquisition module 710, the identity recognition module 720, the payment scenario recognition module 730 and the payment rule determination module 740 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware and firmware or by a suitable combination of any of them. Alternatively, at least one of the acquisition module 710, the identity recognition module 720, the payment scenario recognition module 730 and the payment rule determination module 740 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be performed.

[0152] Figure 8 The structural block diagram of a payment device according to an embodiment of the present disclosure is schematically shown.

[0153] like Figure 8 As shown, the payment device 800 of this embodiment includes an image acquisition module 810 , a feature extraction module 820 and a feature uploading module 830 .

[0154] The image acquisition module 810 is used to collect the current biometric information and the current payment scenario identification information from the user, and the current payment scenario identification feature is collected simultaneously during the current biometric feature collection process. In one embodiment, the image acquisition module 810 can be used to perform the operation S610 described above, which will not be repeated here.

[0155] The feature extraction module 820 is used to extract features from the current biometric identification information and the current payment scenario identification information to obtain the current biometric identification feature and the current payment scenario identification feature. In one embodiment, the feature extraction module 820 can be used to perform the operation S620 described above, which will not be repeated here.

[0156] The feature uploading module 830 is used to upload the current biometric feature and the current payment scenario identification feature to the server. In one embodiment, the feature uploading module 830 can be used to perform the operation S630 described above, which will not be described in detail here.

[0157] In the embodiments of the present disclosure, not only the importance of user identity authentication security during payment is taken into account, but also the importance of the security of the payment scene in which the user is located during payment. By separately collecting biometric features for identity authentication and payment scene identification features for payment scene determination, the payment rules for the current payment are determined, which greatly improves the security verification level and plays a positive role in protecting personal and property safety. In addition, considering the concealment and imperceptibility of the collection of payment scene identification features, a consistent collection method can be used to collect biometric features and payment scene features respectively, so as to collect the corresponding information in a concealed and imperceptible manner, thereby improving the security of payment.

[0158] According to an embodiment of the present disclosure, the feature extraction module includes: a feature extraction unit and an encryption unit, the feature extraction unit is used to extract features from the current biometric information and the current payment scenario identification information to obtain the current biometric feature plaintext and the current payment scenario identification feature plaintext; and the encryption unit is used to encrypt the current biometric feature plaintext and the current payment scenario identification feature plaintext to obtain the current biometric feature ciphertext and the current payment scenario identification feature ciphertext.

[0159] According to an embodiment of the present disclosure, the feature extraction unit is also used to extract features from the entered biometric information and the entered payment scenario identification information to obtain a preset biometric feature plaintext and a preset payment scenario identification feature plaintext; the encryption unit is also used to encrypt the preset biometric feature plaintext and the preset payment scenario identification feature plaintext to obtain the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext, the preset biometric feature ciphertext and the current biometric feature ciphertext are homomorphically encrypted, and the preset payment scenario identification feature ciphertext and the current payment scenario identification feature ciphertext are homomorphically encrypted; and the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext are sent to the server.

[0160] According to an embodiment of the present disclosure, the biometric identification feature includes: a palm print image feature and a palm vein image feature, and the payment scenario identification feature includes: a gesture image feature.

[0161] According to an embodiment of the present disclosure, any multiple modules of the image acquisition module 810, the feature extraction module 820 and the feature uploading module 830 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the image acquisition module 810, the feature extraction module 820 and the feature uploading module 830 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation modes of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the image acquisition module 810, the feature extraction module 820 and the feature uploading module 830 can be at least partially implemented as a computer program module, and when the computer program module is run, the corresponding function can be executed.

[0162] Fig. 9 A block diagram of an electronic device suitable for implementing a payment method according to an embodiment of the present disclosure is schematically shown.

[0163] like Fig. 9 As shown, the electronic device 900 according to an embodiment of the present disclosure includes a processor 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage part 908 into a random access memory (RAM) 903. The processor 901 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 901 may also include an onboard memory for caching purposes. The processor 901 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0164] In RAM 903, various programs and data required for the operation of electronic device 900 are stored. Processor 901, ROM 902 and RAM 903 are connected to each other via bus 904. Processor 901 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 902 and / or RAM 903. It should be noted that the program can also be stored in one or more memories other than ROM 902 and RAM 903. Processor 901 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0165] According to an embodiment of the present disclosure, the electronic device 900 may further include an input / output (I / O) interface 905, which is also connected to the bus 904. The electronic device 900 may further include one or more of the following components connected to the I / O interface 905: an input portion 906 including a keyboard, a mouse, etc.; an output portion 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 908 including a hard disk, etc.; and a communication portion 909 including a network interface card such as a LAN card, a modem, etc. The communication portion 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the I / O interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed, so that a computer program read therefrom is installed into the storage portion 908 as needed.

[0166] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0167] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus, or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 902 and / or RAM 903 described above and / or one or more memories other than ROM 902 and RAM 903.

[0168] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the item recommendation method provided by the embodiment of the present disclosure.

[0169] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 901. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0170] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 909, and / or installed from a removable medium 911. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0171] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the processor 901, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0172] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0173] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0174] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0175] The embodiments of the present disclosure are described above. However, these embodiments are only for the purpose of illustration and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A payment method, characterized in that: The method is applied in a server, and the method comprises: Receiving a current biometric feature and a current payment scenario recognition feature from a user terminal, wherein the current payment scenario recognition feature is collected simultaneously during the collection process of the current biometric feature; Identifying the user based on the current biometric feature; If the user identity is successfully identified, identifying the current payment scenario based on the current payment scenario identification feature; and The payment is completed based on the payment rules determined based on the current payment scenario.

2. The method according to claim 1, characterized in that The current biometric feature is in encrypted form. The identifying the user identity based on the current biometric feature includes: Acquire a preset biometric feature, wherein the preset biometric feature exists in a ciphertext form, and the preset biometric feature and the current biometric feature are homomorphically encrypted; and The current biometric feature is matched with the preset biometric feature.

3. The method according to claim 2, characterized in that The current payment scenario identification feature exists in encrypted form. The identifying the current payment scenario based on the current payment scenario identification feature includes: Obtain a preset payment scenario identification feature set, the preset payment scenario identification feature set including preset payment scenario identification features corresponding to N different payment scenarios, N is a positive integer, the preset payment scenario identification feature exists in ciphertext form, and the preset payment scenario identification feature and the current payment scenario identification feature are homomorphically encrypted; Based on the current payment scenario identification feature, matching the preset payment scenario identification feature in the preset payment scenario identification feature set; and When any one of the preset payment scenario identification features in the preset payment scenario identification feature set matches successfully, the corresponding current payment scenario is determined.

4. The method according to claim 3, characterized in that The biometric features include: palm print image features and palm vein image features, The matching of the current biometric feature and the preset biometric feature includes: When the current biometric identification feature is a current palm print image feature and a current palm vein image feature, and when the preset biometric identification feature is a preset palm print image feature and a preset palm vein image feature, based on the current palm print image feature and the current palm vein image feature, the preset palm print image feature and the preset palm print image feature are matched in parallel, wherein when the current palm print image feature matches the preset palm print image feature and the current palm vein image feature matches the preset palm vein image feature, it is determined that the match is successful; or When the current biometric identification feature is a current palm print image feature and a current palm vein image feature, and when the preset biometric identification feature is a preset palm print image feature and a preset palm vein image feature, the preset palm print image feature and the preset palm print image feature are matched based on the current palm print image feature and the current palm vein image feature, wherein when the current palm print image feature matches the preset palm print image feature or the current palm vein image feature matches the preset palm vein image feature, it is determined that the match is successful; or When the current biometric feature is a current palm print image feature and a current palm vein image feature, and when the preset biometric feature is a preset palm print image feature and a preset palm vein image feature, outputting a matching result through a multimodal model based on the current palm print image feature and the current palm vein image feature; or When the current biometric feature is the current fused image feature and the preset biometric feature is the preset fused image feature, the preset fused image feature is matched based on the current fused image feature, wherein when the current fused image feature matches the preset fused image feature, it is determined that the match is successful.

5. The method according to claim 4, characterized in that The payment scene recognition feature includes a gesture image feature, The identifying the current payment scenario based on the current payment scenario identification feature includes: Based on the current gesture image feature, a preset gesture image feature in the preset payment scenario recognition feature set is matched.

6. The method according to any one of claims 1 to 5, characterized in that: The payment scenarios include: normal willingness to pay scenario, abnormal willingness to pay scenario and abnormal scenario. The completing payment according to the payment rule determined based on the current payment scenario includes: When the current payment scenario is a normal willingness to pay scenario, completing payment according to the first payment amount; When the current payment scenario is an abnormal payment willingness scenario, completing payment according to the second payment amount; and In the case where the current payment scenario is an abnormal scenario, payment is completed according to the third payment amount and / or a background alarm is triggered.

7. A payment method, characterized in that: The method is applied in a user terminal, and the method includes: Collecting current biometric information and current payment scenario identification information from the user, wherein the current payment scenario identification feature is collected simultaneously during the current biometric feature collection process; Extracting features from the current biometric identification information and the current payment scenario identification information to obtain current biometric identification features and current payment scenario identification features; and The current biometric identification feature and the current payment scenario identification feature are sent to the server.

8. According to the method of claim 7, the extracting features from the current biometric identification information and the current payment scenario identification information to obtain the current biometric identification features and the current payment scenario identification features comprises: Extracting features from the current biometric identification information and the current payment scenario identification information to obtain current biometric identification feature plaintext and current payment scenario identification feature plaintext; as well as The current biometric feature plaintext and the current payment scenario identification feature plaintext are encrypted to obtain the current biometric feature ciphertext and the current payment scenario identification feature ciphertext.

9. The method according to claim 8, wherein: In the collecting of the current biometric identification information and the current payment scenario identification information from the user, wherein the current payment scenario identification feature is collected simultaneously during the current biometric identification feature collection process, the process further includes: Extracting features from the entered biometric information and the entered payment scenario identification information to obtain preset biometric feature plaintext and preset payment scenario identification feature plaintext; Encrypting the preset biometric feature plaintext and the preset payment scenario identification feature plaintext to obtain the preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext, wherein the preset biometric feature ciphertext and the current biometric feature ciphertext are homomorphically encrypted, and the preset payment scenario identification feature ciphertext and the current payment scenario identification feature ciphertext are homomorphically encrypted; and The preset biometric feature ciphertext and the preset payment scenario identification feature ciphertext are sent to the server.

10. The method according to any one of claims 7 to 9, characterized in that: The biometric identification features include: palm print image features and palm vein image features, and the payment scenario identification features include: gesture image features.

11. A payment device, characterized in that: The device is configured in a server, and the device includes: A feature receiving module, used to receive a current biometric feature and a current payment scenario recognition feature from a user terminal, wherein the current payment scenario recognition feature is collected simultaneously during the collection process of the current biometric feature; An identity recognition module, used to recognize the user's identity based on the current biometric feature; a payment scenario identification module, configured to identify a current payment scenario based on the current payment scenario identification feature when the user identity identification passes; and The payment rule determination module is used to complete the payment based on the payment rule determined by the current payment scenario.

12. A payment device, characterized in that: The device is configured in a user terminal, and includes: An image acquisition module, used to acquire current biometric information and current payment scenario identification information from the user, wherein the current payment scenario identification feature is acquired simultaneously during the acquisition process of the current biometric feature; a feature extraction module, used to extract features from the current biometric identification information and the current payment scenario identification information to obtain a current biometric identification feature and a current payment scenario identification feature; and The feature sending module is used to send the current biometric feature and the current payment scenario identification feature to the server.

13. An electronic device, comprising: one or more processors; a storage device for storing one or more computer programs, The method is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 10.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

Images