WO2021244531A1 - 一种基于人脸识别的支付方法及装置 - Google Patents

一种基于人脸识别的支付方法及装置 Download PDF

Info

Publication number
WO2021244531A1
WO2021244531A1 PCT/CN2021/097684 CN2021097684W WO2021244531A1 WO 2021244531 A1 WO2021244531 A1 WO 2021244531A1 CN 2021097684 W CN2021097684 W CN 2021097684W WO 2021244531 A1 WO2021244531 A1 WO 2021244531A1
Authority
WO
WIPO (PCT)
Prior art keywords
password
user
virtual keyboard
characters
authenticated
Prior art date
Application number
PCT/CN2021/097684
Other languages
English (en)
French (fr)
Inventor
高阳
Original Assignee
支付宝(杭州)信息技术有限公司
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 支付宝(杭州)信息技术有限公司 filed Critical 支付宝(杭州)信息技术有限公司
Publication of WO2021244531A1 publication Critical patent/WO2021244531A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
    • G06F3/04886—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION 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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, 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
    • G06Q20/401—Transaction verification
    • G06Q20/4014—Identity check for transactions
    • G06Q20/40145—Biometric identity checks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification

Definitions

  • This specification relates to the field of information security technology, and in particular to a payment method and device based on face recognition.
  • terminal devices with facial payment functions have appeared.
  • the terminal devices can collect the user’s facial information for identification, and perform payment operations after identifying the user’s identity. Therefore, the user does not need to carry his own mobile terminal, but can pay by displaying the face in the terminal device.
  • a payment method based on face recognition which aims at the registration of facial features.
  • the user configures and stores the authentication password correspondingly; the method includes: calling the image acquisition module to collect the face image of the user to be paid; recognizing the collected face image, and determining the user ID corresponding to the face image; The determined user ID further determines the pre-stored authentication password corresponding to the user ID; dynamically generates and displays a virtual keyboard according to the characters contained in the pre-stored authentication password text; obtains the password to be authenticated entered by the user on the virtual keyboard, and according to the password The authentication result determines whether to perform a payment operation.
  • a payment device based on face recognition for users in a registered set of facial features, corresponding authentication passwords are configured and stored;
  • the device includes: an image acquisition module for calling the image acquisition module , Collect the face image of the user to be paid; the image recognition module is used to recognize the collected face image and determine the user ID corresponding to the face image; the password determination module is used to further Determine the pre-stored authentication password corresponding to the user ID; the virtual keyboard generation module is used to dynamically generate and display a virtual keyboard according to the characters contained in the pre-stored authentication password text; the password authentication module is used to obtain the user’s input on the virtual keyboard The password to be authenticated, and whether to perform the payment operation is determined according to the result of the password authentication.
  • the technical solution provided in this manual can determine the user ID corresponding to the face image after recognizing the user’s face information, and then determine the pre-stored authentication password corresponding to the user ID; generate a virtual keyboard according to the determined pre-stored authentication password, and judge Whether the password to be authenticated entered by the user can be authenticated, and the payment operation is performed after passing. That is, the use of a more private pre-stored authentication password for secondary authentication can effectively reduce the phenomenon of embezzling facial information for payment.
  • FIG. 1 is a schematic flowchart of a payment method based on face recognition according to an embodiment of this specification
  • Fig. 2 is a schematic diagram of a virtual keyboard according to an embodiment of the present specification
  • Fig. 3 is a schematic diagram of a virtual keyboard for hiding plaintext characters according to an embodiment of this specification
  • FIG. 4 is a schematic diagram of an operation of inputting a password based on a virtual keyboard for hiding plaintext characters according to an embodiment of the present specification
  • FIG. 5 is a schematic flowchart of another payment method based on face recognition according to an embodiment of the present specification
  • Fig. 6a is a schematic diagram of another virtual keyboard according to an embodiment of the present specification.
  • Fig. 6b is a schematic diagram of another virtual keyboard for hiding plaintext characters according to an embodiment of the present specification.
  • FIG. 6c is a schematic diagram of another operation of inputting a password based on a virtual keyboard for hiding plaintext characters according to an embodiment of the present specification
  • FIG. 7 is a schematic structural diagram of a payment device based on face recognition according to an embodiment of this specification.
  • Fig. 8 is a schematic diagram of the structure of a device for configuring the device in the embodiment of this specification.
  • first, second, third, etc. may be used in this specification to describe various information, the information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other.
  • first information may also be referred to as second information, and similarly, the second information may also be referred to as first information.
  • word “if” as used herein can be interpreted as "when” or “when” or “in response to a certainty”.
  • the payment method based on biometric identification can make payment without the user's use of a mobile terminal, which is more convenient for the user, and therefore is the key development direction of the current payment method.
  • terminal devices with facial payment functions have appeared.
  • the terminal devices can collect the user’s facial information for identification. After the user’s identity is identified, it can be directly found The account associated with the user identity performs the payment operation, so the user does not need to carry his own mobile terminal, and only needs to display the face in the terminal device to make the payment.
  • face information is information that is easier for other people to obtain, it belongs to information that is easy to leak. Therefore, there may be a phenomenon that the user's property is lost due to the use of facial information for payment. For example, after the thief obtains the user's facial image through the camera device, the payment can be made based on the user's facial image. In addition, problems such as similar faces cannot be completely avoided. Compared with other applications based on biometrics, payment applications involve the user's property security. Therefore, the current payment functions based on facial features still need to be further improved in terms of security.
  • the solution provided in this manual is: when a user needs to make a payment based on face recognition, the user’s face image is first acquired and recognized. After the user’s identity is determined, the user’s identity can be further determined.
  • the payment method based on face recognition proposed in this specification can be applied to a payment terminal device based on face recognition.
  • the embodiment of this specification proposes a payment method based on face recognition.
  • corresponding authentication passwords are configured and stored; the authentication passwords here can be different according to the user’s security requirements.
  • User-configured password information with any number of digits and any text type; it can also be password information that specifies the use of uniform digits and text types. For example, it can be uniformly specified to use the password information that is easy for users to remember, the number of digits is relatively short, and it can be clearly distinguished from Other payment passwords (for example, usually payment passwords are generally 6 digits) digital passwords, such as 4-digit digital passwords. This application does not limit this.
  • the method is specifically as follows: S101, call the image acquisition module to collect the face image of the user to be paid; the terminal device used for face recognition payment can perform this step when it detects that the user has a demand for payment based on the face. After it is detected that the user clicks the "Pay" button or other forms of triggering operations after detecting that the user has purchased the product, it is determined that the user has a payment demand; it can also be after the user has purchased the product for a preset time, for example, after 5 seconds, Make sure that users have payment needs. Of course, if the terminal device supports both face recognition payment methods and scan code payment or other payment methods, it can further provide the user with options for all supported payment methods so that the user can choose the payment method by himself. After it is determined that the user has a need for payment based on face recognition, the image acquisition module can be called, and the image acquisition module is used to collect the face image of the user to be paid.
  • the face image can be extracted based on image recognition technology. Face feature information. After extracting the face feature information, you can further match the obtained face feature information with the pre-stored face feature information in the face feature registration set.
  • the form of the face feature registration set can be as shown in the table As shown in 1, for example, the acquired facial feature information can be matched with the pre-stored facial feature information of user 1, user 2, and user 3, respectively. After the matching is successful, the pre-stored facial feature information with successful matching can be found The user ID.
  • the criterion for successful matching may be that the matching score exceeds the preset score to determine that the matching is successful. For example, if the preset score is 90 points, and the obtained facial feature information matches the pre-stored facial feature information of user 3 and the score exceeds 90 points, it can be determined that the user ID corresponding to the collected facial image is user 3 .
  • the form and content shown in Table 1 are simple exemplary content. The storage form and field information in actual applications can be set according to actual needs. For example, only the user ID can be stored in the facial feature registry. The corresponding relationship with the pre-stored facial feature information, the corresponding relationship between the user ID and the pre-stored facial authentication password is stored in another entry.
  • S103 According to the determined user ID, further determine a pre-stored authentication password corresponding to the user ID;
  • the pre-stored authentication password corresponding to user 3 can be further determined.
  • S104 Dynamically generate and display a virtual keyboard according to the characters contained in the pre-stored authentication password text; since the characters in the pre-stored authentication password for each user are not the same, for example, some users pre-stored pure digital text information, and some users pre-stored It is pure letter text information, and some users pre-stored text information that is a combination of numbers and letters. Therefore, it is possible to dynamically generate a virtual keyboard that is more in line with user needs for the characters contained in the determined pre-stored authentication password text, instead of generating a unified virtual keyboard for all users.
  • the method of dynamically generating virtual keyboards please refer to the following The content of the description will not be detailed here. After the virtual keyboard is generated, it can be displayed in the interactive interface of the terminal device for users to use.
  • S105 Obtain the password to be authenticated input by the user on the virtual keyboard, and determine whether to perform a payment operation according to the password authentication result.
  • the user After viewing the virtual keyboard in the interactive interface, the user can input the password to be authenticated on the virtual keyboard. After obtaining the password to be authenticated entered by the user, the terminal device can perform matching based on the pre-acquired pre-stored authentication password, combined with the above S103 The example in can be matched with "5678". For the matching method, please refer to the description below. I will not go into details here. If the matching is successful, it can be determined that the user has passed the authentication and further obtain the user's pre-stored account information. And perform payment operations for the account.
  • the technical solution provided in this manual can determine the user ID corresponding to the face image after recognizing the user’s face information, and then determine the pre-stored authentication password corresponding to the user ID; generate a virtual keyboard according to the determined pre-stored authentication password, and judge Whether the password to be authenticated entered by the user can be authenticated, and the payment operation is performed after passing. That is, the use of a more private pre-stored authentication password for secondary authentication can effectively reduce the phenomenon of embezzling facial information for payment.
  • the virtual keyboard Since the user is allowed to enter the pre-stored authentication password through the virtual keyboard, the virtual keyboard must include at least pre-stored authentication For the characters contained in the password text, for example, the pre-stored authentication password determined in S103 is "5678", then the generated virtual keyboard must contain at least 5, 6, 7, 8, four keys to meet the user's requirements. It is understandable that, as an authentication method, a password includes the 4 characters themselves and the sequence of 4 characters at the same time.
  • the above example is only a four-digit password. If the pre-stored authentication password has a large number of digits, such as 6 or 8 digits, the security of only generating a virtual keyboard including the characters contained in the pre-stored authentication password text higher.
  • the virtual keyboard that only includes the characters contained in the pre-stored authentication password text is more convenient for the user to input, that is, the user does not need to search in the virtual keyboard, and can immediately check the character information that he needs to input.
  • at least the order of the pre-stored authentication passwords needs to be processed out of order, that is, the position of each character on the virtual keyboard is randomly arranged.
  • the user when the user enters the password to be authenticated, other people may see the authentication password entered by the user. For example, a person standing behind the user may easily view the information entered by the user through a peeping screen. In order to prevent other people from easily observing the information input by the user, some strategies that can confuse the prying eyes can be adopted.
  • the generated virtual keyboard can also include any other characters.
  • Any character can be any character other than the characters contained in the pre-stored authentication password text, for example, the pre-stored authentication password. If it is "5678", a virtual keyboard that also includes other numbers or letters can be generated. Of course, it can also be repeated characters in "5678" or repeated characters of any other characters appearing on the virtual keyboard multiple times.
  • the pre-stored authentication password is "0789", and there are 0, 7, 8, 9 keys in the virtual keyboard
  • characters such as O similar to 0 and q similar to 9 can also be generated.
  • the generated virtual keyboard can be as shown in Figure 2.
  • the snoopers are far away and cannot easily distinguish the actual content on the virtual keyboard. , It is impossible to easily obtain what the user actually enters on the virtual keyboard.
  • obfuscation can also be performed at the stage of user input.
  • One way may be that, since the snooper generally spies the character clicked by the user when the user clicks, it can hide the content of the plaintext characters on the virtual keyboard when it is detected that the user starts to input.
  • Figure 3 it is a schematic diagram of the virtual keyboard in Figure 2 after the plaintext character content is hidden. It can be understood here that the form shown in Figure 3 is only an example and is not used to limit the hidden plaintext character content proposed in this specification. form. Since the character content on the virtual keyboard is automatically hidden when the user is inputting, the snooper cannot directly snoop the actual content input by the user, which can greatly improve the security.
  • Another way of obfuscation at the user input stage can be to use fuzzy matching rules, allowing the user to input the password to be authenticated that is not completely consistent with the pre-stored authentication password, that is, the content entered by the user is not actually the pre-stored authentication password. Even if the snooper really snooped the content entered by the user, he actually did not obtain the user's pre-stored authentication password.
  • it may be a password authentication result obtained by matching the password to be authenticated input by the user with a pre-stored authentication password according to a fuzzy matching algorithm, where the fuzzy matching algorithm may be the whole content or part of the content of the password to be authenticated and the pre-stored authentication password When it matches, it is determined that the match is successful.
  • the password authentication is considered to be passed, where X can be on the virtual keyboard Any character of.
  • the above fuzzy matching algorithm only allows one password to be added, and the allowed number of digits can also be set according to actual needs.
  • the fuzzy matching algorithm used in this embodiment is not to reduce the accuracy of authentication password matching, but to further allow the use of secondary matching as the fuzzy matching algorithm on the premise of successful face recognition and matching. To confuse the vision of the snooper, so that the snooper cannot obtain the user's actual pre-stored authentication password, thereby further improving the security of user information.
  • the preset security operation can be performed when it is determined that the same user has entered the same "password to be authenticated" with the increased number of digits twice.
  • the password to be authenticated input by the user can be obtained; S502, it is further judged whether the password to be authenticated input by the user is successfully matched with the pre-stored authentication password; the matching success here can be entered by the user
  • the password to be authenticated is exactly the same as the pre-stored authentication password; or the part of the password to be authenticated entered by the user is the same as the pre-stored authentication password, that is, the fuzzy matching algorithm is used to determine the success of the match.
  • S506 Perform a payment operation directly on the account corresponding to the user ID.
  • S504 in the case where it is determined that the fuzzy matching algorithm is used to determine that the matching is successful, further retrieve the password record to be authenticated input by the user, and determine whether the password to be authenticated input by the user during the last payment process is the same as the password to be authenticated this time.
  • the passwords are the same; if yes, execute S505; if not, execute S506.
  • the security operation can be to force the user to re-enter an authentication password that complies with the authentication rules, that is, not allowing a "password to be authenticated" with an increased number of digits to be used twice in a row.
  • the security operation can also be to improve the user's facial image recognition matching requirements.
  • the initial face matching score is 90 points, that is, if the score of matching facial feature information is greater than or equal to 90 points, the matching is determined to be successful.
  • the user's face matching score can be increased to 95 points, that is, matching
  • the score of the facial feature information is greater than or equal to 95 points to determine that the matching is successful, so as to further enhance the security of the user account.
  • the user has used the authentication password of the "password to be authenticated" with increased digits twice in succession, it can be further judged whether the current face recognition score has reached the improved matching success standard, and if it has reached the matching success, the matching is determined to be successful If it is not reached, the interface of the face recognition failure will be displayed directly in the interactive interface.
  • the security operation can also be to improve the user's facial image recognition matching requirements.
  • the initial face matching score is 90 points, that is, if the score of matching facial feature information is greater than or equal to 90 points, the matching is determined to be successful.
  • the user's score can be increased to 95 points, that is, matching facial features
  • the information score is greater than or equal to 95 points before the match is determined to be successful.
  • the user will be matched based on the newly determined face recognition matching requirements to further improve the security of the user account.
  • the method of this embodiment can be used to perform security operations to protect the user's account.
  • the terminal device After the user clicks the payment button in the terminal device in a payment behavior, the terminal device calls the image acquisition module to collect the face image of the user to be paid, recognize the collected face image, and determine the user ID corresponding to the face image ,
  • the pre-stored authentication password further determined according to the user's identity is "8562"
  • the generated virtual keyboard is as shown in Figure 6a, which is a virtual keyboard including two-pass single-digit numbers. Since users only pay attention to what they need to input, they can ignore other content, and because snoopers need to pay attention to everything on the keyboard, and repeated characters appear frequently in the keyboard, the snoopers cannot remember where all the characters appear in a short time. .
  • the terminal device After confirming the user input, hide the content of the plaintext characters on the virtual keyboard as shown in Figure 6b.
  • the arrow direction shown in Figure 6c is that the user has clicked 8, 5, 6, 3, 2, five keys at a time through the virtual keyboard. After that, "85632" was entered. Since the snoopers could not know what the user actually entered, the security was effectively improved.
  • the terminal device matches the password to be authenticated and the predicted authentication password entered by the user according to the fuzzy matching algorithm, determines that the matching is successful, and executes the operation of deducting money from the user's account.
  • this manual also provides a payment device based on face recognition.
  • the device includes: an image acquisition module 710, used to call the image acquisition module to collect the face image of the user to be paid; the image recognition module 720, used to recognize the collected face image, determine the face image corresponding to User ID; password determination module 730, used to further determine the pre-stored authentication password corresponding to the user ID according to the determined user ID; virtual keyboard generation module 740, used to dynamically generate a virtual keyboard based on the characters contained in the pre-stored authentication password text And show; the password authentication module 750 is used to obtain the password to be authenticated entered by the user on the virtual keyboard, and determine whether to perform a payment operation according to the result of the password authentication.
  • the virtual keyboard generating module 740 is specifically configured to generate a virtual keyboard including at least the characters included in the pre-stored authentication password text and randomly arranging character positions.
  • the virtual keyboard on the basis of including the characters contained in the pre-stored authentication password text, the virtual keyboard further includes: characters other than the characters contained in the pre-stored authentication password text, and/or, Repeated characters that are the same as the characters contained in the pre-stored authentication password text.
  • the other characters include characters that are highly similar to the characters contained in the pre-stored authentication password text.
  • the password authentication module 750 is specifically configured to hide the content of the plaintext characters on the virtual keyboard when it is detected that the user starts to input; determine the content of the characters on the virtual keyboard according to the user's click position on the virtual keyboard. The entered password to be authenticated.
  • the password authentication result is a password authentication result obtained according to a fuzzy matching algorithm; the fuzzy matching algorithm includes: when all or part of the content of the password to be authenticated matches the pre-stored authentication password, Confirm that the match is successful.
  • the password authentication module 750 is also used to determine if part of the content of the password to be authenticated matches the pre-stored authentication password; then for the current user, it is determined that the last payment process , Whether the input password to be authenticated is the same as the password to be authenticated this time; if they are the same, the preset security operation is performed.
  • the relevant part can refer to the part of the description of the method embodiment.
  • the device embodiments described above are only illustrative. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in this specification. Those of ordinary skill in the art can understand and implement without creative work.
  • the embodiments of this specification also provide a computer device, which at least includes a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein the processor implements the aforementioned method when the program is executed.
  • the method at least includes: invoking an image acquisition module to collect the face image of the user to be paid; recognizing the collected face image to determine the user ID corresponding to the face image; and further determining the user according to the determined user ID Identify the corresponding pre-stored authentication password; dynamically generate and display a virtual keyboard based on the characters contained in the pre-stored authentication password text; obtain the password to be authenticated entered by the user on the virtual keyboard, and determine whether to perform a payment operation according to the password authentication result.
  • FIG. 8 shows a more specific hardware structure diagram of a computing device provided by an embodiment of this specification.
  • the device may include a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050.
  • the processor 1010, the memory 1020, the input/output interface 1030, and the communication interface 1040 realize the communication connection between each other in the device through the bus 1050.
  • the processor 1010 may be implemented by a general CPU (Central Processing Unit, central processing unit), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits for execution related Program to realize the technical solutions provided in the embodiments of this specification.
  • a general CPU Central Processing Unit, central processing unit
  • a microprocessor an application specific integrated circuit (Application Specific Integrated Circuit, ASIC)
  • ASIC Application Specific Integrated Circuit
  • the memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory, random access memory), static storage device, dynamic storage device, etc.
  • the memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the related program codes are stored in the memory 1020 and called and executed by the processor 1010.
  • the input/output interface 1030 is used to connect an input/output module to realize information input and output.
  • the input/output/module can be configured in the device as a component (not shown in the figure), or can be connected to the device to provide corresponding functions.
  • the input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and an output device may include a display, a speaker, a vibrator, an indicator light, and the like.
  • the communication interface 1040 is used to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices.
  • the communication module can realize communication through wired means (such as USB, network cable, etc.), or through wireless means (such as mobile network, WIFI, Bluetooth, etc.).
  • the bus 1050 includes a path to transmit information between various components of the device (for example, the processor 1010, the memory 1020, the input/output interface 1030, and the communication interface 1040).
  • the above device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040, and the bus 1050, in the specific implementation process, the device may also include the necessary equipment for normal operation. Other components.
  • the above-mentioned device may also include only the components necessary to implement the solutions of the embodiments of the present specification, and not necessarily include all the components shown in the figures.
  • the embodiments of this specification also provide a computer-readable storage medium on which a computer program is stored, and the program is executed by a processor to implement the aforementioned method.
  • the method at least includes: invoking an image acquisition module to collect the face image of the user to be paid; recognizing the collected face image to determine the user ID corresponding to the face image; and further determining the user according to the determined user ID Identify the corresponding pre-stored authentication password; dynamically generate and display a virtual keyboard based on the characters contained in the pre-stored authentication password text; obtain the password to be authenticated entered by the user on the virtual keyboard, and determine whether to perform a payment operation according to the password authentication result.
  • Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology.
  • the information can be computer-readable instructions, data structures, program modules, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • a typical implementation device is a computer.
  • the specific form of the computer can be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email receiving and sending device, and a game control A console, a tablet computer, a wearable device, or a combination of any of these devices.
  • the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments.
  • the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.
  • the device embodiments described above are merely illustrative, and the modules described as separate components may or may not be physically separated.
  • the functions of the modules can be combined in the same way when implementing the solutions of the embodiments of this specification. Or multiple software and/or hardware implementations. It is also possible to select some or all of the modules according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement without creative work.

Abstract

一种基于人脸识别的支付方法及装置，针对人脸特征注册集中的用户，对应配置认证口令并存储；该方法包括：调用图像采集模块（710），采集待支付用户的人脸图像；对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识；根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断是否执行支付操作。

Description

一种基于人脸识别的支付方法及装置 技术领域
本说明书涉及信息安全技术领域，尤其涉及一种基于人脸识别的支付方法及装置。
背景技术
随着互联网技术的发展，目前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。
在一些场景中，例如无人超市、游泳馆等场景中，已经出现了具有人脸支付功能的终端设备，终端设备可以采集用户的人脸信息进行识别，在识别出用户身份后进行支付操作，因此用户不用携带自身的移动终端，就可以通过在该终端设备中展示人脸进行支付。
但是由于人脸信息属于容易泄露的信息，因此会出现盗用人脸信息进行支付的现象，造成该用户的财产损失，另外，相似脸等问题也无法完全避免。可见，目前基于人脸特征的支付功能，在安全性上仍有进一步提升的需求。
发明内容
针对上述技术问题，本说明书提供一种基于人脸识别的支付方法及装置，技术方案如下：根据本说明书的第一方面，提供一种基于人脸识别的支付方法，针对人脸特征注册集中的用户，对应配置认证口令并存储；所述方法包括：调用图像采集模块，采集待支付用户的人脸图像；对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识；根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断是否执行支付操作。
根据本说明书的第二方面，提供一种基于人脸识别的支付装置，针对人脸特征注册集中的用户，对应配置认证口令并存储；所述装置包括：图像采集模块，用于调用图像采集模块，采集待支付用户的人脸图像；图像识别模块，用于对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识；口令确定模块，用于根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；虚拟键盘生成模块，用于根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；口令认证模块，用于获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断是否执行支付操作。
本说明书所提供的技术方案，识别出用户的人脸信息后可以确定人脸图像对应的用户标识，进而可以确定该用户标识对应的预存认证口令；根据确定的预存认证口令生成虚拟键盘，并判断用户输入的待认证口令是否能够认证通过，在通过后才执行支付操 作。即利用私密性更高的预存认证口令做二次认证，因此可以有效的减少因为盗用人脸信息进行支付的现象。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本说明书。
附图说明
为了更清楚地说明本说明书实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本说明书实施例中记载的一些实施例，对于本领域普通技术人员来讲，还可以根据这些附图获得其他的附图。
图1是本说明书实施例的一种基于人脸识别的支付方法的流程示意图；
图2是本说明书实施例的一种虚拟键盘的示意图；
图3是本说明书实施例的一种隐藏明文字符的虚拟键盘的示意图；
图4是本说明书实施例的一种基于隐藏明文字符的虚拟键盘输入口令的操作示意图；
图5是本说明书实施例的另一种基于人脸识别的支付方法的流程示意图；
图6a是本说明书实施例的另一种虚拟键盘的示意图；
图6b是本说明书实施例的另一种隐藏明文字符的虚拟键盘的示意图；
图6c是本说明书实施例的另一种基于隐藏明文字符的虚拟键盘输入口令的操作示意图；
图7是本说明书实施例的一种基于人脸识别的支付装置结构示意图；
图8是用于配置本说明书实施例装置的一种设备的结构示意图。
具体实施方式
为了使本领域技术人员更好地理解本说明书实施例中的技术方案，下面将结合本说明书实施例中的附图，对本说明书实施例中的技术方案进行详细地描述，显然，所描述的实施例仅仅是本说明书的一部分实施例，而不是全部的实施例。基于本说明书中的实施例，本领域普通技术人员所获得的所有其他实施例，都应当属于保护的范围。
在本说明书使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本说明书。在本说明书和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。
应当理解，尽管在本说明书可能采用术语第一、第二、第三等来描述各种信息，但这些信息不应限于这些术语。这些术语仅用来将同一类型的信息彼此区分开。例如，在不脱离本说明书范围的情况下，第一信息也可以被称为第二信息，类似地，第二信息也可以被称为第一信息。取决于语境，如在此所使用的词语“如果”可以被解释成为“在……时”或“当……时”或“响应于确定”。
随着互联网技术的发展，目前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。
基于生物特征识别的支付方式，不需用户使用移动终端就可以进行支付，对于用户来说更为便捷，因此是目前支付方式的重点发展方向。
在一些场景中，例如无人超市、游泳馆等场景中，已经出现了具有人脸支付功能的终端设备，终端设备可以采集用户的人脸信息进行识别，在识别出用户身份后，直接查找到与该用户身份关联的账户进行支付操作，因此用户不用携带自身的移动终端，只需通过在该终端设备中展示人脸就可以进行支付。
但是由于人脸信息是其他人比较容易获取的信息，属于容易泄露的信息。因此会出现盗用人脸信息进行支付造成该用户的财产损失的现象，例如，盗取者通过摄像设备获取到用户的人脸图像后，就可以基于用户的人脸图像进行支付。另外，相似脸等问题也无法完全避免。而相对于其他基于生物特征识别的应用而言，支付应用涉及用户的财产安全，因此目前基于人脸特征的支付功能，在安全性上仍有进一步提升的需求。
针对上述技术问题，本说明书提供的方案是：在用户需要基于人脸识别的方式进行支付时，首先获取用户的人脸图像并进行识别，在确定了用户的标识后可以进一步确定该用户标识所对应的预存认证口令，在查找到该用户的预存认证口令口后，可以基于该预存认证口令动态的生成虚拟键盘并展示在交互界面中，匹配用户通过该虚拟键盘输入的待认证口令和预存认证口令后，可以根据口令认证结果判断是否执行此次支付操作。本说明书提出的基于人脸识别的支付方法可以应用于基于人脸识别的支付终端设备。
如图1所示，本说明书实施例提出一种基于人脸识别的支付方法，针对人脸特征注册集中的用户，对应配置认证口令并存储；这里的认证口令可以是根据用户的安全要求不同，用户自行配置的任意位数任意文本类型的口令信息；也可以是规定使用统一位数和文本类型的口令信息，例如可以统一规定使用便于用户记忆的、位数比较简短，同时又能明显区分于其他支付密码(例如通常支付密码一般为6位数字)数字口令，例如4位的数字口令。本申请对此并不做限定。
该方法具体为：S101，调用图像采集模块，采集待支付用户的人脸图像；用于人脸识别支付的终端设备，在检测到用户存在基于人脸支付的需求时，可以执行本步骤，可以在检测到用户选购完商品后点击“去支付”按键或其他形式的触发操作后，确定用户存在支付需求；也可以是在用户选购完商品后达到预设时间后，例如5秒后，确定用户 存在支付需求。当然，若该终端设备既支持人脸识别的支付方式、又支持扫码支付或其他支付方式时，可以进一步将支持的所有支付方式的选项提供给用户，以便用户自行选择支付方式。在确定用户存在基于人脸识别的支付的需求后，可以调用图像采集模块，利用图像采集模块来采集待支付用户的人脸图像。
S102，对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识；在利用图像采集模块采集到该用户的人脸图像后，可以基于图像识别技术提取出该人脸图像中的人脸特征信息，在提取出人脸特征信息后，可以近一步将获取的人脸特征信息与人脸特征注册集中的各预存人脸特征信息进行匹配，人脸特征注册集的形式可以如表1所示，例如，可以将获取的人脸特征信息与用户1、用户2、用户3的预存人脸特征信息分别进行匹配，在匹配成功后，可以查找出该匹配成功的预存人脸特征信息的用户标识。其中，匹配成功的标准可以是匹配分值超过预设分值则判断匹配成功。例如，预设分值为90分，获取的人脸特征信息后与用户3的预存人脸特征信息匹配分值超过了90分，则可以确定采集到的人脸图像对应的用户标识为用户3。可以理解的是表1所示的形式和内容均为简单的示例性内容，实际应用中的存储形式和各字段信息可以根据实际需求进行设置，例如，人脸特征注册集中可以仅保存有用户标识和预存人脸特征信息的对应关系，在另一个表项中存储用户标识和预存人脸认证口令的对应关系。
用户标识 预存人脸特征信息 预存人脸认证口令
用户1 XXX 1234
用户2 XXXX ABCD
用户3 XX 5678
表1
S103，根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；
结合上述S102中的例子，例如在确定了用户标识为用户3后，可以进一步确定用户3对应的预存认证口令，结合上述表1中的例子，可以确定该用户3的预存认证口令为“5678”。
S104，根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；由于每个用户预存的认证口令包含的字符并不相同，例如有的用户预存的是纯数字文本信息、有的用户预存的是纯字母文本信息、有的用户预存的是数字加字母组合的文本信息。因此，可以动态地针对所确定的预存认证口令文本中包含的字符，动态地生成更符合用户需求的虚拟键盘，而不是针对所有用户都生成统一的虚拟键盘，动态生成虚拟键盘的方式可以参照下文描述的内容，这里先不做详述。生成虚拟键盘后可以展示在终端设备的交互界面中供用户使用。
S105，获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断 是否执行支付操作。
用户在查看到交互界面中出现虚拟键盘后，可以在该虚拟键盘上输入待认证口令，终端设备在获取到用户输入的待认证口令后，可以基于预先获取的预存认证口令进行匹配，结合上述S103中的例子，可以和“5678”进行匹配，匹配的方式可以参照下文的描述，这里先不做详述，若匹配成功，则可以确定用户通过了认证，并进一步获取该用户预存的账户信息，并针对该账户执行支付操作。
本说明书所提供的技术方案，识别出用户的人脸信息后可以确定人脸图像对应的用户标识，进而可以确定该用户标识对应的预存认证口令；根据确定的预存认证口令生成虚拟键盘，并判断用户输入的待认证口令是否能够认证通过，在通过后才执行支付操作。即利用私密性更高的预存认证口令做二次认证，因此可以有效的减少因为盗用人脸信息进行支付的现象。
下面对上述S104中，如何根据预存认证口令文本中包含的字符，动态生成虚拟键盘进行描述：由于是要允许用户通过该虚拟键盘输入预存的认证口令，因此该虚拟键盘中至少要包括预存认证口令文本中包含的字符，例如S103中确定的预存认证口令为“5678”，则生成的虚拟键盘中至少要包含5、6、7、8，四个按键，以能够满足用户的使用要求。可以理解的是，口令作为一种认证方式，其既包括4个字符本身、同时又包含4个字符的排列顺序，因此即使虚拟键盘中仅包含这4个字符，若输入者不知道排序顺序，大概率依然无法一次输入正确的认证口令。另外，上述举的例子仅为四位口令，若预存认证口令的位数较多时、例如6位、8位时，若仅生成包括预存认证口令文本中包含的字符的虚拟键盘的安全性也就更高。仅包括预存认证口令文本中包含的字符的虚拟键盘更方便用户的输入，即用户不需在虚拟键盘中寻找，就可以立刻查看到自己需要输入的字符信息。当然，为了避免直接将预存认证口令的顺序也展示给输入者，这里也至少需要将预存认证口令的顺序进行乱序处理，即随机排布每个字符在虚拟键盘上的位置。
另外，在用户输入待认证口令的时候，其他人有可能看到用户输入的认证口令，例如站在用户背后的人，就有可能通过窥屏轻易的查看到用户输入的信息。为了尽量避免其他人能够容易的观察到用户输入的信息，因此可以采用一些可以混淆窥探者视觉的策略。
一种方式可以是，生成的虚拟键盘中除了预存认证口令文本中包含的字符，还可以包括其他任意字符，任意字符可以是除了预存认证口令文本中包含的字符以外的任意字符，例如预存认证口令为“5678”，则可以生成还包括其他数字或字母的虚拟键盘。当然也可以是在虚拟键盘上出现多次“5678”中的重复字符或出现其他任意字符的重复字符。
除此之外，还可以是生成与预存认证口令文本中包含的字符相似度较高的字符，例如预存认证口令为“0789”，则虚拟键盘中除了存在0、7、8、9几个按键以外还可以 生成与0相似的O，与9相似的q等字符。
例如，若确定的预存认证口令为“0789”，则生成的虚拟键盘可以如图2所示，用户在输入口令时，窥探者由于站位较远，因此无法轻易区分出虚拟键盘上的实际内容，也就无法轻易获取到用户实际在该虚拟键盘上输入的内容。
另外，除了在生成的虚拟键盘的内容上混淆窥探者的视觉以外，还可以在用户输入的阶段进行混淆。
一种方式可以是，由于窥探者一般是在用户点击时窥探用户点击的字符，因此可以在检测到用户开始输入时，隐藏虚拟键盘上的明文字符内容。如图3所示，为图2隐藏明文字符内容后的虚拟键盘的示意图，这里可以理解的是，图3所示的形式仅为实例性，并不用于限定本说明书提出的隐藏明文字符内容的形式。由于在用户输入时，虚拟键盘上的字符内容自动隐藏，因此窥探者无法直接窥探到用户输入的实际内容，可以很大程度的提高安全性。
但由于要隐藏虚拟键盘上的明文字符内容，因此需要用户凭借记忆去点击待认证口令字符所在的位置，因此，该功能需要在用户开通口令认证的同时就向用户提前告知，以便其在实际使用口令进行认证时，可以在输入前先记下自己需要输入字符的所在位置。如图4所示，结合上述图3，若用户需要输入“0789”则用户可以依照图中箭头的方向依次点击四个按键，就可以实现输入待认证口令，终端设备就可以根据用户在虚拟键盘上的点击位置确定用户实际输入的内容。
在用户输入的阶段进行混淆的另一种方式还可以是采用模糊匹配规则，允许用户输入的待认证口令并不完全与预存认证口令一致，即用户输入的内容实际上并不是预存认证口令，这样即使窥探者真的窥探到用户输入的内容后，实际上也并没有获取到该用户的预存认证口令。
例如，可以是根据模糊匹配算法，对用户输入的待认证口令和预存认证口令进行匹配以得到的口令认证结果，其中模糊匹配算法可以是待认证口令的全部内容或部分内容与所述预存认证口令相匹配时，确定匹配成功。
例如，用户输入的预存认证口令为“1234”，则在用户输入“X1234”、“1X234”、“12X34”、“123X4”、“1234X”时均认为口令认证通过，其中X可以是虚拟键盘上的任意字符。
当然，上述模糊匹配算法仅允许增加1位口令、还可以根据实际需求设置允许增加的位数。
用户在输入了上述增加位数的“待认证口令”后，即使被窥探者窥探到仍然无法获取到用户实际的预存认证口令。
这里需要说明的是，本实施例中采用的模糊匹配算法并不是为了降低认证口令匹 配的精准度，而是在人脸识别及匹配成功的前提上进一步允许采用二次匹配为模糊匹配算法，用来混淆窥探者的视觉，以使窥探者无法获取到用户实际的预存认证口令，从而更进一步的提升了用户信息的安全性。
可以理解的是，上述各个混淆窥探者视觉的方式既可以单独执行也可以结合在一起执行，本说明书并不对此进行限定。
在一种实施方式中，为了避免盗取者利用获取到的上述用户输入的增加位数“待认证口令”和用户人脸信息进行支付以造成用户的财务损失。可以在确定同一用户两次输入了相同的增加位数的“待认证口令”的情况下，执行预设的安全操作。
确定同一用户两次输入了相同增加位数的“待认证口令”方法流程图可以如图5所示。
S501，在用户通过虚拟键盘输入带认证口令后，可以获取用户输入的待认证口令；S502，进一步判断用户输入的待认证口令是否与预存的认证口令匹配成功；这里的匹配成功可以是用户输入的待认证口令与预存的认证口令完全相同；或用户输入的待认证口令的部分内容与预存认证口令相同，即采用模糊匹配算法判定匹配成功。
若匹配成功则执行S503；若匹配失败则执行S501，提示用户再次输入待认证口令；S503，在匹配成功的基础上进一步判断，是否是用了模糊匹配算法判定的匹配成功；若是则执行S504；若否则执行S506。
S506，直接针对该用户标识对应的账户执行支付操作。
S504，在确定是使用了模糊匹配算法判定匹配成功的情况下，进一步调取用户输入的待认证口令记录，并判断该用户上次支付过程中输入的待认证口令是否与本次输入的待认证口令相同；若是，则执行S505；若否，则执行S506。
另外，在确定是使用了模糊匹配算法判定匹配成功的情况下，还需要记录本次输入的待认证口令、以便为以后支付过程的查询做准备。当然，在存储资源充足和系统资源较空闲的情况下，也可以选择记录每次用户输入的待认证口令，即在S501执行后就记录用户输入的待认证口令。
S505，执行预设的安全操作。
其中，安全操作可以是强制用户重新输入一个符合认证规则的认证口令、即不允许一个增加位数的“待认证口令”连续使用两次。
安全操作还可以是，对该用户的人脸图像识别匹配要求进行提升。例如，初始的人脸匹配分值为90分，即匹配人脸特征信息的分值大于等于90分则确定匹配成功，此时可以将该用户的人脸匹配分值提升为95分，即匹配人脸特征信息的分值大于等于95分才认定匹配成功，以进一步提升该用户账户的安全性。若发现用户连续使用了两次增加位数的“待认证口令”的认证口令后，可以进一步判断当前的人脸识别分值是否达到了 提升后的匹配成功的标准，若达到了则确定匹配成功，若未达到则直接在交互界面中显示人脸识别失败的界面。
安全操作还可以是，对该用户的人脸图像识别匹配要求进行提升。例如，初始的人脸匹配分值为90分，即匹配人脸特征信息的分值大于等于90分则确定匹配成功，此时可以将该用户的分值提升为95分，即匹配人脸特征信息的分值大于等于95分才认定匹配成功，在以后的人脸识别认证过程中，对于该用户都基于新确定了人脸识别匹配要求进行匹配，以进一步提升该用户账户的安全性。
本实施例的方式中，在混淆窥探者视觉的情况下，若窥探者仍然窥探到了用户输入的待认证口令，可以采用本实施例的方式，执行安全操作以对用户的账户进行保护。
下面以一个具体的例子，对本说明书提出的基于人脸识别的支付方法进行说明。
用户在一次支付行为中点击终端设备中的支付按钮后，终端设备调用图像采集模块，采集待支付用户的人脸图像，对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识，进一步根据用户的标识确定的预存认证口令为“8562”，则生成的虚拟键盘如图6a所示，为包括两遍个位数字的虚拟键盘。由于用户只关注自己需要输入的内容，因此可以忽略其他内容，而窥探者由于需要关注键盘上所有内容，而键盘中频繁出现重复字符，因此窥探者并无法短时间内记住所有字符出现的位置。在确定用户输入后，如图6b所示隐藏虚拟键盘上的明文字符内容，如图6c所示的箭头方向为用户通过该虚拟键盘一次点击了8、5、6、3、2，五个按键后，输入了“85632”，由于窥探者无法知晓用户实际输入的内容，因次有效提升了安全性。终端设备根据模糊匹配算法匹配用户输入的待认证口令和预测认证口令，确定匹配成功，执行从该用户的账户中扣款的操作。
与前述一种基于人脸识别的支付方法相对应，本说明书还提供了一种基于人脸识别的支付装置，针对人脸特征注册集中的用户，对应配置认证口令并存储；参见图7所示，该装置包括：图像采集模块710，用于调用图像采集模块，采集待支付用户的人脸图像；图像识别模块720，用于对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识；口令确定模块730，用于根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；虚拟键盘生成模块740，用于根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；口令认证模块750，用于获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断是否执行支付操作。
在一个实施例中，所述虚拟键盘生成模块740，具体用于生成至少包括所述预存认证口令文本中包含的字符、且随机排布字符位置的虚拟键盘。
在一个实施例中，所述虚拟键盘，在包括所述预存认证口令文本中包含的字符的基础上，还包括：除所述预存认证口令文本中包含的字符以外的其他字符，和/或，与所述预存认证口令文本中包含的字符相同的重复字符。
在一个实施例中，所述其他字符包括：与所述预存认证口令文本中包含的字符相 似度较高的字符。
在一个实施例中，所述口令认证模块750，具体用于在检测到用户开始输入时，隐藏所述虚拟键盘上的明文字符内容；根据所述用户在所述虚拟键盘上的点击位置确定其输入的待认证口令。
在一个实施例中，所述口令认证结果为根据模糊匹配算法得到的口令认证结果；所述模糊匹配算法包括：所述待认证口令的全部内容或部分内容与所述预存认证口令相匹配时，确定匹配成功。
在一个实施例中，所述口令认证模块750，还用于在所述待认证口令的部分内容与所述预存认证口令相匹配的情况下；则针对当前的用户，判断在上一笔支付过程中，其输入的待认证口令是否与本次输入的待认证口令相同；若相同，则执行预设的安全操作。
上述设备中各个部件的功能和作用的实现过程具体详见上述方法中对应步骤的实现过程，在此不再赘述。
对于装置实施例而言，由于其基本对应于方法实施例，所以相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的。可以根据实际的需要选择其中的部分或者全部模块来实现本说明书方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
本说明书实施例还提供一种计算机设备，其至少包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，处理器执行所述程序时实现前述的方法。该方法至少包括：调用图像采集模块，采集待支付用户的人脸图像；对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识；根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断是否执行支付操作。
图8示出了本说明书实施例所提供的一种更为具体的计算设备硬件结构示意图，该设备可以包括：处理器1010、存储器1020、输入/输出接口1030、通信接口1040和总线1050。其中处理器1010、存储器1020、输入/输出接口1030和通信接口1040通过总线1050实现彼此之间在设备内部的通信连接。
处理器1010可以采用通用的CPU(Central Processing Unit，中央处理器)、微处理器、应用专用集成电路(Application Specific Integrated Circuit，ASIC)、或者一个或多个集成电路等方式实现，用于执行相关程序，以实现本说明书实施例所提供的技术方案。
存储器1020可以采用ROM(Read Only Memory，只读存储器)、RAM(Random Access Memory，随机存取存储器)、静态存储设备，动态存储设备等形式实现。存储器1020可以存储操作系统和其他应用程序，在通过软件或者固件来实现本说明书实施例所 提供的技术方案时，相关的程序代码保存在存储器1020中，并由处理器1010来调用执行。
输入/输出接口1030用于连接输入/输出模块，以实现信息输入及输出。输入输出/模块可以作为组件配置在设备中(图中未示出)，也可以外接于设备以提供相应功能。其中输入设备可以包括键盘、鼠标、触摸屏、麦克风、各类传感器等，输出设备可以包括显示器、扬声器、振动器、指示灯等。
通信接口1040用于连接通信模块(图中未示出)，以实现本设备与其他设备的通信交互。其中通信模块可以通过有线方式(例如USB、网线等)实现通信，也可以通过无线方式(例如移动网络、WIFI、蓝牙等)实现通信。
总线1050包括一通路，在设备的各个组件(例如处理器1010、存储器1020、输入/输出接口1030和通信接口1040)之间传输信息。
需要说明的是，尽管上述设备仅示出了处理器1010、存储器1020、输入/输出接口1030、通信接口1040以及总线1050，但是在具体实施过程中，该设备还可以包括实现正常运行所必需的其他组件。此外，本领域的技术人员可以理解的是，上述设备中也可以仅包含实现本说明书实施例方案所必需的组件，而不必包含图中所示的全部组件。
本说明书实施例还提供一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现前述的方法。该方法至少包括：调用图像采集模块，采集待支付用户的人脸图像；对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识；根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断是否执行支付操作。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
通过以上的实施方式的描述可知，本领域的技术人员可以清楚地了解到本说明书实施例可借助软件加必需的通用硬件平台的方式来实现。基于这样的理解，本说明书实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在存储介质中，如ROM/RAM、磁碟、光盘等，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)执行本说明书实施例各个实施例或者实施例的某些部分所述的方法。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机，计算机的具体形式可以是个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件收发设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任意几种设备的组合。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于装置实施例而言，由于其基本相似于方法实施例，所以描述得比较简单，相关之处参见方法实施例的部分说明即可。以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，在实施本说明书实施例方案时可以把各模块的功能在同一个或多个软件和/或硬件中实现。也可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性劳动的情况下，即可以理解并实施。
以上所述仅是本说明书实施例的具体实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本说明书实施例原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也应视为本说明书实施例的保护范围。

Claims (17)

  1. 一种基于人脸识别的支付方法，针对人脸特征注册集中的用户，对应配置认证口令并存储；所述方法包括：
    调用图像采集模块，采集待支付用户的人脸图像；
    对采集到的人脸图像进行识别，确定该人脸图像对应的用户标识；
    根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；
    根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；
    获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断是否执行支付操作。
  2. 根据权利要求1所述的方法，所述根据预存认证口令文本中包含的字符，动态生成虚拟键盘，包括：
    生成至少包括所述预存认证口令文本中包含的字符、且随机排布字符位置的虚拟键盘。
  3. 根据权利要求2所述的方法，所述虚拟键盘，在包括所述预存认证口令文本中包含的字符的基础上，还包括：
    除所述预存认证口令文本中包含的字符以外的其他字符，和/或，
    与所述预存认证口令文本中包含的字符相同的重复字符。
  4. 根据权利要求3所述的方法，所述其他字符包括：与所述预存认证口令文本中包含的字符相似度较高的字符。
  5. 根据权利要求1所述的方法，所述获取用户在所述虚拟键盘上输入的待认证口令，包括：
    在检测到用户开始输入时，隐藏所述虚拟键盘上的明文字符内容；
    根据所述用户在所述虚拟键盘上的点击位置确定其输入的待认证口令。
  6. 根据权利要求1所述的方法，所述口令认证结果为根据模糊匹配算法得到的口令认证结果；所述模糊匹配算法包括：所述待认证口令的全部内容或部分内容与所述预存认证口令相匹配时，确定匹配成功。
  7. 根据权利要求6所述的方法，还包括：
    当所述待认证口令的部分内容与所述预存认证口令相匹配时；则针对当前的用户，判断在上一笔支付过程中，其输入的待认证口令是否与本次输入的待认证口令相同；
    若相同，则执行预设的安全操作。
  8. 根据权利要求7所述的方法，所述安全操作，包括：
    对所述用户的人脸图像识别匹配要求进行提升。
  9. 一种基于人脸识别的支付装置，针对人脸特征注册集中的用户，对应配置认证口令并存储；所述装置包括：
    图像采集模块，用于调用图像采集模块，采集待支付用户的人脸图像；
    图像识别模块，用于对采集到的人脸图像进行识别，确定该人脸图像对应的用户标 识；
    口令确定模块，用于根据所确定的用户标识，进一步确定该用户标识对应的预存认证口令；
    虚拟键盘生成模块，用于根据预存认证口令文本中包含的字符，动态生成虚拟键盘并展示；
    口令认证模块，用于获取用户在所述虚拟键盘上输入的待认证口令，并根据口令认证结果判断是否执行支付操作。
  10. 根据权利要求9所述的装置，所述虚拟键盘生成模块，具体用于生成至少包括所述预存认证口令文本中包含的字符、且随机排布字符位置的虚拟键盘。
  11. 根据权利要求10所述的装置，所述虚拟键盘，在包括所述预存认证口令文本中包含的字符的基础上，还包括：
    除所述预存认证口令文本中包含的字符以外的其他字符，和/或，
    与所述预存认证口令文本中包含的字符相同的重复字符。
  12. 根据权利要求11所述的装置，所述其他字符包括：与所述预存认证口令文本中包含的字符相似度较高的字符。
  13. 根据权利要求9所述的装置，
    所述口令认证模块，具体用于在检测到用户开始输入时，隐藏所述虚拟键盘上的明文字符内容；
    根据所述用户在所述虚拟键盘上的点击位置确定其输入的待认证口令。
  14. 根据权利要求9所述的装置，所述口令认证结果为根据模糊匹配算法得到的口令认证结果；所述模糊匹配算法包括：所述待认证口令的全部内容或部分内容与所述预存认证口令相匹配时，确定匹配成功。
  15. 根据权利要求14所述的装置，
    所述口令认证模块，还用于在所述待认证口令的部分内容与所述预存认证口令相匹配的情况下；则针对当前的用户，判断在上一笔支付过程中，其输入的待认证口令是否与本次输入的待认证口令相同；
    若相同，则执行预设的安全操作。
  16. 根据权利要求15所述的装置，所述安全操作，包括：
    对所述用户的人脸图像识别匹配要求进行提升。
  17. 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述程序时实现如权利要求1至8任一项所述的方法。
PCT/CN2021/097684 2020-06-04 2021-06-01 一种基于人脸识别的支付方法及装置 WO2021244531A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010501293.7A CN111611976A (zh) 2020-06-04 2020-06-04 一种基于人脸识别的支付方法及装置
CN202010501293.7 2020-06-04

Publications (1)

Publication Number Publication Date
WO2021244531A1 true WO2021244531A1 (zh) 2021-12-09

Family

ID=72199916

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/097684 WO2021244531A1 (zh) 2020-06-04 2021-06-01 一种基于人脸识别的支付方法及装置

Country Status (2)

Country Link
CN (1) CN111611976A (zh)
WO (1) WO2021244531A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114731280A (zh) * 2022-02-25 2022-07-08 百果园技术(新加坡)有限公司 身份认证方法、装置、终端、存储介质及程序产品

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111611976A (zh) * 2020-06-04 2020-09-01 支付宝(杭州)信息技术有限公司 一种基于人脸识别的支付方法及装置
CN112150151B (zh) * 2020-10-09 2023-07-14 平安科技（深圳）有限公司 安全支付方法、装置、电子设备及存储介质
CN112819061A (zh) * 2021-01-27 2021-05-18 北京小米移动软件有限公司 口令信息识别方法、装置、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104978512A (zh) * 2014-04-09 2015-10-14 周宏建 密码输入与确认方法及其系统
CN107633166A (zh) * 2017-07-21 2018-01-26 徐智能 一种隐蔽输入字符的动态虚拟键盘输入方法
CN109615387A (zh) * 2018-11-29 2019-04-12 中国科学院重庆绿色智能技术研究院 一种基于人脸识别的消费支付系统及方法
CN111611976A (zh) * 2020-06-04 2020-09-01 支付宝(杭州)信息技术有限公司 一种基于人脸识别的支付方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113902446A (zh) * 2019-08-30 2022-01-07 北京银联金卡科技有限公司 基于安全单元和可信执行环境的人脸支付安全方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104978512A (zh) * 2014-04-09 2015-10-14 周宏建 密码输入与确认方法及其系统
CN107633166A (zh) * 2017-07-21 2018-01-26 徐智能 一种隐蔽输入字符的动态虚拟键盘输入方法
CN109615387A (zh) * 2018-11-29 2019-04-12 中国科学院重庆绿色智能技术研究院 一种基于人脸识别的消费支付系统及方法
CN111611976A (zh) * 2020-06-04 2020-09-01 支付宝(杭州)信息技术有限公司 一种基于人脸识别的支付方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114731280A (zh) * 2022-02-25 2022-07-08 百果园技术(新加坡)有限公司 身份认证方法、装置、终端、存储介质及程序产品
CN114731280B (zh) * 2022-02-25 2024-02-09 百果园技术(新加坡)有限公司 身份认证方法、装置、终端及存储介质

Also Published As

Publication number Publication date
CN111611976A (zh) 2020-09-01

Similar Documents

Publication Publication Date Title
WO2021244531A1 (zh) 一种基于人脸识别的支付方法及装置
US10360412B2 (en) Contextual contemporaneous gesture and keyboard entry authentication
US10395065B2 (en) Password protection under close input observation based on dynamic multi-value keyboard mapping
US11258810B2 (en) Identity authentication method, apparatus, and system
US20130263240A1 (en) Method for authentication and verification of user identity
US11171968B1 (en) Method and system for user credential security
CN106355141B (zh) 可携式电子装置及其操作方法
KR20150050666A (ko) 패턴 입력 장치 및 방법과 이를 이용한 기록 매체
JP2016045811A (ja) 認証システム及び方法
US11902275B2 (en) Context-based authentication of a user
US20170249450A1 (en) Device and Method for Authenticating a User
US20110154483A1 (en) Electronic device with password protection function and method thereof
US20200201977A1 (en) Method for authenticating a first user and corresponding first device and system
EP4163854A1 (en) Systems and methods for conducting remote user authentication
US10460094B2 (en) Method, apparatus, and storage medium for data processing
KR101516565B1 (ko) 온라인 상에서의 이미지를 이용한 인증방법 및 장치
CN111181981A (zh) 一种处理方法、装置及计算机设备
CN111125742A (zh) 文件管理方法、智能终端以及具有存储功能的装置
WO2018232659A1 (zh) 一种移动终端隐私处理方法及移动终端
US20230306970A1 (en) Authentication by speech at a machine
Suruthi et al. Efficient handwritten passwords to overcome spyware attacks
KR101823528B1 (ko) 사용자의 행위 패턴을 이용한 인증 방법 및 그 방법을 구현하는 프로그램을 기록한 기록매체
CN116301402A (zh) 密码输入方法和装置
Joseph et al. ACHIEVING PRIVACY PROTECTION OF MULTIFACTOR AUTHENTICATION IN CLOUD
KR20140083937A (ko) 다중 용도 일회용 코드 운영 방법

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: 21818763

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21818763

Country of ref document: EP

Kind code of ref document: A1