WO2023273042A1 - 支付方法、系统、电子设备及存储介质 - Google Patents

支付方法、系统、电子设备及存储介质 Download PDF

Info

Publication number
WO2023273042A1
WO2023273042A1 PCT/CN2021/126183 CN2021126183W WO2023273042A1 WO 2023273042 A1 WO2023273042 A1 WO 2023273042A1 CN 2021126183 W CN2021126183 W CN 2021126183W WO 2023273042 A1 WO2023273042 A1 WO 2023273042A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
payment
face
feature
local
Prior art date
Application number
PCT/CN2021/126183
Other languages
English (en)
French (fr)
Inventor
张垚
张帅
Original Assignee
深圳市商汤科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市商汤科技有限公司 filed Critical 深圳市商汤科技有限公司
Publication of WO2023273042A1 publication Critical patent/WO2023273042A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/38Payment protocols; Details thereof
    • G06Q20/40Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401Transaction verification
    • G06Q20/4014Identity check for transactions
    • G06Q20/40145Biometric identity checks

Definitions

  • the present disclosure relates to the technical field of information security, in particular, to a payment method, system, electronic equipment and storage medium.
  • Embodiments of the present disclosure at least provide a payment method, system, electronic device, and storage medium to improve payment efficiency.
  • an embodiment of the present disclosure provides a payment method applied to a local terminal device, including:
  • the legal user includes a user whose payment behavior on the local terminal device first meets the preset condition;
  • the facial features to be recognized can be extracted based on the acquired face pictures of the users to be recognized. In this way, at least one legitimate user in the local facial feature database is read.
  • the face feature to be recognized can be compared with at least one pre-stored face feature, and the comparison result is sent to the server so that the server completes the payment process based on the comparison result.
  • the local terminal device in this disclosure can use the local face feature database for feature comparison, so that the server only needs to implement the payment operation based on the comparison result, especially when there are many local terminal devices and multiple payment requirements Under this circumstance, each local terminal device can perform feature comparison on its own without queuing up at the server for comparison, which will significantly improve the efficiency of payment.
  • the method before the responding to the payment request, the method further includes:
  • the human face quality detection result from the plurality of first human face pictures, determine the target human face picture with the highest quality score, and extract the first human face feature from the target human face picture;
  • a local facial feature database is created according to the first facial features, wherein the pre-stored facial features include the first facial features.
  • the first face feature of the first user may be obtained to construct a local face feature database.
  • the above-mentioned first user may be a peripheral user who uses a local terminal device to pay for items, and the above-mentioned first face feature may be a target face picture with the highest quality score selected from a plurality of first face pictures obtained by the first user.
  • the extracted facial features can improve the feature comparison speed and comparison accuracy of the local terminal device to a certain extent.
  • the method further includes:
  • the first user has the right to register on the local terminal device, determine that the first user is a legal user, and respond to the registration request, and obtain multiple first face pictures of the first user ;
  • the method After extracting the first human face feature from the target human face picture, the method also includes:
  • a local facial feature database is created according to the first facial features.
  • the identity information can be used to verify the registration authority of the first user, and it can also be based on the user's permanent residence.
  • the consistency between the location and the geographic location of the local terminal device is used to determine whether to perform the face feature storage operation, thereby ensuring the security of subsequent face verification.
  • the method also includes:
  • the user feature storage instruction includes at least one second face feature of a second user, and the second user is that the payment behavior data on the local terminal device meets the first 2.
  • the payment behavior data includes payment frequency and/or payment times;
  • the second facial features of the second user with relatively high payment frequency and relatively large number of payments can be synchronized to the local facial feature database to increase the comparison speed.
  • the method after receiving the user characteristic storage instruction sent by the server, the method further includes:
  • the current remaining storage capacity of the local facial feature database is greater than or equal to the data volume of the second facial feature, storing the second facial feature in the local facial feature database; or,
  • the current remaining storage capacity of the local facial feature database is less than the data volume of the second facial feature, according to the second preset condition, delete some facial features from the local facial feature database, and store all the facial features
  • the second face feature is stored in the local face feature database.
  • the creating a local face feature library according to the first face feature includes:
  • the first face feature of the first user can be clustered in combination with the user type, and a corresponding feature sub-library can be created for the classification group, thereby constructing a local face feature library.
  • the face features can be directly selected from the corresponding feature sub-library for comparison, which will further improve the comparison efficiency.
  • the comparing the pre-stored facial features with the facial features to be identified, and determining the comparison result includes:
  • the feature sub-library for comparison can be determined based on the user type of the user to be paid, and then the feature comparison can be realized based on the similarity between features, which is simple and efficient.
  • the method when there are multiple legitimate users whose similarity is greater than a preset threshold in the feature sub-database; the method further includes:
  • user profile construction can be combined with further user screening to ensure the accuracy of the comparison result.
  • the method also includes:
  • the third user is a user whose payment behavior data meets a third preset condition;
  • the payment behavior data includes payment frequency and/or payment times;
  • the face features of the third user whose payment frequency is relatively low and payment times are relatively small can be deleted from the local face feature database, and the storage space of the local terminal device can be increased while ensuring the comparison speed.
  • the method also includes:
  • the comparison result indicates that the comparison is successful, acquiring the account information of the user to be paid, and the face block diagram corresponding to the face picture to be recognized;
  • the sending of the comparison result to the server includes:
  • the server is used to pay based on the comparison result and the account information, and to make payment based on the face frame Check the payment result.
  • the account information of the user to be paid can be determined and sent to the server together with the comparison result so that the server can directly deduct money based on the account information and complete the payment process, further improving payment efficiency.
  • the payment result can also be checked based on the face frame to ensure the smooth progress of the payment operation.
  • the method also includes:
  • a feature comparison request carrying the face picture to be recognized is sent to the server, wherein the feature comparison request is used to request the server based on the Perform feature comparison on the image of the face to be identified, and trigger the server to perform a payment operation if the server comparison is successful;
  • the image of the face to be recognized can be directly sent to the server so that the server can perform feature comparison before payment, improving the service quality of payment.
  • the embodiment of the present disclosure also provides a payment method applied to a server, including:
  • the comparison result is that the local terminal device compares the face features to be recognized of the face picture to be recognized with the pre-stored face features of at least one legal user in the local face feature database obtained by comparison; the legal user includes a user whose behavior on the local terminal device satisfies the first preset condition;
  • a payment operation is performed based on the comparison result.
  • the payment operation can be performed based on the comparison result sent by the local terminal device.
  • the local terminal device can use the local face feature database for feature comparison, so that the server only needs to implement the payment operation based on the comparison result.
  • each local terminal device can perform feature comparison on its own without queuing up at the server for comparison, which will significantly improve the efficiency of payment.
  • the payment operation based on the comparison result includes:
  • the payment operation is performed based on the new comparison result.
  • the method also includes:
  • the payment behavior data generated by historical payment users on the local terminal device; the payment behavior data includes payment frequency and/or payment times;
  • the user characteristic storage instruction is used to instruct the local terminal device to synchronize the information of the historical payment user.
  • the method also includes:
  • the method also includes:
  • the face block diagram is the local terminal device in the case that the comparison result indicates that the comparison is successful, and the face picture to be recognized corresponds to the person who indicates the user to be paid an image of the face part;
  • the payment result is verified based on the face frame diagram.
  • the payment operation based on the comparison result includes:
  • comparison result indicates that the comparison is successful, searching for account information matching the user to be paid from the pre-stored account information of at least one user based on the comparison result;
  • the payment operation is performed based on the found account information matched by the user to be paid.
  • the embodiment of the present disclosure also provides a payment device, which is applied to a local terminal device, including:
  • the response module is used to respond to the payment request, obtain the face picture to be recognized of the user to be paid, and extract the face features to be recognized of the face picture to be recognized;
  • the reading module is used to read the pre-stored facial features of at least one legal user in the local facial feature library; the legal user includes a user whose payment behavior on the local terminal device first satisfies a preset condition;
  • a comparison module configured to compare the pre-stored facial features with the facial features to be identified, and determine a comparison result
  • a sending module configured to send the comparison result to a server, wherein the server is used to make payment according to the comparison result.
  • the embodiment of the present disclosure also provides a payment device applied to a server, including:
  • the obtaining module is used to obtain the comparison result sent by the local terminal device; the comparison result is that the local terminal device compares the face feature to be recognized of the face picture to be recognized with the face feature of at least one legal user in the local face feature database. Pre-stored face features are compared and obtained; the legal user includes a user whose payment behavior on the local terminal device meets the first preset condition;
  • a payment module configured to perform a payment operation based on the comparison result.
  • the embodiment of the present disclosure also provides a payment system, which is characterized in that it includes: the local terminal device described in any one of the first aspect and its implementation manners and any one of the second aspect and its implementation manners The server described in the item.
  • an embodiment of the present disclosure further provides an electronic device, including: a processor, a memory, and a bus, the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the The processor communicates with the memory through a bus, and when the machine-readable instructions are executed by the processor, the payment method described in any one of the first aspect and its implementation, the second aspect and its implementation is executed step.
  • the embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, and the computer program is executed by a processor as in the first aspect and its various implementation modes 1.
  • a computer program is stored, and the computer program is executed by a processor as in the first aspect and its various implementation modes 1.
  • the embodiments of the present disclosure further provide a computer program product, including computer readable codes, or a non-volatile computer readable storage medium carrying computer readable codes, when the computer readable codes are stored in an electronic
  • the processor in the electronic device executes the steps of the payment method described in any one of the first aspect and its various implementations, the second aspect and its various implementations.
  • Figure 1 shows a flow chart of a payment method provided by an embodiment of the present disclosure
  • Fig. 2 shows a flow chart of another payment method provided by an embodiment of the present disclosure
  • Fig. 3 shows a schematic diagram of a payment system provided by an embodiment of the present disclosure
  • Fig. 4 shows a schematic diagram of a payment device provided by an embodiment of the present disclosure
  • Fig. 5 shows a schematic diagram of another payment device provided by an embodiment of the present disclosure
  • FIG. 6 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure
  • Fig. 7 shows a schematic diagram of another electronic device provided by an embodiment of the present disclosure.
  • the present disclosure provides a payment method, device, electronic device and storage medium to improve payment efficiency.
  • the execution subject of the payment method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities.
  • the computer device is, for example, Including: terminal equipment or other processing equipment, terminal equipment can be user equipment (User Equipment, UE), mobile equipment, user terminal, terminal, cellular phone, cordless phone, personal digital assistant (Personal Digital Assistant, PDA), handheld device, Computing devices, in-vehicle devices, wearable devices, etc.
  • the payment method may be implemented by a processor invoking computer-readable instructions stored in a memory.
  • the method includes steps S101 to S104, wherein:
  • S101 Respond to the payment request, obtain the face picture to be recognized of the user to be paid, and extract the face features to be recognized from the face picture to be recognized;
  • S102 Read at least one pre-stored face feature of a legal user in the local face feature database; the legal user includes the user whose payment behavior on the local terminal device first meets the preset condition;
  • S104 Send the comparison result to the server, where the server is used to make payment according to the comparison result.
  • the above payment method can be mainly applied to at least one payment scenario, and can be mainly applied to face payment, for example, it can be applied to an unmanned supermarket scenario.
  • Embodiments of the present disclosure provide a payment method, device, electronic equipment, and storage medium, so as to improve payment efficiency.
  • the face features to be recognized can be extracted based on the obtained face pictures to be recognized, and the pre-stored face features of at least one legal user in the local face feature database can be read.
  • the comparison result can be sent to the server so that the server can complete the payment process based on the comparison result.
  • the face picture to be recognized may be collected by a camera set on the local terminal device, that is, when there is a payment request, the camera may start a collection operation to capture the face of the user to be paid.
  • the camera may start a collection operation to capture the face of the user to be paid.
  • Different application scenarios correspond to different users to be paid, so details will not be repeated here.
  • the local terminal device When the local terminal device captures the face, it can extract the face features to be recognized from the face picture to be recognized, and compare the face features to be recognized with the pre-stored face features of at least one legal user in the local face feature database. Comparison. Here, based on the similarity between the two features, it can be determined whether the user to be paid is a legitimate user, and when it is determined that the user to be paid is a legitimate user, the comparison result can be notified to the server so that the server can complete the follow-up In the payment process, if the user to be paid is determined to be an illegal user, the face picture to be recognized can be directly sent to the server so that the server can perform identity comparison again, and can complete the follow-up if the identity comparison is successful. payment process.
  • the payment method provided by the embodiment of the present disclosure prefers to complete the identity comparison on the local terminal device side, so that even if there are many local terminal devices, it will not cause the need to queue up on the server side for identity comparison.
  • the time-consuming problem has significantly improved the efficiency of subsequent payment.
  • the embodiment of the present disclosure can also use the server to perform identity comparison again when the comparison of the local terminal device fails. This is mainly because the server often has stronger computing power and richer data resources. In this way, the success rate of comparison can be improved and the security of payment can be ensured.
  • the local face feature library here may collect at least one pre-stored face feature of a legal user, and the legal user may include users whose behavior on the local terminal device meets preset conditions. For example, it may be a user who has pre-registered on the local terminal device, or a user who often pays on the local terminal device, etc., or other users who meet the preset conditions. limit.
  • the comparison result and the acquired face picture to be recognized may be sent to the server.
  • the local terminal device when the local terminal device fails to compare, it can send a feature comparison request carrying a face picture to be recognized to the server.
  • the server receives the feature comparison request, it can trigger the server to complete the payment process if the comparison is successful based on the image of the face to be recognized.
  • the picture of the face to be recognized can be sent at the same time, but also the frame of the face extracted from the picture of the face to be recognized can be sent at the same time.
  • the face frame diagram corresponds to the face area of the user to be paid.
  • a series of operations such as face frame extraction, face feature extraction, and feature comparison can be performed on the server side to complete the payment process.
  • a series of operations such as face frame extraction, face feature extraction, and feature comparison.
  • the local terminal device when it is determined that the comparison result indicates that the comparison fails, the local terminal device can also obtain the account information of the user to be paid, and send the comparison result and account information to the server.
  • the account information here can be information related to the account to be deducted by the user to be paid, for example, it can be bank card number information, user name information of a third-party payment platform, etc.
  • the account information sent by the server through the local terminal device can be sent to The corresponding deduction platform initiates a deduction command and executes the final deduction action to complete the payment process.
  • the face frame when the comparison result indicates that the comparison is successful, can also be extracted from the acquired face picture to be recognized, and the extracted face frame can be sent to the server for archiving.
  • the payment operation involves user property. Once a problem occurs, it is often necessary to trace back the cause of the payment problem in a timely manner, and the archive of the small image (that is, the face frame) can help the payment result.
  • Check, and the small picture is transmitted to the server through the local terminal device, and it will not occupy too much network bandwidth.
  • the at least one pre-stored face feature included in the local face feature library in the embodiment of the present disclosure may be determined by the relevant user after registering on the local terminal device, or determined by the server based on the payment behavior of the relevant user.
  • Step 1 receiving a registration request of the first user initiated on the local terminal device
  • Step 2 Respond to the registration request and obtain multiple first face pictures of the first user;
  • Step 3 inputting a plurality of first human face pictures into the human face quality detection model to obtain the human face quality detection result;
  • Step 4 according to the human face quality detection result, from a plurality of first human face pictures, determine the target human face picture with the highest quality score, and extract the first human face feature from the target human face picture;
  • Step 5 Create a local facial feature library according to the first facial feature, wherein the pre-stored facial features include the first facial feature.
  • the first face picture may be obtained in response to the registration request of the first user, and when the face feature is extracted from the first face picture, the first face feature may be stored in a local face feature database.
  • the local terminal device can support user input, for example, a face image can be collected and input through a camera.
  • a face image can be collected and input through a camera.
  • multiple face pictures can be entered for a user.
  • the face quality scoring can be performed on the multiple first face pictures corresponding to the first user.
  • the quality score can be selected The tallest image of a human face.
  • the above-mentioned face quality detection model is used to determine the features related to the picture quality based on the analysis of the clarity, completeness and exposure of the face picture, and determine the picture quality score based on these features.
  • the first face feature of this face picture can be added to the local face.
  • the embodiments of the present disclosure also support inputting other information, for example, inputting personnel account information through a keyboard.
  • the face picture, face features and corresponding account information can be synchronized to the server, so as to keep the synchronization between the server and the local terminal device, and facilitate the server to manage multiple devices.
  • the identity information can be used to verify the registration authority of the first user, specifically through follow these steps to achieve:
  • Step 1 Obtain the identity information of the first user
  • Step 2 Based on the identification information, it is judged whether the first user has the right to register on the local terminal device;
  • Step 3 If the first user has the right to register on the local terminal device, determine that the first user is a legitimate user, and respond to the registration request to obtain multiple first face pictures of the first user.
  • the identity information whether the first user has registration authority.
  • the user here can be the owner of the local terminal device, or the manager of the local terminal device, or someone else with registration authority. User.
  • the face feature warehousing operation it is also possible to determine whether to carry out the face feature warehousing operation based on the consistency between the user's permanent residence and the geographic location to which the local terminal device belongs, that is, if the first user's permanent residence is consistent with the local terminal device's
  • the geographical location of the devices is consistent, which to a certain extent shows the rationality of face feature entry on the local terminal device.
  • the first user may be a resident of the community.
  • a local face feature library can be created according to the first face feature, thereby further ensuring the security of subsequent face verification.
  • the local face feature database can be updated according to the following steps:
  • Step 1 Receive the user feature storage instruction sent by the server; the user feature storage instruction includes the second face feature of at least one second user, and the second user is a person whose payment behavior data on the local terminal device meets the second preset condition User; payment behavior data including payment frequency and/or number of payments;
  • Step 2 storing the second face feature in the local face feature database.
  • the first preset condition here may be the condition that the payment frequency is higher than the preset frequency, and the payment times are greater than the preset times. That is to say, in the present disclosure, when the server determines that certain users (that is, second users) often make payments on the local terminal device, automatically synchronize the facial features of these users to the local facial feature library of the terminal device, to increase the comparison speed.
  • the second face feature is stored in the local face feature library; if the current remaining storage capacity of the local face feature library is less than the data amount of the second face feature, according to the second preset condition, from Some facial features are deleted from the local facial feature database, and the second facial features are stored in the local facial feature database.
  • the face features of users with relatively low payment frequency and relatively few payment times can be deleted.
  • the local face feature database can also be updated according to the following steps:
  • Step 1 Receive a feature deletion instruction for at least one third user sent by the server; the third user is a user whose payment behavior data meets the third preset condition; the payment behavior data includes payment frequency and/or payment times;
  • Step 2 Delete the face feature of the third user from the local face feature database to obtain an updated local face feature database.
  • the third preset condition here can be the condition that the payment frequency is lower than or equal to the preset frequency, and the number of payments is less than or equal to the preset number of times. In addition, it can also be that the payment duration from the current time exceeds the preset duration.
  • One condition That is to say, the present disclosure can delete the user from the local facial feature database when the server determines that some users (ie, the third user) have not made payment on the local terminal device for a long time, and the user is in the local facial feature database. facial features to maintain a relatively fixed data size locally to ensure that the storage space of the local terminal device is sufficient.
  • the information of the third user may be retained on the server side, so as to perform information synchronization in a timely manner when information synchronization is required.
  • the payment method provided by the embodiments of the present disclosure can establish a feature sub-base based on face feature clustering, and then realize fast face comparison based on the feature comparison of the feature sub-base.
  • the above-mentioned database building scheme can be realized through the following steps:
  • Step 1 Determine the user type to which the first user belongs
  • Step 2 cluster the first facial features to obtain multiple classification groups
  • Step 3 Create a feature sub-library for the classification group
  • Step 4 Construct a local face feature library according to multiple feature sub-databases.
  • face feature comparison can be performed based on the user type, and then a local face feature library can be created based on the feature sub-base corresponding to the classification group.
  • the foregoing user types may be determined based on different application scenarios. Taking the unmanned supermarket as an example, the user types here can be students, parents, elderly, etc. For different types of students, the corresponding first facial features are different, and then can be stored in different local Face feature library.
  • clustering can also be combined with information such as user preferences.
  • clustering methods such as K-means can be used to implement clustering, and details will not be described here.
  • the feature comparison can be performed as follows:
  • Step 1 Based on the user type to which the user to be paid belongs, determine the feature sub-base corresponding to the face feature to be recognized;
  • Step 2 determining the similarity between the face feature to be recognized and at least one pre-stored face feature in the determined feature sub-library;
  • Step 3 If there is a legitimate user whose similarity is greater than the preset threshold in the feature sub-database, determine that the comparison is successful; if there is no legitimate user whose similarity is greater than the preset threshold in the feature sub-database, determine that the comparison is fail.
  • the feature sub-library corresponding to the user to be paid can be locked based on the user type, and then the similarity between at least one pre-stored face feature in the feature sub-library and the face feature to be recognized in the face picture to be recognized can be determined, similar
  • the comparison in the case that there is a legitimate user whose similarity is greater than the preset threshold in the feature sub-database, it can be determined that the comparison is successful, so as to complete the identity comparison, and there is no legal user whose similarity is greater than the preset threshold in the feature sub-database.
  • a legitimate user it is determined that the comparison fails, and a request for another comparison is initiated to the server to complete the subsequent payment process.
  • the feature similarity here can be determined based on the cosine formula.
  • Step 1 Obtain the portrait description features of multiple legitimate users
  • Step 2 Construct user portraits for multiple legitimate users based on the acquired portrait description features
  • Step 3 Compare the user portraits corresponding to the multiple legitimate users with the user portraits of the user to be paid, and select the legitimate user with the highest user portrait matching degree from the multiple legitimate users as the legitimate user who has successfully compared.
  • the portrait description feature here can describe at least one user from more feature dimensions, and the more comprehensive dimensional description makes the feature comparison result more targeted and improves the comparison accuracy.
  • the face picture and related personal information of at least one owner in the community can be entered in advance on the local terminal equipment set in the supermarket, and these owners can serve as resident of the local terminal equipment member.
  • the information of the new owner can be entered into the local terminal device, or when the server determines that the new owner has frequent payment behaviors, the facial features can be automatically synchronized to the local terminal device for New owners can quickly complete local identity comparison.
  • the owner's information can be deleted on the local terminal device, or the server can initiate deletion of the owner's information to the local terminal device when the server determines that the owner has not paid for a long time instructions to make full use of the storage space of the local terminal device.
  • the execution body of the payment method may be a server, and in a specific application, it may be a cloud server.
  • the above method includes steps S201-S202, wherein:
  • S201 Obtain the comparison result sent by the local terminal device; the comparison result is that the local terminal device compares the face feature to be recognized in the face picture to be recognized with the pre-stored face feature of at least one legitimate user in the local face feature database Obtained; legal users include users whose payment behavior on the local terminal device meets the first preset condition;
  • the server here can perform the payment operation based on the comparison result sent by the local terminal device.
  • the comparison result above can be obtained by the local terminal device comparing the face features to be recognized in the face picture to be recognized with the pre-stored face features of at least one legal user in the local face feature database.
  • the identity comparison when it is determined that the identity comparison of the local terminal device fails, the identity comparison can be performed again on the server side, and subsequent payment operations can be performed, which can be specifically implemented through the following steps:
  • Step 1 When the comparison result indicates that the comparison fails, receive the face picture to be recognized sent by the local terminal device;
  • Step 2 Perform feature comparison of the user to be paid based on the face image to be recognized, and obtain a new comparison result
  • Step 3 Perform payment operation based on the new comparison result.
  • the identity comparison process on the server side can be determined based on the face database, where the face database can contain at least one authorized user's face picture and corresponding personal information, which is better than that of the local terminal to a certain extent.
  • the user coverage of the local face feature database in the device is wider.
  • the specific feature comparison method is similar and will not be repeated here.
  • the local terminal device when it is determined that the identity comparison of the local terminal device is successful, can send the comparison result and account information to the server for payment, or only send the comparison result to the server.
  • the server can search for the account information matching the user to be paid from the pre-stored account information of at least one user based on the comparison result, and perform the payment operation based on the found account information matching the user to be paid.
  • the payment operation can be performed according to the following steps :
  • Step 1 Judging whether the account balance pointed to by the account information of the user to be paid meets the preset payment amount, and obtaining the judgment result;
  • Step 2 Perform payment operation based on the judgment result.
  • a deduction application can be initiated to the account bound to the user to be paid.
  • the account balance of the user to be paid is greater than the payment amount, based on the previous identity verification
  • the corresponding payment amount can be directly deducted from the account bound by the payment user to successfully complete the payment.
  • payment failure information may be generated to remind the payee that the user to be paid needs to pay again.
  • the entire balance in the account bound by the user to be paid can be directly deducted, and a reminder that there is still a part of the balance that has not been paid.
  • the thumbnail file can also be archived to check the payment result. That is to say, the payment check instruction can be used here to check the payment result based on the face block diagram extracted from the face picture to be recognized. The specific verification method will not be repeated here, and details can be referred to the above description.
  • the embodiments of the present disclosure can add information according to the following steps:
  • Step 1 Obtain payment behavior data generated by historical payment users on local terminal devices; payment behavior data includes payment frequency and/or payment times;
  • Step 2 When the payment behavior data satisfies the second preset condition, generate a user characteristic storage instruction pointing to the historical payment user;
  • Step 3 Send the user characteristic storage instruction to the local terminal device, the user characteristic storage instruction is used to instruct the local terminal device to synchronize the information of the historical payment user.
  • the second preset condition here may be the condition that the payment frequency is higher than the preset frequency, and the payment times are greater than the preset times. That is to say, the present disclosure can automatically synchronize the information of these users (such as face pictures or personal information, etc.) speed.
  • the embodiments of the present disclosure can delete information according to the following steps:
  • Step 1 When the payment behavior data satisfies the third preset condition, generate a feature deletion instruction directed to the historical payment user;
  • Step 2 Send a feature deletion command to the local terminal device, the feature deletion command is used to instruct the local terminal device to delete the information of the historical payment user.
  • the third preset condition here can be the condition that the payment frequency is lower than or equal to the preset frequency, and the number of payments is less than or equal to the preset number of times. In addition, it can also be that the payment duration from the current time exceeds the preset duration.
  • One condition That is to say, the present disclosure can delete the user's information from the local terminal device when the server determines that some users have not made payment at the local terminal device for a long time, and the user is at the local terminal device, so as to maintain a relatively fixed local The data scale ensures that the storage space of the local terminal device is sufficient.
  • the writing order of each step does not mean a strict execution order and constitutes any limitation on the implementation process.
  • the specific execution order of each step should be based on its function and possible
  • the inner logic is OK.
  • the embodiment of the present disclosure also provides a payment system, as shown in FIG. 3 , the payment system realizes For the feature comparison of the local terminal device and the payment on the server side, refer to the above description for the specific implementation process of the local terminal device and the server, and will not repeat them here.
  • the embodiment of the present disclosure also provides a payment device corresponding to the payment method. Since the problem-solving principle of the device in the embodiment of the present disclosure is similar to the above-mentioned payment method in the embodiment of the present disclosure, the implementation of the device can refer to the method The implementation of this method will not be repeated here.
  • the device includes: a response module 401, a reading module 402, a comparison module 403 and a sending module 404; wherein,
  • the response module 401 is used to respond to the payment request, obtain the face picture to be recognized of the user to be paid, and extract the face feature to be recognized from the face picture to be recognized;
  • the reading module 402 is used to read the pre-stored facial features of at least one legal user in the local facial feature library; the legal user includes the user whose payment behavior at the local terminal device first meets the preset condition;
  • Comparison module 403 for comparing the pre-stored facial features with the facial features to be identified, to determine the comparison result
  • the sending module 404 is configured to send the comparison result to the server, wherein the server is used to make payment according to the comparison result.
  • the face features to be recognized can be extracted based on the acquired face pictures of the user to be recognized. In this way, at least one legitimate user in the local face feature database is read.
  • the face feature to be recognized can be compared with at least one pre-stored face feature, and the comparison result is sent to the server so that the server completes the payment process based on the comparison result.
  • the local terminal device in this disclosure can use the local face feature database for feature comparison, so that the server only needs to implement the payment operation based on the comparison result, especially when there are many local terminal devices and multiple payment requirements Under this circumstance, each local terminal device can perform feature comparison on its own without queuing up at the server for comparison, which will significantly improve the efficiency of payment.
  • the above reading module 402 is also used for:
  • the human face quality detection result from a plurality of first human face pictures, determine the target human face picture with the highest quality score, and extract the first human face feature from the target human face picture;
  • a local face feature database is created according to the first face feature, wherein the pre-stored face feature includes the first face feature.
  • the above reading module 402 is also used for:
  • the first user has the authority to register on the local terminal device, determine that the first user is a legitimate user, and respond to a registration request to obtain multiple first face pictures of the first user;
  • a local facial feature database is created according to the first facial features.
  • the above reading module 402 is also used for:
  • the user feature storage instruction includes the second face feature of at least one second user, and the second user is a user whose payment behavior data on the local terminal device meets the second preset condition; Behavioral data including payment frequency and/or number of payments;
  • the second face feature is stored in a local face feature database.
  • the above reading module 402 is also used for:
  • the second facial feature is stored in the local facial feature database
  • the above-mentioned reading module 402 is used to create a local face feature library according to the first face feature according to the following steps:
  • the comparison module 403 is used to compare the pre-stored face features with the face features to be recognized according to the following steps, and determine the comparison result:
  • the above-mentioned comparison module 403 is also used for:
  • the above reading module 402 is also used for:
  • the third user is a user whose payment behavior data meets the third preset condition;
  • the payment behavior data includes payment frequency and/or payment times;
  • the facial features of the third user are deleted from the local facial feature database to obtain an updated local facial feature database.
  • the above sending module 404 is also configured to:
  • the server Send the comparison result, account information, and face frame to the server; the server is used to pay based on the comparison result and account information, and to check the payment result based on the face frame.
  • the above sending module 404 is also configured to:
  • FIG. 5 is a schematic diagram of another payment device provided by an embodiment of the present disclosure
  • the device includes: an acquisition module 501 and a payment module 502; wherein,
  • the obtaining module 501 is used to obtain the comparison result sent by the local terminal device; the comparison result is that the local terminal device compares the face feature to be recognized of the face picture to be recognized with the pre-stored face of at least one legal user in the local face feature database Features are compared; legitimate users include users whose payment behavior on the local terminal device meets the first preset condition;
  • the payment module 502 is configured to perform a payment operation based on the comparison result.
  • the payment operation can be performed based on the comparison result sent by the local terminal device, where the local terminal device can use the local face feature database for feature comparison, so that the server only needs to implement the payment operation based on the comparison result.
  • each local terminal device can perform feature comparison on its own without queuing up at the server for comparison, which will significantly improve the efficiency of payment.
  • the payment module 502 is configured to perform a payment operation based on the comparison result according to the following steps:
  • the feature comparison of the user to be paid is performed to obtain a new comparison result
  • the payment operation is performed based on the new comparison result.
  • the above-mentioned device also includes:
  • the synchronization module 503 is used to acquire payment behavior data generated by historical payment users on local terminal devices; the payment behavior data includes payment frequency and/or payment times; when the payment behavior data meets the second preset condition, generate a link to the historical payment behavior data.
  • the user's user feature storage instruction ; send the user feature storage instruction to the local terminal device, and the user feature storage instruction is used to instruct the local terminal device to synchronize the information of the historical payment user.
  • the above-mentioned device also includes:
  • the deletion module 504 is used to generate a feature deletion instruction directed to the historical payment user when the payment behavior data meets the third preset condition; send the feature deletion instruction to the local terminal device, and the feature deletion instruction is used to instruct the local terminal device to delete the history Payment user information.
  • the acquiring module 501 is also configured to:
  • the face block diagram is an image corresponding to the face part of the user to be paid in the face picture to be recognized when the comparison result of the local terminal device indicates that the comparison is successful;
  • the payment result is verified based on the face block diagram.
  • the payment module 502 is configured to perform a payment operation based on the comparison result according to the following steps:
  • the account information matching the user to be paid is searched from the pre-stored account information of at least one user based on the comparison result;
  • the payment operation is performed based on the found account information matched by the user to be paid.
  • FIG. 6 is a schematic structural diagram of the electronic device provided by the embodiment of the present disclosure, including: a processor 601 , a memory 602 , and a bus 603 .
  • the memory 602 stores machine-readable instructions executable by the processor 601 (for example, execution instructions corresponding to the response module 401, the reading module 402, the comparison module 403, and the sending module 404 in the device in FIG.
  • the processor 601 communicates with the memory 602 through the bus 603, and when the machine-readable instructions are executed by the processor 601, the following processes are performed:
  • the legal users include users whose payment behavior on the local terminal device meets the first preset condition;
  • the comparison result is sent to the server, wherein the server is used to make payment according to the comparison result.
  • the embodiment of the present disclosure also provides an electronic device, as shown in FIG. 7 , which is a schematic structural diagram of the electronic device provided by the embodiment of the present disclosure, including: a processor 701 , a memory 702 , and a bus 703 .
  • the memory 702 stores machine-readable instructions executable by the processor 701 (for example, execution instructions corresponding to the acquisition module 501 and the payment module 502 in the device in FIG. communicate through the bus 703, and the machine-readable instructions are executed by the processor 701 to perform the following processing:
  • the comparison result sent by the local terminal device; the comparison result is obtained by the local terminal device comparing the face features to be recognized in the face picture to be recognized with the pre-stored face features of at least one legal user in the local face feature database ; Legitimate users include users whose payment behavior on the local terminal device meets the first preset condition;
  • the payment operation is performed based on the comparison result.
  • Embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the payment method described in the foregoing method embodiments are executed.
  • the storage medium may be a volatile or non-volatile computer-readable storage medium.
  • the embodiment of the present disclosure also provides a computer program product, the computer program product carries a program code, and the instructions included in the program code can be used to execute the steps of the payment method described in the above method embodiment, for details, please refer to the above method implementation example, which will not be repeated here.
  • the above-mentioned computer program product may be specifically implemented by means of hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) etc. Wait.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium executable by a processor.
  • the technical solution of the present disclosure is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present disclosure.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disc and other media that can store program codes. .

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Computer Security & Cryptography (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Collating Specific Patterns (AREA)

Abstract

提供了一种支付方法、装置、电子设备及存储介质,其中,方法包括:响应支付请求,获取待支付用户的待识别人脸图片,并提取待识别人脸图片的待识别人脸特征(S101);读取本地人脸特征库中至少一个合法用户的预存人脸特征;合法用户包括在本地终端设备的支付行为满足第一预设条件的用户(S102);将预存人脸特征与待识别人脸特征进行比对,确定比对结果(S103);将比对结果发送至服务器,服务器用于根据比对结果进行支付(S104)。

Description

支付方法、系统、电子设备及存储介质
本申请要求2021年06月30日提交、申请号为202110736082.6,发明名称为“支付方法、系统、电子设备及存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本公开涉及信息安全技术领域,具体而言,涉及一种支付方法、系统、电子设备及存储介质。
背景技术
随着互联网技术的发展,基于互联网进行支付的方式已经非常普及,例如,扫码支付、指纹支付和人脸支付。其中,人脸支付由于用户不用携带自身的移动设备的良好体验而得以广泛关注。
在进行人脸支付的过程中,往往需要接入具有刷脸功能的支付设备,在这一支付设备中展示人脸以进行支付操作。由于支付本身的严谨性,需要经过比较复杂的验证,目前市面上的支付设备大都采用云端识别的方式,也就是在支付终端进行人脸采集,然后送至云端进行识别并支付。
发明内容
本公开实施例至少提供一种支付方法、系统、电子设备及存储介质,以提升支付效率。
第一方面,本公开实施例提供了一种支付方法,应用于本地终端设备,包括:
响应支付请求,获取待支付用户的待识别人脸图片,并提取所述待识别人脸图片的待识别人脸特征;
读取本地人脸特征库中至少一个合法用户的预存人脸特征;所述合法用户包括在所述本地终端设备的支付行为第一满足预设条件的用户;
将所述预存人脸特征与所述待识别人脸特征进行比对,确定比对结果;
将所述比对结果发送至服务器,其中,所述服务器用于根据所述比对结果进行支付。
采用上述支付方法,在响应支付请求的情况下,可以基于获取的待支付用户的待识别人脸图片提取出待识别人脸特征,这样,在读取到本地人脸特征库中至少一个合法用户的预存人脸特征的情况下,可以将待识别人脸特征与至少一个预存人脸特征进行比对,并将比对结果发送至服务器以使服务器基于比对结果完成支付过程。本公开中的本地终端设备能够利用本地人脸特征库进行特征比对,这样服务器仅需基于比对结果实现支付操作即可,特别是在本地终端设备比较多,并具有多个支付需求的情况下,各本地终端设备可以自行进行特征比对,无需在服务器排队进行比对,这将显著提升支付的效率。
在一种可能的实施方式中,所述响应支付请求,获取待支付用户的待识别人脸图片之前,所述方法还包括:
接收在所述本地终端设备上发起的第一用户的注册请求;
响应所述注册请求,获取所述第一用户的多张第一人脸图片;
将所述多张第一人脸图片输入至人脸质量检测模型,获得人脸质量检测结果;
根据所述人脸质量检测结果,从所述多张第一人脸图片中,确定质量分数最高的目标人脸图片,并从所述目标人脸图片中提取第一人脸特征;
根据所述第一人脸特征,创建本地人脸特征库,其中,所述预存人脸特征包括所述第一人脸特征。
这里,可以基于第一用户的注册请求,获取第一用户的第一人脸特征进而构建得到本地人脸特征库。上述第一用户可以是使用本地终端设备进行物品支付的周边用户,上述第一人脸特征可以是从第一用户获取的多张第一人脸图片中选取的质量分数最高的目标人脸图片中提取出的人脸特征,该人俩特征一定程度上可以提升本地终端设备的特征比对速度和对比准确度。
在一种可能的实施方式中,接收在所述本地终端设备上发起的第一用户的注册请求之后,所述方法还包括:
获取所述第一用户的身份标识信息;
基于所述身份标识信息,判断所述第一用户是否具备在所述本地终端设备上进行注册的权限;
若所述第一用户具备在所述本地终端设备上进行注册的权限,确定所述第一用户为合法用户,并响应所述注册请求,获取所述第一用户的多张第一人脸图片;
所述从所述目标人脸图片中提取第一人脸特征之后,所述方法还包括:
判断所述第一用户的常住地与所述本地终端设备所属的地理位置是否一致;
若所述第一用户的常住地与所述本地终端设备所属的地理位置一致,根据所述第一人脸特征,创建本地人脸特征库。
这里,为了进一步确保本地人脸特征库中所存储的人脸特征对应用户的合法性,在接收注册请求之后,可以利用身份标识信息对第一用户进行注册权限的验证,还可以基于用户的常住地与本地终端设备所属的地理位置之间的一致性来确定是否进行人脸特征入库操作,从而确保了后续进行人脸核对的安全性。
在一种可能的实施方式中,所述方法还包括:
接收所述服务器发送的用户特征存储指令;所述用户特征存储指令中包括至少一个第二用户的第二人脸特征,所述第二用户为在所述本地终端设备上的支付行为数据满足第二预设条件的用户;所述支付行为数据包括支付频率和/或支付次数;
将所述第二人脸特征存储至所述本地人脸特征库。
这里,可以将支付频率比较高、支付次数比较多的第二用户的第二人脸特征同步到本地人脸特征库,以提升比对速度。
在一种可能的实施方式中,所述接收所述服务器发送的用户特征存储指令之后,所述方法还包括:
判断所述本地人脸特征库当前的剩余存储量是否大于或等于所述第二人脸特征的数据量;
若所述本地人脸特征库当前的剩余存储量大于或等于所述第二人脸特征的数据量,将所述第二人脸特征存储至所述本地人脸特征库;或,
若所述本地人脸特征库当前的剩余存储量小于所述第二人脸特征的数据量,根据第二预设条件,从所述本地人脸特征库中删除部分人脸特征,并将所述第二人脸特征存储至所述本地人脸特征库。
在一种可能的实施方式中,所述根据所述第一人脸特征,创建本地人脸特征库,包括:
确定所述第一用户所属的用户类型;
根据所述用户类型,对所述第一人脸特征进行聚类,获得多个分类组;
为所述分类组创建特征子库;
根据多个所述特征子库,构建所述本地人脸特征库。
这里,可以结合用户类型对第一用户的第一人脸特征进行聚类,并为分类组创建对应的特征子库,从而构建得到本地人脸特征库,这样,在后续进行特征比对的情况下,可以直接从相应的特征子库选取人脸特征进行比对,这将进一步提升比对效率。
在一种可能的实施方式中,所述将所述预存人脸特征与所述待识别人脸特征进行比对,确定比对结果,包括:
基于所述待支付用户所属的用户类型,确定与所述待识别人脸特征对应的特征子库;
确定所述待识别人脸特征与确定的所述特征子库中的至少一个预存人脸特征之间的相似度;
在所述特征子库中存在相似度大于预设阈值的合法用户的情况下,确定比对成功;在所述特征子库中不存在相似度大于预设阈值的合法用户的情况下,确定比对失败。
这里,首先可以基于待支付用户所属的用户类型确定进行比对的特征子库,而后基于特征之间的相似度实现特征比对,简单高效。
在一种可能的实施方式中,在所述特征子库中存在相似度大于预设阈值的合法用户为多个情况下;所述方法还包括:
获取多个所述合法用户的画像描述特征;
基于获取的所述画像描述特征对多个所述合法用户分别构建用户画像;
将多个所述合法用户分别对应的用户画像与所述待支付用户的用户画像进行比对,从多个所述合法用户中选取出用户画像匹配度最高的合法用户作为比对成功的合法用户。
这里,在针对待支付用户确定相似度比较高的用户有多个的情况下,可以结合用户画像构建进一步进行用户筛选,以确保比对结果的准确性。
在一种可能的实施方式中,所述方法还包括:
接收所述服务器发送的针对至少一个第三用户的特征删除指令;所述第三用户为支付行为数据满足第三预设条件的用户;所述支付行为数据包括支付频率和/或支付次数;
从所述本地人脸特征库中删除所述第三用户的人脸特征,得到更新后的本地人脸特征库。
这里,可以将支付频率比较低、支付次数比较少的第三用户的人脸特征从本地人脸特征库中删除,在确保比对速度的情况下,增大本地终端设备的存储空间。
在一种可能的实施方式中,所述方法还包括:
在所述比对结果指示比对成功的情况下,获取所述待支付用户的账户信息,以及所述待识别人脸图片对应的人脸框图;
所述将所述比对结果发送至服务器包括:
将所述比对结果、所述账户信息以及所述人脸框图发送至服务器;所述服务器用于基于所述比对结果和所述账户信息进行支付,以及用于基于所述人脸框图对支付结果进行核对。
这里,在本地终端设备比对成功的情况下,可以确定待支付用户的账户信息并连同比对结果一同发送至服务器以便于服务器直接基于账户信息进行扣款并完成支付过程,进一步提升支付效率。与此同时,还可以基于人脸框图对支付结果进行核对,确保支付操作的顺利进行。
在一种可能的实施方式中,所述方法还包括:
在所述比对结果指示比对失败的情况下,向所述服务器发送携带有所述待识别人脸图片的特征比对请求,其中,所述特征比对请求用于请求所述服务器基于所述待识别人脸图片进行特征比对,并在所述服务器比对成功的情况下触发所述服务器进行支付操作;
接收所述服务器在支付操作完成后返回的支付成功信息。
为了确保支付操作的顺利进行,在本地终端设备比对失败的情况下,可以直接将待识别人脸图片发送至服务器以使服务器先进行特征比对再进行支付,提升支付的服务质量。
第二方面,本公开实施例还提供了一种支付方法,应用于服务器,包括:
获取本地终端设备发送的比对结果;所述比对结果是所述本地终端设备将待识别人脸图片的待识别人脸特征与本地人脸特征库中至少一个合法用户的预存人脸特征进行比对得到的;所述合法用户包括在所述本地终端设备的行为满足第一预设条件的用户;
基于所述比对结果进行支付操作。
采用上述支付方法,可以基于本地终端设备发送的比对结果进行支付操作,这里的本地终端设备能够利用本地人脸特征库进行特征比对,这样服务器仅需基于比对结果实现支付操作即可,特别是在本地终端设备比较多,并具有多个支付需求的情况下,各本地终端设备可以自行进行特征比对,无需在服务器排队进行比对,这将显著提升支付的效率。
在一种可能的实施方式中,所述基于所述比对结果进行支付操作,包括:
在比对结果指示比对失败的情况下,接收所述本地终端设备发送的待识别人脸图片;
基于所述待识别人脸图片对待支付用户进行特征比对,得到新的比对结果;
基于新的比对结果进行支付操作。
在一种可能的实施方式中,所述方法还包括:
获取历史支付用户在所述本地终端设备产生的支付行为数据;所述支付行为数据包括支付频率和/或支付次数;
在所述支付行为数据满足第二预设条件的情况下,生成指向所述历史支付用户的用户特征存储指令;
发送所述用户特征存储指令至所述本地终端设备;所述用户特征存储指令用于指示所述本地终 端设备同步所述历史支付用户的信息。
在一种可能的实施方式中,所述方法还包括:
在所述支付行为数据满足第三预设条件的情况下,生成指向所述历史支付用户的特征删除指令;
发送所述特征删除指令至所述本地终端设备,所述特征删除指令用于指示所述本地终端设备删除所述历史支付用户的信息。
在一种可能的实施方式中,所述方法还包括:
接收所述本地终端设备发送的人脸框图;所述人脸框图是所述本地终端设备在比对结果指示比对成功的情况下,所述待识别人脸图片中对应指示待支付用户的人脸部分的图像;
响应支付核对指令,基于所述人脸框图对支付结果进行核对。
在一种可能的实施方式中,所述基于所述比对结果进行支付操作,包括:
在比对结果指示比对成功的情况下,基于所述比对结果从预存的至少一个用户的账户信息中查找与待支付用户匹配的账户信息;
基于查找到的所述待支付用户匹配的账户信息进行支付操作。
第三方面,本公开实施例还提供了一种支付装置,应用于本地终端设备,包括:
响应模块,用于响应支付请求,获取待支付用户的待识别人脸图片,并提取所述待识别人脸图片的待识别人脸特征;
读取模块,用于读取本地人脸特征库中至少一个合法用户的预存人脸特征;所述合法用户包括在所述本地终端设备的支付行为第一满足预设条件的用户;
比对模块,用于将所述预存人脸特征与所述待识别人脸特征进行比对,确定比对结果;
发送模块,用于将所述比对结果发送至服务器,其中,所述服务器用于根据所述比对结果进行支付。
第四方面,本公开实施例还提供了一种支付装置,应用于服务器,包括:
获取模块,用于获取本地终端设备发送的比对结果;所述比对结果是所述本地终端设备将待识别人脸图片的待识别人脸特征与本地人脸特征库中至少一个合法用户的预存人脸特征进行比对得到的;所述合法用户包括在所述本地终端设备的支付行为满足第一预设条件的用户;
支付模块,用于基于所述比对结果进行支付操作。
第五方面,本公开实施例还提供了一种支付系统,其特征在于,包括:如第一方面及其实施方式任一项所述的本地终端设备和如第二方面及其实施方式任一项所述的服务器。
第六方面,本公开实施例还提供了一种电子设备,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行如第一方面及其实施方式、第二方面及其实施方式任一所述的支付方法的步骤。
第七方面,本公开实施例还提供了一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行如第一方面及其各种实施方式、第二方面及其各种 实施方式任一所述的支付方法的步骤。
第八方面,本公开实施例还提供了一种计算机程序产品,包括计算机可读代码,或者承载有计算机可读代码的非易失性计算机可读存储介质,当所述计算机可读代码在电子设备的处理器中运行时,所述电子设备中的处理器执行如第一方面及其各种实施方式、第二方面及其各种实施方式任一所述的支付方法的步骤。
关于上述支付装置、电子设备、计算机可读存储介质及计算机程序产品的效果描述参见上述支付方法的说明,这里不再赘述。
为使本公开的上述目的、特征和优点能更明显易懂,下文特举实施例,并配合所附附图,作详细说明如下。
附图说明
为了更清楚地说明本公开实施例的技术方案,下面将对实施例中所需要使用的附图作简单地介绍,此处的附图被并入说明书中并构成本说明书中的一部分,这些附图示出了符合本公开的实施例,并与说明书一起用于说明本公开的技术方案。应当理解,以下附图仅示出了本公开的某些实施例,因此不应被看作是对范围的限定,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他相关的附图。
图1示出了本公开实施例所提供的一种支付方法的流程图;
图2示出了本公开实施例所提供的另一种支付方法的流程图;
图3示出了本公开实施例所提供的一种支付系统的示意图;
图4示出了本公开实施例所提供的一种支付装置的示意图;
图5示出了本公开实施例所提供的另一种支付装置的示意图;
图6示出了本公开实施例所提供的一种电子设备的示意图;
图7示出了本公开实施例所提供的另一种电子设备的示意图。
具体实施方式
为使本公开实施例的目的、技术方案和优点更加清楚,下面将结合本公开实施例中附图,对本公开实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本公开一部分实施例,而不是全部的实施例。通常在此处附图中描述和示出的本公开实施例的组件可以以各种不同的配置来布置和设计。因此,以下对在附图中提供的本公开的实施例的详细描述并非旨在限制要求保护的本公开的范围,而是仅仅表示本公开的选定实施例。基于本公开的实施例,本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例,都属于本公开保护的范围。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步定义和解释。
本文中术语“和/或”,仅仅是描述一种关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中术语“至少一种”表示多种中的任意一种或多种中的至少两种的任意组合,例如,包括A、B、C中的至少一种,可以表示包括从A、B和C构成的集合中选择的任意一个或多个元素。
经研究发现,在进行人脸支付的过程中,往往需要接入具有刷脸支付功能的支付设备,在这一支付设备中展示人脸以进行支付操作。由于支付本身的严谨性,需要经过比较复杂的验证,目前市面上的支付设备大都采用云端识别的方式,也就是在支付终端进行人脸采集,然后送至云端进行识别并支付。
然而,在支付终端比较多的情况下,上述方式会导致云端的识别压力比较大,将造成比较长的支付延迟,降低服务质量。
基于上述研究,本公开提供了一种支付方法、装置、电子设备及存储介质,以提升支付效率。
为便于对本实施例进行理解,首先对本公开实施例所公开的一种支付方法进行详细介绍,本公开实施例所提供的支付方法的执行主体一般为具有一定计算能力的计算机设备,该计算机设备例如包括:终端设备或其它处理设备,终端设备可以为用户设备(User Equipment,UE)、移动设备、用户终端、终端、蜂窝电话、无绳电话、个人数字助理(Personal Digital Assistant,PDA)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中,该支付方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。
参见图1所示,为本公开实施例提供的支付方法的流程图,方法包括步骤S101~S104,其中:
S101:响应支付请求,获取待支付用户的待识别人脸图片,并提取待识别人脸图片的待识别人脸特征;
S102:读取本地人脸特征库中至少一个合法用户的预存人脸特征;合法用户包括在本地终端设备的支付行为第一满足预设条件的用户;
S103:将预存人脸特征与待识别人脸特征进行比对,确定比对结果;
S104:将比对结果发送至服务器,其中,服务器用于根据比对结果进行支付。
这里,为了便于理解本公开实施例提供的支付方法,接下来首先对该支付方法的应用场景进行简单说明。上述支付方法主要可以应用于至少一种支付场景中,且主要可以是应用于人脸支付中,例如,可以应用于无人超市场景中。
在进行人脸支付的过程中,往往需要接入具有刷脸功能的终端设备。在终端设备进行人脸采集后,可以送到云端进行身份验证,并能够在身份验证通过后进行支付。然而,在支付设备比较多的情况下,上述方式会导致云端的识别压力比较大,将造成比较长的支付延迟,降低服务质量。
本公开实施例提供了一种支付方法、装置、电子设备及存储介质,以提升支付效率。
这里,可以基于获取的待识别人脸图片提取出待识别人脸特征,并能够读取本地人脸特征库中至少一个合法用户的预存人脸特征,这样,在将预存人脸特征与待识别人脸特征进行比对之后,可以将比对结果发送至服务器以使服务器基于比对结果完成支付过程。
其中,待识别人脸图片可以是利用本地终端设备上设置的摄像头采集的,也即,在具有支付请求的情况下,摄像头可以启动采集操作对待支付用户的人脸进行捕捉。不同的应用场景所对应的待支付用户也不同,在此不再赘述。
在本地终端设备捕捉到人脸的情况下,可以提取待识别人脸图片的待识别人脸特征,并将待识别人脸特征与本地人脸特征库中至少一个合法用户的预存人脸特征进行比对。这里,可以基于两个特征之间的相似度来确定待支付用户是否为合法用户,并能够在确定待支付用户为合法用户的情况 下,将这一比对结果通知给服务器以便于服务器完成后续的支付过程,还能够在确定待支付用户为非法用户的情况下,直接将待识别人脸图片发送给服务器以便于服务器再次进行身份比对,并能够在身份比对成功的情况下,完成后续的支付过程。
可知的是,本公开实施例提供的支付方法首选在本地终端设备侧完成身份比对,这样,即使本地终端设备比较多,也不会导致因为需要在服务器侧排队进行身份比对所带来的耗时问题,显著提升了后续的支付效率。
除此之外,本公开实施例还能够在本地终端设备比对失败的情况下,利用服务器再次进行身份比对,这主要是考虑到服务器往往具有更强的算力和更丰富的数据资源,从而可以提升比对成功率,确保支付的安全性。
这里的本地人脸特征库收集的可以是至少一个合法用户的预存人脸特征,合法用户则可以包括在本地终端设备的行为满足预设条件的用户。例如,可以是预先在本地终端设备进行注册的用户,还可以是经常在本地终端设备上进行支付的用户等,还可以是其它满足预设条件的用户,本公开实施例在此不做具体的限制。
本公开实施例提供的支付方法,在确定比对结果指示比对失败的情况下,可以将比对结果以及获取的待识别人脸图片发送至服务器。
在具体应用中,可以在本地终端设备比对失败的情况下,向服务器发送携带有待识别人脸图片的特征比对请求。服务器在接收到特征比对请求的情况下,可以基于待识别人脸图片进行比对成功的情况下,触发服务器完成支付过程。
需要说明的是,随着比对结果指示比对失败的信息的发送,不仅可以同时发送的是待识别人脸图片,还可以同时发送的是从待识别人脸图片中提取的人脸框图,该人脸框图对应待支付用户的人脸区域。
在同时发送待识别人脸图片的情况下,可以在服务器侧进行人脸框图提取,人脸特征提取,特征比对等一系列操作进而完成支付过程,在同时发送的是人脸框图的情况下,可以直接进行人脸特征提取,特征比对等一系列操作。
本公开实施例提供的支付方法,在确定比对结果指示比对失败的情况下,还可以在本地终端设备获取待支付用户的账户信息,并将比对结果以及账户信息发送至服务器。
这里的账户信息可以是与待支付用户的待扣款账户的相关信息,例如,可以是银行卡号信息,第三方支付平台的用户名信息等,这样,服务器通过本地终端设备发送的账户信息可以向相应的扣款平台发起扣款指令,并执行最终的扣款动作,完成支付过程。
在实际应用中,考虑到图像背景信息对人脸真伪性判断的关键作用,可以是直接将待识别人脸图片发送至服务器以使服务器完成一系列的身份比对以及支付操作,进一步确保支付的安全性。
除此之外,本公开实施例在比对结果指示比对成功的情况下,还可以从获取的待识别人脸图片中提取人脸框图,并将提取的人脸框图发送至服务器进行存档。这主要是考虑到在实际的业务场景中,支付操作涉及用户财产,一旦出现问题,往往需要及时的回溯出现支付问题的原因,而小图(即人脸框图)的存档,可以帮助支付结果的核对,且小图经由本地终端设备传输到服务器,也不会占用过大的网络带宽。
需要说明的是,在实际应用中,不仅可以利用人脸框图存档,也可以直接利用待识别人脸图片 进行存档。
本公开实施例中的本地人脸特征库包括的至少一个预存人脸特征,可以是相关用户在本地终端设备进行注册后确定的,也可以是服务器基于相关用户的支付行为确定的,接下来可以进一步进行说明。
本公开实施例提供的支付方法可以按照如下步骤构建本地人脸特征库:
步骤一、接收在本地终端设备上发起的第一用户的注册请求;
步骤二、响应注册请求,获取第一用户的多张第一人脸图片;
步骤三、将多张第一人脸图片输入至人脸质量检测模型,获得人脸质量检测结果;
步骤四、根据人脸质量检测结果,从多张第一人脸图片中,确定质量分数最高的目标人脸图片,并从目标人脸图片中提取第一人脸特征;
步骤五、根据第一人脸特征,创建本地人脸特征库,其中,预存人脸特征包括第一人脸特征。
这里,可以响应第一用户的注册请求,获取第一人脸图片,在从第一人脸图片中提取出人脸特征的情况下,可以将第一人脸特征存储在本地人脸特征库。
在具体应用中,本地终端设备可以支持用户录入,例如,可以通过摄像头采集录入人脸图片。通常情况下,针对一个用户可以录入多张人脸图片。为了进一步提升后续进行特征比对的准确性,这里,可以基于预先训练好的人脸质量检测模型对第一用户对应的多张第一人脸图片进行人脸质量打分,这里,可以选取质量分数最高的一张人脸图片。
其中,上述人脸质量检测模型用于基于人脸图片的清晰度、完整度、曝光度等分析来确定与图片质量相关的特征,并基于这些特征确定图片质量得分。
在本地终端设备录入相关信息的用户默认会经常在该设备支付,成功录入人脸图片并选取出目标人脸图片的情况下,即可以将这一人脸图片的第一人脸特征加入本地人脸特征库。
与此同时,本公开实施例还支持录入其它信息,例如,通过键盘录入人员账户信息等。这里,可以将人脸图片、人脸特征以及对应的账户信息同步至服务器,以保持服务器与本地终端设备的同步,便于服务器进行多设备管理。
在实际应用中,为了进一步确保本地人脸特征库中所存储的人脸特征对应用户的合法性,在接收注册请求之后,可以利用身份标识信息对第一用户进行注册权限的验证,具体可以通过如下步骤来实现:
步骤一、获取第一用户的身份标识信息;
步骤二、基于身份标识信息,判断第一用户是否具备在本地终端设备上进行注册的权限;
步骤三、若第一用户具备在本地终端设备上进行注册的权限,确定第一用户为合法用户,并响应注册请求,获取第一用户的多张第一人脸图片。
这里,可以基于身份标识信息验证第一用户是否具备注册权限。在进行注册权限验证之前,可以预先为本地终端设备绑定具备注册权限的用户标识,这里的用户可以是本地终端设备的拥有者,也可以是本地终端设备的管理者,还可以其它具有注册权限的用户。
本公开实施例中,还可以基于用户的常住地与本地终端设备所属的地理位置之间的一致性来确定是否进行人脸特征入库操作,也即,若第一用户的常住地与本地终端设备所属的地理位置一致,一定程度上说明在本地终端设备上进行人脸特征录入的合理性,例如,对于小区便利店设置的本地终端设备而言,第一用户可以是小区住户。进而,可以根据第一人脸特征,创建本地人脸特征库,从而进一步确保了后续进行人脸核对的安全性。
本公开实施例中,可以按照如下步骤更新本地人脸特征库:
步骤一、接收服务器发送的用户特征存储指令;用户特征存储指令中包括至少一个第二用户的第二人脸特征,第二用户为在本地终端设备上的支付行为数据满足第二预设条件的用户;支付行为数据包括支付频率和/或支付次数;
步骤二、将第二人脸特征存储至本地人脸特征库。
这里的第一预设条件可以是支付频率高于预设频率、支付次数大于预设次数这一条件。也即,本公开可以是在服务器确定某些用户(即第二用户)经常在本地终端设备进行支付的情况下,自动把这些用户的人脸特征同步至该终端设备的本地人脸特征库,以提升比对速度。
在实际应用中,还需要评估本地人脸特征库当前的剩余存储量是否大于或等于待存储的第二人脸特征的数据量,若本地人脸特征库当前的剩余存储量大于或等于第二人脸特征的数据量,将第二人脸特征存储至本地人脸特征库;若本地人脸特征库当前的剩余存储量小于第二人脸特征的数据量,根据第二预设条件,从本地人脸特征库中删除部分人脸特征,并将第二人脸特征存储至本地人脸特征库。这里,可以删除支付频率比较低、支付次数比较少的用户的人脸特征。
本公开实施例中,还可以按照如下步骤更新本地人脸特征库:
步骤一、接收服务器发送的针对至少一个第三用户的特征删除指令;第三用户为支付行为数据满足第三预设条件的用户;支付行为数据包括支付频率和/或支付次数;
步骤二、从本地人脸特征库中删除第三用户的人脸特征,得到更新后的本地人脸特征库。
这里的第三预设条件可以是支付频率低于或等于预设频率、支付次数小于或等于预设次数这一条件,除此之外,还可以是距离当前时间的支付时长超过预设时长这一条件。也即,本公开可以是在服务器确定某些用户(即第三用户)长期不在该本地终端设备进行支付,并且该用户在本地人脸特征库的情况,从本地人脸特征库中删除该用户的人脸特征,以在本地维持一个相对固定的数据规模,确保本地终端设备的存储空间足够使用。
需要说明的是,在实际应用中,可以在服务器侧保留第三用户的信息,以便在有需要进行信息同步的情况下,及时的进行信息同步。
为了进一步提升人脸比对的效率,本公开实施例提供的支付方法可以基于人脸特征聚类建立特征子库,进而基于特征子库的特征比对实现快速的人脸比对。
其中,上述建库方案具体可以通过如下步骤来实现:
步骤一、确定第一用户所属的用户类型;
步骤二、根据用户类型,对第一人脸特征进行聚类,获得多个分类组;
步骤三、为分类组创建特征子库;
步骤四、根据多个特征子库,构建本地人脸特征库。
这里,可以基于用户类型,进行人脸特征比对,进而基于分类组对应的特征子库创建本地人脸特征库。
其中,上述用户类型可以是基于不同的应用场景来确定的。以无人超市这一场景为例,这里的用户类型可以是学生、家长、老人等类型,针对不同的学生类型,所对应的第一人脸特征也不相同,进而可以入库到不同的本地人脸特征库。
另外,在进行人脸特征聚类的过程中,还可以结合用户的偏好等信息进行聚类,这里可以采用K-means等聚类方法实现聚类,这里不做赘述。
基于构建有不同特征子库的本地人脸特征库而言,这里可以按照如下方法进行特征比对:
步骤一、基于待支付用户所属的用户类型,确定与待识别人脸特征对应的特征子库;
步骤二、确定待识别人脸特征与确定的特征子库中的至少一个预存人脸特征之间的相似度;
步骤三、在特征子库中存在相似度大于预设阈值的合法用户的情况下,确定比对成功;在特征子库中不存在相似度大于预设阈值的合法用户的情况下,确定比对失败。
这里,可以可基于用户类型锁定与待支付用户对应的特征子库,进而确定特征子库中的至少一个预存人脸特征与待识别人脸图片的待识别人脸特征之间的相似度,相似度越高,说明比中的可能性也越高,反之,相似度越低,说明比中的可能性也越低。这里,可以在在特征子库中存在相似度大于预设阈值的合法用户的情况下,确定比对成功,以完成身份比对,还可以在特征子库中不存在相似度大于预设阈值的合法用户的情况下,确定比对失败,并向服务器发起再次进行比对的请求以完成后续的支付过程。
这里的特征相似度可以是基于余弦公式来确定的。
在实际应用中,若从特征子库中查找到多个相似度比较高的预存人脸特征,为了便于进行后续的支付操作,这里可以结合用户画像进一步进行用户筛选以确定最终的比对人,具体可以按照如下步骤实现:
步骤一、获取多个合法用户的画像描述特征;
步骤二、基于获取的画像描述特征对多个合法用户分别构建用户画像;
步骤三、将多个合法用户分别对应的用户画像与待支付用户的用户画像进行比对,从多个合法用户中选取出用户画像匹配度最高的合法用户作为比对成功的合法用户。
这里的画像描述特征可以从更多特征维度描述至少一个用户,通过更全维度的描述使得特征比对结果更为针对性,提升了比对准确性。
接下来以无人超市场景为例,对本地人脸特征库的维护过程进行说明。
对于一个坐落在某小区的无人超市而言,预先可以在超市内设置的本地终端设备上录入该小区内至少一个业主的人脸图片以及相关个人信息,这些业主可以作为本地终端设备的常驻会员。在一定时间内,若入住了新的业主,可以将新的业主的信息录入本地终端设备,也可以在服务器确定新的业主具有频繁支付行为的情况下,自动同步人脸特征到本地终端设备以便新的业主可以快速完成本地身份比对。若有业主搬出了该小区,这里,可以在本地终端设备删除这一业主的信息,也可以 在服务器确定这一业主长期不具有支付行为的情况下,向本地终端设备发起删除这一业主的信息的指令以便充分利用本地终端设备的存储空间。
参见图2所示,为本公开实施例提供的支付方法的流程图,该支付方法的执行主体可以是服务器,在具体应用中,可以是云端服务器。上述方法包括步骤S201~S202,其中:
S201:获取本地终端设备发送的比对结果;比对结果是本地终端设备将待识别人脸图片的待识别人脸特征与本地人脸特征库中至少一个合法用户的预存人脸特征进行比对得到的;合法用户包括在本地终端设备的支付行为满足第一预设条件的用户;
S202:基于比对结果进行支付操作。
这里的服务器可以基于本地终端设备发送的比对结果进行支付操作。上述比对结果可以是本地终端设备将待识别人脸图片的待识别人脸特征与本地人脸特征库中至少一个合法用户的预存人脸特征进行比对得到的。
有关待识别人脸特征与本地人脸特征库中的预存人脸特征之间的比对过程可以参照上述描述内容,在此不再赘述。有关合法用户的具体说明也可以参见上述描述,在此也不再赘述。
本公开实施例中,在确定本地终端设备身份比对失败的情况下,可以在服务器侧重新进行身份比对,并进行后续支付操作,具体可以通过如下步骤来实现:
步骤一、在比对结果指示比对失败的情况下,接收本地终端设备发送的待识别人脸图片;
步骤二、基于待识别人脸图片对待支付用户进行特征比对,得到新的比对结果;
步骤三、基于新的比对结果进行支付操作。
这里,有关服务器侧进行身份比对的过程可以是基于人脸库确定的,这里的人脸库可以包含有至少一种已授权用户的人脸图片以及对应的个人信息,一定程度上比本地终端设备中的本地人脸特征库的用户覆盖面更广。具体的特征比对方式类似,在此不做赘述。
本公开实施例中,在确定本地终端设备身份比对成功的情况下,本地终端设备可以连同比对结果以及账户信息一起发送至服务器以进行支付,也可以仅发送比对结果至服务器,这样,这样服务器则可以基于比对结果从预存的至少一个用户的账户信息中查找与待支付用户匹配的账户信息,基于查找到的待支付用户匹配的账户信息进行支付操作,可以按照如下步骤进行支付操作:
步骤一、判断待支付用户的账户信息指向的账户余额是否满足预设支付额,得到判断结果;
步骤二、基于判断结果进行支付操作。
这里,在确定待支付用户身份合法的情况下,可以向待支付用户绑定的账户发起扣款申请,这样,在确定待支付用户的账户余额大于支付额的情况下,基于之前的身份合法验证可以直接对待支付用户绑定的账户扣除相应的支付额,以成功完成支付。
在确定待支付用户的账户余额小于支付额的情况下,可以生成支付失败信息以提醒收款方需要待支付用户再次支付。除此之外,基于之前的身份合法验证还可以直接扣除待支付用户绑定的账户中的全部余额,并提醒还有部分余额未支付。
除此之外,本公开实施例在确定本地终端设备身份比对成功的情况下,还可以进行小图存档实现支付结果进行核对。也即,这里可以支付核对指令,基于从待识别人脸图片中提取的人脸框图对 支付结果进行核对。有关具体的核对方法在此不再赘述,具体可以参见上述描述内容。
为了更好的服务于本地终端设备,本公开实施例中的服务器与本地终端设备之间存在信息添加和信息删除的需求,接下来可以通过如下两个方面进一步进行说明。
第一方面:本公开实施例可以按照如下步骤进行信息添加:
步骤一、获取历史支付用户在本地终端设备产生的支付行为数据;支付行为数据包括支付频率和/或支付次数;
步骤二、在支付行为数据满足第二预设条件的情况下,生成指向历史支付用户的用户特征存储指令;
步骤三、发送用户特征存储指令至本地终端设备,用户特征存储指令用于指示本地终端设备同步历史支付用户的信息。
这里的第二预设条件可以是支付频率高于预设频率、支付次数大于预设次数这一条件。也即,本公开可以是在服务器确定某些用户经常在本地终端设备进行支付的情况下,自动把这些用户的信息(例如人脸图片或者个人信息等)同步至该终端设备,以提升比对速度。
第二方面:本公开实施例可以按照如下步骤进行信息删除:
步骤一、在支付行为数据满足第三预设条件的情况下,生成指向历史支付用户的特征删除指令;
步骤二、发送特征删除指令至本地终端设备,特征删除指令用于指示本地终端设备删除历史支付用户的信息。
这里的第三预设条件可以是支付频率低于或等于预设频率、支付次数小于或等于预设次数这一条件,除此之外,还可以是距离当前时间的支付时长超过预设时长这一条件。也即,本公开可以是在服务器确定某些用户长期不在该本地终端设备进行支付,并且该用户在本地终端设备的情况,从本地终端设备中删除该用户的信息,以在本地维持一个相对固定的数据规模,确保本地终端设备的存储空间足够使用。
本领域技术人员可以理解,在具体实施方式的上述方法中,各步骤的撰写顺序并不意味着严格的执行顺序而对实施过程构成任何限定,各步骤的具体执行顺序应当以其功能和可能的内在逻辑确定。
基于上述实施例提供的本地终端设备和服务器的支付方法,本公开实施例还提供了一种支付系统,如图3所示,该支付系统通过本地终端设备与服务器之间的通信连接,实现了本地终端设备的特征比对,以及服务器侧的支付,有关本地终端设备和服务器的具体实现过程参见上述描述内容,在此不再赘述。
基于同一发明构思,本公开实施例中还提供了与支付方法对应的支付装置,由于本公开实施例中的装置解决问题的原理与本公开实施例上述支付方法相似,因此装置的实施可以参见方法的实施,重复之处不再赘述。
参照图4所示,为本公开实施例提供的一种支付装置的示意图,装置包括:响应模块401、读取模块402、比对模块403和发送模块404;其中,
响应模块401,用于响应支付请求,获取待支付用户的待识别人脸图片,并提取待识别人脸图片的待识别人脸特征;
读取模块402,用于读取本地人脸特征库中至少一个合法用户的预存人脸特征;合法用户包括在本地终端设备的支付行为第一满足预设条件的用户;
比对模块403,用于将预存人脸特征与待识别人脸特征进行比对,确定比对结果;
发送模块404,用于将比对结果发送至服务器,其中,服务器用于根据比对结果进行支付。
采用上述支付装置,在响应支付请求的情况下,可以基于获取的待支付用户的待识别人脸图片提取出待识别人脸特征,这样,在读取到本地人脸特征库中至少一个合法用户的预存人脸特征的情况下,可以将待识别人脸特征与至少一个预存人脸特征进行比对,并将比对结果发送至服务器以使服务器基于比对结果完成支付过程。本公开中的本地终端设备能够利用本地人脸特征库进行特征比对,这样服务器仅需基于比对结果实现支付操作即可,特别是在本地终端设备比较多,并具有多个支付需求的情况下,各本地终端设备可以自行进行特征比对,无需在服务器排队进行比对,这将显著提升支付的效率。
在一种可能的实施方式中,上述读取模块402,还用于:
响应支付请求,获取待支付用户的待识别人脸图片之前,接收在本地终端设备上发起的第一用户的注册请求;
响应注册请求,获取第一用户的多张第一人脸图片;
将多张第一人脸图片输入至人脸质量检测模型,获得人脸质量检测结果;
根据人脸质量检测结果,从多张第一人脸图片中,确定质量分数最高的目标人脸图片,并从目标人脸图片中提取第一人脸特征;
根据第一人脸特征,创建本地人脸特征库,其中,预存人脸特征包括第一人脸特征。
在一种可能的实施方式中,上述读取模块402,还用于:
接收在本地终端设备上发起的第一用户的注册请求之后,获取第一用户的身份标识信息;
基于身份标识信息,判断第一用户是否具备在本地终端设备上进行注册的权限;
若第一用户具备在本地终端设备上进行注册的权限,确定第一用户为合法用户,并响应注册请求,获取第一用户的多张第一人脸图片;
从目标人脸图片中提取第一人脸特征之后,判断第一用户的常住地与本地终端设备所属的地理位置是否一致;
若第一用户的常住地与本地终端设备所属的地理位置一致,根据第一人脸特征,创建本地人脸特征库。
在一种可能的实施方式中,上述读取模块402,还用于:
接收服务器发送的用户特征存储指令;用户特征存储指令中包括至少一个第二用户的第二人脸特征,第二用户为在本地终端设备上的支付行为数据满足第二预设条件的用户;支付行为数据包括支付频率和/或支付次数;
将第二人脸特征存储至本地人脸特征库。
在一种可能的实施方式中,上述读取模块402,还用于:
接收服务器发送的用户特征存储指令之后,判断本地人脸特征库当前的剩余存储量是否大于或等于第二人脸特征的数据量;
若本地人脸特征库当前的剩余存储量大于或等于第二人脸特征的数据量,将第二人脸特征存储至本地人脸特征库;或,
若本地人脸特征库当前的剩余存储量小于第二人脸特征的数据量,根据第二预设条件,从本地人脸特征库中删除部分人脸特征,并将第二人脸特征存储至本地人脸特征库。
在一种可能的实施方式中,上述读取模块402用于按照以下步骤根据第一人脸特征,创建本地人脸特征库:
确定第一用户所属的用户类型;
根据用户类型,对第一人脸特征进行聚类,获得多个分类组;
为分类组创建特征子库;
根据多个特征子库,构建本地人脸特征库。
在一种可能的实施方式中,上述比对模块403用于按照以下步骤将预存人脸特征与待识别人脸特征进行比对,确定比对结果:
基于待支付用户所属的用户类型,确定与待识别人脸特征对应的特征子库;
确定待识别人脸特征与确定的特征子库中的至少一个预存人脸特征之间的相似度;
在特征子库中存在相似度大于预设阈值的合法用户的情况下,确定比对成功;在特征子库中不存在相似度大于预设阈值的合法用户的情况下,确定比对失败。
在一种可能的实施方式中,在特征子库中存在相似度大于预设阈值的合法用户为多个情况下;上述比对模块403,还用于:
获取多个合法用户的画像描述特征;
基于获取的画像描述特征对多个合法用户分别构建用户画像;
将多个合法用户分别对应的用户画像与待支付用户的用户画像进行比对,从多个合法用户中选取出用户画像匹配度最高的合法用户作为比对成功的合法用户。
在一种可能的实施方式中,上述读取模块402,还用于:
接收服务器发送的针对至少一个第三用户的特征删除指令;第三用户为支付行为数据满足第三预设条件的用户;支付行为数据包括支付频率和/或支付次数;
从本地人脸特征库中删除第三用户的人脸特征,得到更新后的本地人脸特征库。
在一种可能的实施方式中,上述发送模块404,还用于:
在比对结果指示比对成功的情况下,获取待支付用户的账户信息,以及待识别人脸图片对应的人脸框图;
将比对结果、账户信息以及人脸框图发送至服务器;服务器用于基于比对结果和账户信息进行支付,以及用于基于人脸框图对支付结果进行核对。
在一种可能的实施方式中,上述发送模块404,还用于:
在比对结果指示比对失败的情况下,向服务器发送携带有待识别人脸图片的特征比对请求,其中,特征比对请求用于请求服务器基于待识别人脸图片进行特征比对,并在服务器比对成功的情况下触发服务器进行支付操作;
接收服务器在支付操作完成后返回的支付成功信息。
参照图5所示,为本公开实施例提供的另一种支付装置的示意图,装置包括:获取模块501、支付模块502;其中,
获取模块501,用于获取本地终端设备发送的比对结果;比对结果是本地终端设备将待识别人脸图片的待识别人脸特征与本地人脸特征库中至少一个合法用户的预存人脸特征进行比对得到的;合法用户包括在本地终端设备的支付行为满足第一预设条件的用户;
支付模块502,用于基于比对结果进行支付操作。
采用上述支付装置,可以基于本地终端设备发送的比对结果进行支付操作,这里的本地终端设备能够利用本地人脸特征库进行特征比对,这样服务器仅需基于比对结果实现支付操作即可,特别是在本地终端设备比较多,并具有多个支付需求的情况下,各本地终端设备可以自行进行特征比对,无需在服务器排队进行比对,这将显著提升支付的效率。
在一种可能的实施方式中,支付模块502,用于按照以下步骤基于比对结果进行支付操作:
在比对结果指示比对失败的情况下,接收本地终端设备发送的待识别人脸图片;
基于待识别人脸图片对待支付用户进行特征比对,得到新的比对结果;
基于新的比对结果进行支付操作。
在一种可能的实施方式中,上述装置还包括:
同步模块503,用于获取历史支付用户在本地终端设备产生的支付行为数据;支付行为数据包括支付频率和/或支付次数;在支付行为数据满足第二预设条件的情况下,生成指向历史支付用户的用户特征存储指令;发送用户特征存储指令至本地终端设备,用户特征存储指令用于指示本地终端设备同步历史支付用户的信息。
在一种可能的实施方式中,上述装置还包括:
删除模块504,用于在支付行为数据满足第三预设条件的情况下,生成指向历史支付用户的特征删除指令;发送特征删除指令至本地终端设备,特征删除指令用于指示本地终端设备删除历史支付用户的信息。
在一种可能的实施方式中,获取模块501,还用于:
接收本地终端设备发送的人脸框图;人脸框图是本地终端设备在比对结果指示比对成功的情况下,待识别人脸图片中对应指示待支付用户的人脸部分的图像;
响应支付核对指令,基于人脸框图对支付结果进行核对。
在一种可能的实施方式中,支付模块502,用于按照以下步骤基于比对结果进行支付操作:
在比对结果指示比对成功的情况下,基于比对结果从预存的至少一个用户的账户信息中查找与 待支付用户匹配的账户信息;
基于查找到的待支付用户匹配的账户信息进行支付操作。
关于装置中的各模块的处理流程、以及各模块之间的交互流程的描述可以参照上述方法实施例中的相关说明,这里不再详述。
本公开实施例还提供了一种电子设备,如图6所示,为本公开实施例提供的电子设备结构示意图,包括:处理器601、存储器602、和总线603。存储器602存储有处理器601可执行的机器可读指令(比如,图4中的装置中响应模块401、读取模块402、比对模块403、发送模块404对应的执行指令等),当电子设备运行时,处理器601与存储器602之间通过总线603通信,机器可读指令被处理器601执行时执行如下处理:
响应支付请求,获取待支付用户的待识别人脸图片,并提取待识别人脸图片的待识别人脸特征;
读取本地人脸特征库中至少一个合法用户的预存人脸特征;合法用户包括在本地终端设备的支付行为满足第一预设条件的用户;
将预存人脸特征与待识别人脸特征进行比对,确定比对结果;
将比对结果发送至服务器,其中,服务器用于根据比对结果进行支付。
本公开实施例还提供了一种电子设备,如图7所示,为本公开实施例提供的电子设备结构示意图,包括:处理器701、存储器702、和总线703。存储器702存储有处理器701可执行的机器可读指令(比如,图5中的装置中获取模块501、支付模块502对应的执行指令等),当电子设备运行时,处理器701与存储器702之间通过总线703通信,机器可读指令被处理器701执行时执行如下处理:
获取本地终端设备发送的比对结果;比对结果是本地终端设备将待识别人脸图片的待识别人脸特征与本地人脸特征库中至少一个合法用户的预存人脸特征进行比对得到的;合法用户包括在本地终端设备的支付行为满足第一预设条件的用户;
基于比对结果进行支付操作。
本公开实施例还提供一种计算机可读存储介质,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行上述方法实施例中所述的支付方法的步骤。其中,该存储介质可以是易失性或非易失的计算机可读取存储介质。
本公开实施例还提供一种计算机程序产品,该计算机程序产品承载有程序代码,所述程序代码包括的指令可用于执行上述方法实施例中所述的支付方法的步骤,具体可参见上述方法实施例,在此不再赘述。
其中,上述计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中,所述计算机程序产品具体体现为计算机存储介质,在另一个可选实施例中,计算机程序产品具体体现为软件产品,例如软件开发包(Software Development Kit,SDK)等等。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统和装置的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。在本公开所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,又例如,多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略, 或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些通信接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本公开各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个处理器可执行的非易失的计算机可读取存储介质中。基于这样的理解,本公开的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本公开各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是:以上所述实施例,仅为本公开的具体实施方式,用以说明本公开的技术方案,而非对其限制,本公开的保护范围并不局限于此,尽管参照前述实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:任何熟悉本技术领域的技术人员在本公开揭露的技术范围内,其依然可以对前述实施例所记载的技术方案进行修改或可轻易想到变化,或者对其中部分技术特征进行等同替换;而这些修改、变化或者替换,并不使相应技术方案的本质脱离本公开实施例技术方案的精神和范围,都应涵盖在本公开的保护范围之内。因此,本公开的保护范围应所述以权利要求的保护范围为准。

Claims (18)

  1. 一种支付方法,其特征在于,应用于本地终端设备,包括:
    响应支付请求,获取待支付用户的待识别人脸图片,并提取所述待识别人脸图片的待识别人脸特征;
    读取本地人脸特征库中至少一个合法用户的预存人脸特征;所述合法用户包括在所述本地终端设备的支付行为满足第一预设条件的用户;
    将所述预存人脸特征与所述待识别人脸特征进行比对,确定比对结果;
    将所述比对结果发送至服务器,其中,所述服务器用于根据所述比对结果进行支付。
  2. 根据权利要求1所述的支付方法,其特征在于,所述响应支付请求,获取待支付用户的待识别人脸图片之前,所述方法还包括:
    接收在所述本地终端设备上发起的第一用户的注册请求;
    响应所述注册请求,获取所述第一用户的多张第一人脸图片;
    将所述多张第一人脸图片输入至人脸质量检测模型,获得人脸质量检测结果;
    根据所述人脸质量检测结果,从所述多张第一人脸图片中,确定质量分数最高的目标人脸图片,并从所述目标人脸图片中提取第一人脸特征;
    根据所述第一人脸特征,创建本地人脸特征库,其中,所述预存人脸特征包括所述第一人脸特征。
  3. 根据权利要求2所述的支付方法,其特征在于,所述接收在所述本地终端设备上发起的第一用户的注册请求之后,所述方法还包括:
    获取所述第一用户的身份标识信息;
    基于所述身份标识信息,判断所述第一用户是否具备在所述本地终端设备上进行注册的权限;
    若所述第一用户具备在所述本地终端设备上进行注册的权限,确定所述第一用户为合法用户,并响应所述注册请求,获取所述第一用户的多张第一人脸图片;
    所述从所述目标人脸图片中提取第一人脸特征之后,所述方法还包括:
    判断所述第一用户的常住地与所述本地终端设备所属的地理位置是否一致;
    若所述第一用户的常住地与所述本地终端设备所属的地理位置一致,根据所述第一人脸特征,创建本地人脸特征库。
  4. 根据权利要求2或3所述的支付方法,其特征在于,所述方法还包括:
    接收所述服务器发送的用户特征存储指令;所述用户特征存储指令中包括至少一个第二用户的第二人脸特征,所述第二用户为在所述本地终端设备上的支付行为数据满足第二预设条件的用户;所述支付行为数据包括支付频率和/或支付次数;
    将所述第二人脸特征存储至所述本地人脸特征库。
  5. 根据权利要求4所述的支付方法,其特征在于,所述接收所述服务器发送的用户特征存储指 令之后,所述方法还包括:
    判断所述本地人脸特征库当前的剩余存储量是否大于或等于所述第二人脸特征的数据量;
    若所述本地人脸特征库当前的剩余存储量大于或等于所述第二人脸特征的数据量,将所述第二人脸特征存储至所述本地人脸特征库;或,
    若所述本地人脸特征库当前的剩余存储量小于所述第二人脸特征的数据量,根据第二预设条件,从所述本地人脸特征库中删除部分人脸特征,并将所述第二人脸特征存储至所述本地人脸特征库。
  6. 根据权利要求2-5任一所述的支付方法,其特征在于,所述根据所述第一人脸特征,创建本地人脸特征库,包括:
    确定所述第一用户所属的用户类型;
    根据所述用户类型,对所述第一人脸特征进行聚类,获得多个分类组;
    为所述分类组创建特征子库;
    根据多个所述特征子库,构建所述本地人脸特征库。
  7. 根据权利要求6所述的支付方法,其特征在于,所述将所述预存人脸特征与所述待识别人脸特征进行比对,确定比对结果,包括:
    基于所述待支付用户所属的用户类型,确定与所述待识别人脸特征对应的特征子库;
    确定所述待识别人脸特征与确定的所述特征子库中的至少一个预存人脸特征之间的相似度;
    在所述特征子库中存在相似度大于预设阈值的合法用户的情况下,确定比对成功;在所述特征子库中不存在相似度大于预设阈值的合法用户的情况下,确定比对失败。
  8. 根据权利要求7所述的支付方法,其特征在于,在所述特征子库中存在相似度大于预设阈值的合法用户为多个情况下;所述方法还包括:
    获取多个所述合法用户的画像描述特征;
    基于获取的所述画像描述特征对多个所述合法用户分别构建用户画像;
    将多个所述合法用户分别对应的用户画像与所述待支付用户的用户画像进行比对,从多个所述合法用户中选取出用户画像匹配度最高的合法用户作为比对成功的合法用户。
  9. 根据权利要求2-8任一所述的支付方法,其特征在于,所述方法还包括:
    接收所述服务器发送的针对至少一个第三用户的特征删除指令;所述第三用户为支付行为数据满足第三预设条件的用户;所述支付行为数据包括支付频率和/或支付次数;
    从所述本地人脸特征库中删除所述第三用户的人脸特征,得到更新后的本地人脸特征库。
  10. 根据权利要求1-9任一所述的支付方法,其特征在于,所述方法还包括:
    在所述比对结果指示比对成功的情况下,获取所述待支付用户的账户信息以及所述待识别人脸图片对应的人脸框图;
    所述将所述比对结果发送至服务器包括:
    将所述比对结果、所述账户信息以及所述人脸框图发送至服务器;所述服务器用于基于所述比 对结果和所述账户信息进行支付,以及用于基于所述人脸框图对支付结果进行核对。
  11. 根据权利要求1-10任一所述的支付方法,其特征在于,所述方法还包括:
    在所述比对结果指示比对失败的情况下,向所述服务器发送携带有所述待识别人脸图片的特征比对请求,其中,所述特征比对请求用于请求所述服务器基于所述待识别人脸图片进行特征比对,并在所述服务器比对成功的情况下触发所述服务器进行支付操作;
    接收所述服务器在支付操作完成后返回的支付成功信息。
  12. 一种支付方法,其特征在于,应用于服务器,包括:
    获取本地终端设备发送的比对结果;所述比对结果是所述本地终端设备将待识别人脸图片的待识别人脸特征与本地人脸特征库中至少一个合法用户的预存人脸特征进行比对得到的;所述合法用户包括在所述本地终端设备的支付行为满足第一预设条件的用户;
    基于所述比对结果进行支付操作。
  13. 根据权利要求12所述的支付方法,其特征在于,所述基于所述比对结果进行支付操作,包括:
    在比对结果指示比对失败的情况下,接收所述本地终端设备发送的待识别人脸图片;
    基于所述待识别人脸图片对待支付用户进行特征比对,得到新的比对结果;
    基于新的比对结果进行支付操作。
  14. 根据权利要求12或13所述的支付方法,其特征在于,所述方法还包括:
    获取历史支付用户在所述本地终端设备产生的支付行为数据;所述支付行为数据包括支付频率和/或支付次数;
    在所述支付行为数据满足第二预设条件的情况下,生成指向所述历史支付用户的用户特征存储指令;
    发送所述用户特征存储指令至所述本地终端设备;所述用户特征存储指令用于指示所述本地终端设备同步所述历史支付用户的信息。
  15. 一种支付系统,其特征在于,包括:如权利要求1-11任一项所述的本地终端设备和如权利要求12-14任一项所述的服务器。
  16. 一种电子设备,其特征在于,包括:处理器、存储器和总线,所述存储器存储有所述处理器可执行的机器可读指令,当电子设备运行时,所述处理器与所述存储器之间通过总线通信,所述机器可读指令被所述处理器执行时执行如权利要求1至14任一所述的支付方法。
  17. 一种计算机可读存储介质,其特征在于,该计算机可读存储介质上存储有计算机程序,该计算机程序被处理器运行时执行如权利要求1至14任一所述的支付方法。
  18. 一种计算机程序产品,包括计算机可读代码,或者承载有计算机可读代码的非易失性计算机可读存储介质,当所述计算机可读代码在电子设备的处理器中运行时,所述电子设备中的处理器执行用于实现权利要求1-14中的任一权利要求所述的方法。
PCT/CN2021/126183 2021-06-30 2021-10-25 支付方法、系统、电子设备及存储介质 WO2023273042A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110736082.6 2021-06-30
CN202110736082.6A CN113409055A (zh) 2021-06-30 2021-06-30 支付方法、系统、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023273042A1 true WO2023273042A1 (zh) 2023-01-05

Family

ID=77680484

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/126183 WO2023273042A1 (zh) 2021-06-30 2021-10-25 支付方法、系统、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN113409055A (zh)
WO (1) WO2023273042A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113409055A (zh) * 2021-06-30 2021-09-17 深圳市商汤科技有限公司 支付方法、系统、电子设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106487511A (zh) * 2015-08-27 2017-03-08 阿里巴巴集团控股有限公司 身份认证方法及装置
CN107194699A (zh) * 2017-06-05 2017-09-22 崔俊新 基于生物特征的支付系统、方法、装置及可读存储介质
US20180174149A1 (en) * 2016-12-16 2018-06-21 Mastercard International Incorporated Systems and Methods for Use in Authenticating Consumers in Connection With Payment Account Transactions
CN108595927A (zh) * 2018-04-04 2018-09-28 北京市商汤科技开发有限公司 身份认证、解锁及支付方法、装置、存储介质、产品和设备
CN110096996A (zh) * 2019-04-28 2019-08-06 深圳前海达闼云端智能科技有限公司 生物信息识别方法、装置、终端、系统及存储介质
CN110443014A (zh) * 2019-07-31 2019-11-12 成都商汤科技有限公司 身份验证方法、用于身份验证的电子设备和服务器、系统
CN113409055A (zh) * 2021-06-30 2021-09-17 深圳市商汤科技有限公司 支付方法、系统、电子设备及存储介质

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105930765A (zh) * 2016-02-29 2016-09-07 中国银联股份有限公司 一种支付方法及装置
CN109815775A (zh) * 2017-11-22 2019-05-28 深圳市祈飞科技有限公司 一种基于人脸属性的人脸识别方法及系统
CN110458154B (zh) * 2019-09-12 2021-08-31 腾讯科技(深圳)有限公司 人脸识别方法、装置和计算机可读存储介质
CN111275448A (zh) * 2020-02-22 2020-06-12 腾讯科技(深圳)有限公司 人脸数据处理方法、装置和计算机设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106487511A (zh) * 2015-08-27 2017-03-08 阿里巴巴集团控股有限公司 身份认证方法及装置
US20180174149A1 (en) * 2016-12-16 2018-06-21 Mastercard International Incorporated Systems and Methods for Use in Authenticating Consumers in Connection With Payment Account Transactions
CN107194699A (zh) * 2017-06-05 2017-09-22 崔俊新 基于生物特征的支付系统、方法、装置及可读存储介质
CN108595927A (zh) * 2018-04-04 2018-09-28 北京市商汤科技开发有限公司 身份认证、解锁及支付方法、装置、存储介质、产品和设备
CN110096996A (zh) * 2019-04-28 2019-08-06 深圳前海达闼云端智能科技有限公司 生物信息识别方法、装置、终端、系统及存储介质
CN110443014A (zh) * 2019-07-31 2019-11-12 成都商汤科技有限公司 身份验证方法、用于身份验证的电子设备和服务器、系统
CN113409055A (zh) * 2021-06-30 2021-09-17 深圳市商汤科技有限公司 支付方法、系统、电子设备及存储介质

Also Published As

Publication number Publication date
CN113409055A (zh) 2021-09-17

Similar Documents

Publication Publication Date Title
CN110008903B (zh) 人脸识别方法、装置、系统、存储介质和人脸支付方法
CN109389723B (zh) 利用人脸识别的访客管理方法、装置、计算机设备
CN110569311B (zh) 一种数据库的数据同步方法、设备和计算机存储介质
EP2973013B1 (en) Associating metadata with images in a personal image collection
CN109920174B (zh) 图书借阅方法、装置、电子设备及存储介质
CN110322317B (zh) 一种交易数据处理方法、装置、电子设备及介质
CN111625809B (zh) 数据授权方法及装置、电子设备、存储介质
KR101647691B1 (ko) 하이브리드 기반의 영상 클러스터링 방법 및 이를 운용하는 서버
WO2023273058A1 (zh) 身份识别方法、系统、装置、计算机设备及存储介质
CN112650875A (zh) 房产图片验证方法、装置、计算机设备及存储介质
US20220164423A1 (en) Method and apparatus for user recognition
WO2023273042A1 (zh) 支付方法、系统、电子设备及存储介质
CN102932421A (zh) 云备份方法及装置
CN107948312B (zh) 一种以位置点作为信息出入口的信息归类发布方法及系统
CN112052251B (zh) 目标数据更新方法和相关装置、设备及存储介质
CN110546638A (zh) 生物特征认证的改进
CN103093213A (zh) 视频文件分类方法及终端
US9529984B2 (en) System and method for verification of user identification based on multimedia content elements
WO2016169241A1 (zh) 一种用于在计算机设备中搜索私有资源的方法和装置
KR101633402B1 (ko) 명함관리 시스템
CN111770080A (zh) 一种设备指纹的恢复方法及装置
CN109858339B (zh) 信息验证方法、装置、计算机设备及计算机可读存储介质
CN111784352A (zh) 认证风险识别方法、装置和电子设备
KR102641630B1 (ko) 데이터베이스에 저장된 피처간의 페어와이즈 유사도 매트릭스를 이용한 노이즈 피처 검출 방법 및 시스템
CN117093715B (zh) 词库扩充方法、系统、计算机设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21947969

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE