WO2022222735A1 - 信息处理方法、装置、计算机设备和存储介质 - Google Patents

信息处理方法、装置、计算机设备和存储介质 Download PDF

Info

Publication number
WO2022222735A1
WO2022222735A1 PCT/CN2022/084826 CN2022084826W WO2022222735A1 WO 2022222735 A1 WO2022222735 A1 WO 2022222735A1 CN 2022084826 W CN2022084826 W CN 2022084826W WO 2022222735 A1 WO2022222735 A1 WO 2022222735A1
Authority
WO
WIPO (PCT)
Prior art keywords
cartoon
information
target object
settlement
biological
Prior art date
Application number
PCT/CN2022/084826
Other languages
English (en)
French (fr)
Inventor
张晓翼
张志强
王少鸣
洪哲鸣
郭润增
Original Assignee
腾讯科技(深圳)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 腾讯科技(深圳)有限公司 filed Critical 腾讯科技(深圳)有限公司
Publication of WO2022222735A1 publication Critical patent/WO2022222735A1/zh
Priority to US17/993,208 priority Critical patent/US20230082150A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172Classification, e.g. identification
    • 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • 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
    • G06Q20/382Payment protocols; Details thereof insuring higher security of transaction
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/107Static hand or arm
    • G06V40/11Hand-related biometrics; Hand pose recognition

Definitions

  • the present application relates to the field of computer technology, in particular to information processing technology.
  • the payment device when a user makes face payment for an order through a payment device, the payment device will collect the user's face information, and then display the captured user's face on the device page in real time. See your face on the device. In this scenario, the user's face directly displayed on the device page is easily stolen by surrounding users or other devices, and it is difficult to ensure the security of the user's face information.
  • the present application provides an information processing method, apparatus, computer equipment and storage medium, which can improve the security of biological information of a target object.
  • One aspect of the present application provides an information processing method, executed by a computer device, the method comprising:
  • the service page In response to the biological settlement operation for the target order, the service page is displayed, and the biological information of the target object is collected; the biological settlement operation is used to trigger the authentication of the target object based on the biological information, and the settlement of the target order is carried out according to the authentication result;
  • the cartoon information corresponding to the biological information of the target object is displayed on the service page;
  • the biometric settlement information of the target order is determined at least according to the authentication result for the target object.
  • One aspect of the present application provides an information processing method, executed by a computer device, the method comprising:
  • the service page In response to the biological settlement operation for the target order, the service page is displayed, and the biological information of the target object is collected; the biological settlement operation is used to trigger the authentication of the target object based on the biological information, and the settlement of the target order is carried out according to the authentication result;
  • the target object is authenticated based on the biological information, and the biological information is converted into cartoons to obtain the cartoon information corresponding to the biological information;
  • the cartoon information is displayed on the service page;
  • the biometric settlement information of the target order is determined at least according to the authentication result for the target object.
  • One aspect of the present application provides an information processing device, the device comprising:
  • the first information collection module is used to display the service page in response to the biological settlement operation for the target order, and collect the biological information of the target object;
  • the biological settlement operation is used to trigger the identity verification of the target object based on the biological information, and according to the identity verification As a result, the settlement for the target order is performed;
  • a first information display module configured to display cartoon information corresponding to the biological information of the target object on the service page during the process of performing identity verification on the target object based on the biological information
  • the first settlement module is used to display the biological settlement information of the target order; the biological settlement information is determined at least according to the identity verification result for the target object.
  • One aspect of the present application provides an information processing device, the device comprising:
  • the second information collection module is used to display the service page in response to the biological settlement operation for the target order, and collect the biological information of the target object;
  • the biological settlement operation is used to trigger the identity verification of the target object based on the biological information, and according to the identity verification As a result, the settlement for the target order is performed;
  • the information conversion module is used to authenticate the target object based on the biological information, and perform cartoon conversion on the biological information to obtain the cartoon information corresponding to the biological information;
  • the second information display module is used to display the cartoon information on the service page in the process of authenticating the target object based on the biological information
  • the second settlement module is used to display the biological settlement information of the target order; the biological settlement information is determined at least according to the identity verification result for the target object.
  • One aspect of the present application provides a computer device, including a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method in one aspect of the present application.
  • One aspect of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, causes the processor to perform the above-mentioned aspect. method.
  • a computer program product or computer program comprising computer instructions stored in a computer readable storage medium.
  • the processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method provided in various optional manners such as the above aspect.
  • This application displays the service page according to the biological settlement operation for the target order, and collects the biological information of the target object; in the process of authenticating the target object based on the biological information, the cartoon corresponding to the biological information of the target object is displayed on the service page.
  • Information displays biometric billing information for the target order.
  • the method proposed in the present application can display the cartoon information corresponding to the biological information of the target object on the service page, which improves the security of the biological information of the target object, and does not directly display the biological information of the target object.
  • FIG. 1 is a schematic structural diagram of a network architecture provided by an embodiment of the present application.
  • Fig. 2 is the scene schematic diagram of a kind of face-swiping payment provided by this application;
  • FIG. 3 is a schematic flowchart of an information processing method provided by the present application.
  • Fig. 4 is the page schematic diagram of a kind of service page provided by this application.
  • Fig. 5 is a kind of page schematic diagram of selecting background information provided by this application.
  • FIG. 6 is a schematic page diagram of an order settlement provided by the present application.
  • FIG. 7 is a schematic flowchart of an information processing method provided by the present application.
  • FIG. 8 is a schematic diagram of a model training scenario provided by the present application.
  • FIG. 9 is a schematic diagram of a model training scenario provided by the present application.
  • FIG. 11 is a schematic structural diagram of an information processing device provided by the present application.
  • FIG. 12 is a schematic structural diagram of an information processing device provided by the present application.
  • FIG. 13 is a schematic structural diagram of a computer device provided by the present application.
  • FIG. 1 is a schematic structural diagram of a network architecture provided by an embodiment of the present application.
  • the network architecture may include a server 200 and a terminal device cluster, and the terminal device cluster may include one or more terminal devices, and the number of terminal devices will not be limited here.
  • the multiple terminal devices may specifically include a terminal device 100a, a terminal device 101a, a terminal device 102a, . . . , a terminal device 103a; as shown in FIG.
  • Each terminal device 103a can be connected to the server 200 via a network, so that each terminal device can perform data interaction with the server 200 through the network connection.
  • the server 200 shown in FIG. 1 may be an independent physical server, or a server cluster or a distributed system composed of multiple physical servers, or may provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network Cloud servers for basic cloud computing services such as services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.
  • the terminal device 100a, the terminal device 101a, the terminal device 102a, . . . , and the terminal device 103a may all be user-oriented terminal devices, such as smart phones, tablet computers, notebook computers, desktop computers, smart TVs, frog devices (deployment Offline, devices that support users to complete order payment through operations such as face swiping) and other smart terminals.
  • the user can request the server 200 to cooperate to complete the payment for the order through the above-mentioned terminal device, and, in the process of paying by the face, the terminal device will display the cartoon image of the user on its display interface, so as to use the cartoon image to replace the actual collection. face image.
  • the order may be a commodity order generated by the target user through a shopping application (which may be the following shopping platform), the face-swiping payment may be completed in a payment application (equivalent to the following settlement software), and the shopping application and payment application may It can be the same application or different applications. If the shopping application and the payment application are different applications, the payment application can be called to pay when the order is paid through the shopping application.
  • the server 200 can be the background server of the payment application. The following takes the communication between the terminal device 100a and the server 200 as an example to describe the embodiments of the present application in detail.
  • FIG. 2 is a schematic diagram of a face-swiping payment scenario provided by the present application.
  • the terminal device 100a may respond to the face-swiping payment operation for the order triggered by the user through the payment application, turn on the camera, and collect the user's face video frame (that is, the captured image including the user's face), and,
  • the terminal device 100a can pull the cartoon conversion model 101b from the server 200, and the cartoon conversion model 101b can convert the captured image including the real face of the user into a cartoon image.
  • the specific training process of the cartoon conversion model 101b can refer to the following figure. 7 corresponds to the description in the embodiment.
  • the terminal device 100a can input the collected video frames of the user's face into the cartoon conversion model 101b, and the cartoon video frame 102b (ie, a cartoon image) corresponding to the video frame of the user's face can be generated by the cartoon conversion model 101b.
  • the terminal device 100a can also authenticate the user based on the collected face video frames (such as block 100b), and the terminal device 100a can display the user on the terminal page during the process of authenticating the user. of cartoon video frames (eg, block 103b).
  • the terminal device 100a may cooperate with the server 200 to authenticate the user, thereby obtaining the authentication result 104b for the user.
  • the authentication result 104b may represent that the authentication of the user fails, or that the authentication of the user is successful.
  • the terminal device can obtain the payment result 105b for the user's order, and the payment result 105b can indicate that the user's order payment fails, or can indicate that the user's order payment is successful.
  • the server 200 can pay for the user's order through the payment account associated with the user (such as the account registered by the user through the above payment application);
  • the server 200 can send the prompt information of the successful payment of the order to the user to the terminal device 100a, and the terminal device 100a can obtain the above-mentioned payment result 105b according to the prompt information of the successful payment of the order to the user,
  • the payment result at this time indicates that the user's order payment is successful;
  • the server 200 can send the prompt information about the failure of the user's order payment to the terminal device 100a, and the terminal device 100a can just
  • the above-mentioned payment result 105b is obtained according to the prompt information of the user's order payment failure, and the payment result at this time indicates that the user's order payment failed.
  • the server 200 cannot pay for the user's order.
  • a prompt message indicating that the payment for the user's order has failed can be obtained, and the server 200 can pay for the user's order.
  • the failed prompt information is sent to the terminal device 100a, and the terminal device 100a can obtain the above payment result 105b according to the prompt information of the user's order payment failure, and the payment result at this time indicates that the user's order payment failed.
  • the user's real face may not be displayed, but a cartoon face similar to the user's real face may be displayed, thereby reducing the impact of the displayed real face on the user.
  • the resulting sense of visual conflict enhances the user's interest in face-swiping payment.
  • the security of the user's real face can also be improved.
  • FIG. 3 is a schematic flowchart of an information processing method provided by the present application.
  • the execution body in this embodiment of the present application may be a computer device, or a computer device cluster composed of multiple computer devices.
  • the computer device can be a server or a terminal device. Therefore, the execution subject in this embodiment of the present application may be a server or a terminal device, and may also be executed cooperatively by the server and the terminal device.
  • the execution subject of the present application is a terminal device as an example for description.
  • the method may include:
  • step S101 in response to the biological settlement operation for the target order, a service page is displayed, and biological information of the target object is collected.
  • settlement may refer to payment
  • the target order may be any order that requires payment and settlement.
  • the target order may be a payment order for purchased products in a shopping platform, and for example, the target order may be for an offline store. Online payment of orders for purchased items.
  • the biological settlement operation is the operation of payment and settlement for the target order. Specifically, the biological settlement operation refers to the authentication of the target object based on the biological information of the target object that triggers the payment of the target order, and then according to the authentication result. The operation of settlement payment for an order.
  • the target order can be the order of the target object
  • the target object can be any user
  • the biological information of the target object refers to any biological information that can be used to authenticate the target object, for example, the target object's face information, pupil information, palm fingerprint information or fingerprint information.
  • the terminal device can display the service page according to the biological settlement operation of the target object for the target order, and collect the biological information of the target object: the service page can be understood as a shooting page, and the biological information of the target object can be displayed on the service page.
  • the service page can be understood as a shooting page
  • the biological information of the target object can be displayed on the service page.
  • the cartoon information corresponding to the information reference may be made to the following step S102.
  • the terminal device may display a settlement method list on the terminal page, and the settlement method list may include one or more settlement methods for the target object to select.
  • the settlement method list may include face settlement methods, pupil settlement methods. method, fingerprint settlement method and palmprint settlement method.
  • the terminal device may display a service page according to the target object's selection operation for the settlement method in the settlement method list, and collect biological information corresponding to the settlement method selected by the target object.
  • the selection operation of the target object with respect to the settlement method in the settlement method list may be the above-mentioned biological settlement operation.
  • the collected biological information of the target object can be the face information of the target object; if the settlement method selected by the target object is the pupil settlement method, the collected biological information of the target object can be is the pupil information of the target object; if the settlement method selected by the target object is the fingerprint settlement method, the collected biometric information of the target object can be the fingerprint information of the target object; if the settlement method selected by the target object is the palmprint settlement method, the collected biometric information can be The biological information of the target object may be palmprint information of the target object; and so on.
  • Step S102 in the process of performing identity verification on the target object based on the biological information, displaying cartoon information corresponding to the biological information of the target object on the service page.
  • the terminal device may authenticate the target object based on the collected biological information of the target object, or the terminal device may send the collected biological information of the target object to the server in the background, so that the server can be based on the biological information of the target object. information to authenticate the target object.
  • the terminal device can display the cartoon information corresponding to the biological information of the target object on the service page, please refer to the following description.
  • the biological information of the target object collected by the terminal device may include the i-th face video frame and the j-th face video frame obtained by photographing the target object.
  • the i-th face video frame And the jth frame of face video frame includes the face image of the target object, so the ith frame of face video frame and the jth frame of face video frame include the face information of the target object, the ith frame of face video frame and the The j-frame face video frame can be any two adjacent face video frames obtained by the terminal device shooting the target object when collecting biological information.
  • a face video frame is essentially an image, and both i and j are less than or equal to A positive integer of the total number of all face video frames captured in the process of collecting the biological information of the target object, the i-th face video frame is the face video frame preceding the j-th face video frame.
  • the i-th face video frame and the j-th face video frame each have a face display attribute of the target object, and the face display attribute may include at least one of the following: a face pose attribute, a face expression attribute, and a face configuration
  • the facial gesture attribute can represent the inclination of the face of the target object (such as whether to tilt the head, bow the head or look up, etc.)
  • the facial expression attribute can represent the facial expression of the target object (such as happy expression, sad expression or surprised expression, etc.)
  • the face accessories attribute can represent the accessories (such as glasses or beauty contact accessories) worn on the face of the target object, and the above face display attributes are only examples.
  • the cartoon information corresponding to the biological information of the target object may include the cartoon face video frame corresponding to the i-th face video frame and the cartoon face video frame corresponding to the j-th face video frame. Therefore, at the first moment corresponding to the ith frame of the face video frame (this first moment can be understood as the moment when the ith frame of the face video frame is collected), the terminal device can follow the ith frame of the face on the service page.
  • the face display attribute possessed by the video frame is used to display the cartoon face video frame corresponding to the ith frame of the face video frame, and the cartoon face video frame includes the face corresponding to the target object captured in the ith frame of the face video frame.
  • the cartoon face, the cartoon face has the face display attributes of the ith frame of the face video frame, but the ith frame of the face video frame has the real face display attributes of the target object, and the cartoon face has the target object.
  • Object cartoon's face display properties are used to display the cartoon face video frame corresponding to the ith frame of the face video frame
  • the terminal device when reaching the second moment corresponding to the jth frame of the face video frame from the above-mentioned first moment (this second moment can be understood as the moment when the jth frame of the face video frame is collected), the terminal device can be displayed on the service page.
  • the cartoon face video frame corresponding to the jth frame of the human face video frame is displayed, and the cartoon face video frame includes the jth frame of the face video frame.
  • the cartoon face corresponding to the face of the target object has the face display attribute of the jth frame of the face video frame, but the jth frame of the face video frame has the real face display attribute of the target object, And the cartoon face has the face display attribute of the target object cartoon.
  • the cartoon information corresponding to the biological information can be displayed on the service page synchronously.
  • the time delay between collecting biological information and displaying cartoon information is very small, which can be considered as synchronization.
  • the biological information of the target object may include a collected face image of the target object, and the face image may be any frame of a face video frame of the target object collected during the display of the service page. Therefore, the cartoon information corresponding to the biological information of the target object may include a cartoon face image corresponding to the face image, and the cartoon face image can be understood as a cartoon face video frame corresponding to the face image, and the cartoon face image Include cartoon faces corresponding to the real faces of the target objects in the face images.
  • the terminal device can display the cartoon face image on the service page according to the face display attribute of the face image of the target object.
  • the biological information of the target object may include the collected palmprint image of the target object, and the palmprint image may be any palmprint video frame of the target object collected during the display of the service page. It may be an image obtained by photographing the palm of the target object, and the palmprint image includes palmprint information of the target object. Therefore, the cartoon information corresponding to the biological information of the target object may include a cartoon palmprint image corresponding to the palmprint image, and the cartoon palmprint image can be understood as a cartoon palmprint video frame corresponding to the palmprint image, and the cartoon palmprint image It includes the cartoon palm corresponding to the real palm of the target object in the palm print image.
  • the terminal device can display the cartoon palmprint image on the service page according to the palmprint display attribute of the palmprint image of the target object.
  • the palmprint display attribute may include at least one of palmprint posture attribute and palmprint accessory attribute
  • the palmprint posture attribute may include the degree of inclination and the degree of opening and closing of the palm of the target object in the palmprint image
  • the palmprint accessory attribute may include accessories (such as rings, etc.) worn on the palm of the target object in the palmprint image.
  • the cartoon palmprint image has the palmprint display property of the palmprint image, but the palmprint image has the real palmprint display property of the target object, and the cartoon palmprint image has the palmprint display property of the target object cartoon.
  • the biological information of the target object may include the collected pupil image of the target object, and the pupil image may be any frame of pupil video frames of the target object collected during the display of the service page, and the pupil image may be an image of the target object.
  • An image captured by the subject's eye, and the pupil image includes pupil information of the target subject. Therefore, the cartoon information corresponding to the biological information of the target object may include a cartoon pupil image corresponding to the pupil image, and the cartoon pupil image may be understood as a cartoon pupil video frame corresponding to the pupil image, and the cartoon pupil image includes the target in the pupil image.
  • the terminal device can display the cartoon pupil image on the service page according to the pupil display attribute of the pupil image of the target object.
  • the pupil display attribute may include at least one of a pupil dilation attribute and a pupil accessory attribute
  • the pupil dilation attribute may include the degree of opening or closing of the pupil of the target object in the pupil image.
  • Attributes may include accessories (such as color lenses, etc.) worn on the pupil of the target object in the pupil image.
  • the cartoon pupil image has the pupil display attribute of the pupil image, but the pupil image has the real pupil display attribute of the target object, and the cartoon pupil image has the pupil display attribute of the target object cartoon.
  • the biological information of the target object collected by the terminal device may be several video frames (such as the above-mentioned face video frames, Pupil video frame or palmprint video frame, etc.), the several video frames include the information of the biological parts of the target object (such as face information, pupil information or palmprint information, etc.), cartoon information corresponding to the biological information of the target object Including the cartoon video frame corresponding to each video frame (such as the above-mentioned cartoon face video frame, cartoon pupil video frame or cartoon palm print video frame, etc.).
  • the terminal device can simultaneously display the cartoon video frame corresponding to each video frame on the service page while collecting each video frame, so that the real target object (such as real target object) is not displayed in the process of shooting the target object.
  • the face of the target object to be photographed), and the cartoon image corresponding to the real target object (such as the image of the cartoon face, the image of the cartoon palm print, or the image of the cartoon pupil, etc.) is displayed, and, during the shooting process, the target object What action or change is made, the cartoon image displayed on the service page can also produce the same action or change.
  • the target object in the video frame is very similar to the cartoon image in the cartoon video frame corresponding to the video frame, except that the video frame includes the real target object captured, while the cartoon video frame includes the captured image.
  • the cartoon image corresponding to the target object is very similar to the cartoon image in the cartoon video frame corresponding to the video frame, except that the video frame includes the real target object captured, while the cartoon video frame includes the captured image.
  • FIG. 4 is a schematic page diagram of a service page provided by the present application.
  • the cartoon information of the target object displayed in the service page can be dynamically changed.
  • the service page 100c, the service page 101c and the service page 102c sequentially display the cartoon characters corresponding to the first face video frame of the target object.
  • the interval between adjacent cartoon face video frames is very small, so displaying each cartoon face video frame sequentially and continuously is a dynamic display effect.
  • the display is composed of several cartoon face video frames. cartoon human face video.
  • the biological information is a video frame obtained by photographing a certain biological part of the target object
  • the cartoon information corresponding to the biological information is a cartoon video frame corresponding to the video frame
  • the cartoon video frame may not include the video frame.
  • the background of the photographed target object only includes the cartoon image corresponding to the photographed target object. Therefore, the terminal device can also display a background selection list on the service page.
  • the background selection list can include M kinds of background information, where M is a positive integer, and the specific value of M can be determined according to the actual application scenario, which is not limited.
  • the terminal device can use the background information selected by the target object as the target background information of the cartoon image of the target object in the cartoon video frame according to the selection operation of the target object for the M kinds of background information, and compare the cartoon information and the target in the service page.
  • the synchronous display of the background information can be understood as synthesizing the target background information and the cartoon video frame, and the synthesized cartoon video frame includes the photographed cartoon image of the target object and the target background information.
  • FIG. 5 is a schematic diagram of a page for selecting background information provided by the present application.
  • the service page 100d displays a cartoon video frame 107d corresponding to the video frame obtained by photographing the target object.
  • the service page 100d also includes a background selection list, and the background selection list includes M kinds of background information that can be selected by the target object, such as background information 101d, background information 102d, and background information 103d.
  • the target object does not select background information
  • the background of the cartoon image of the target object in the displayed cartoon face video frame is blank.
  • the terminal device can change from displaying the service page 100d to displaying the service page 104d.
  • the cartoon face of the target object in the displayed cartoon face video frame is displayed.
  • the background information of the image is the background information 101d, that is, the background information of the cartoon image of the target object in the displayed cartoon face video frame includes many small triangles.
  • the terminal device can change from displaying the service page 100d to displaying the service page 105d.
  • the target in the displayed cartoon face video frame is displayed.
  • the background information of the cartoon image of the object is the background information 102d, that is, the background information of the cartoon image of the target object in the displayed cartoon face video frame includes many straight lines.
  • the terminal device can change from displaying the service page 100d to displaying the service page 106d.
  • the target in the displayed cartoon face video frame is displayed.
  • the background information of the cartoon image of the object is the background information 103d, that is, the background information of the cartoon image of the target object in the displayed cartoon face video frame includes many wavy lines.
  • background information 101d background information 102d
  • background information 103d background information 103d
  • specific content included in the background information can be arbitrarily set.
  • Step S103 displaying biological settlement information of the target order.
  • the biological settlement information can be displayed on the service page, or the biological settlement information can also be displayed on a new page that is not a service page.
  • the terminal device may display corresponding biological settlement information, and the displayed biological settlement information is determined at least according to the result of the identity verification on the target object.
  • the biological settlement information can include the following situations:
  • the target order can be settled through the settlement account associated with the target object, and the settlement success information is generated, and the settlement success information can be used as the biological settlement information.
  • the biological settlement information at the time is used to prompt the target object to settle the target order successfully.
  • the identity verification of the target object based on the biometric information fails, it indicates that the settlement account associated with the target object cannot be obtained.
  • the settlement of the target order fails, and the terminal device can generate settlement failure information.
  • the settlement failure information It can be used as biological settlement information, and the biological settlement information at this time is used to prompt the target object to fail to settle the target order.
  • the above-mentioned target order may be settled through settlement software, and the above-mentioned biological settlement operation may also be performed in the settlement software, and the target object may be the user of the settlement software, that is, the target object has registered users in the settlement software Therefore, the settlement account associated with the target object may be an account bound to the target object's user account in the settlement software (eg, a balance account in the settlement software, or a bank account, etc.). Therefore, it can be understood that the successful authentication of the target object through the biological information may refer to obtaining the user account of the target object in the settlement software through the biological information verification. Conversely, the failure to authenticate the target object through the biometric information may refer to obtaining the user account of the target object in the settlement software through the failure to verify the biometric information.
  • the terminal device can also generate settlement confirmation information, and the settlement confirmation information can be used as the biological settlement information.
  • the biological settlement information is used to support the user to settle the target order. That is, it is used to allow the user to confirm and then settle the target order.
  • the settlement confirmation information may include the mask of the user account of the target object obtained by verification in the settlement software (eg, the mask of the mobile phone number associated with the user account), or may include the avatar of the user account of the target object.
  • the terminal device may use the settlement account associated with the target object to settle the target order according to the target object's confirmation operation for the settlement confirmation information.
  • the terminal device may also display an account selection list, in which the account selection list is It may include N settlement accounts associated with the target object, where N is a positive integer, and the specific value of N is determined according to the actual application scenario. Therefore, the terminal device can also use the settlement account selected by the target object as the target settlement account according to the selection operation of the target object on the N settlement accounts in the account selection list, and settle the target order through the target settlement account.
  • the operation of the terminal device to settle the target order may be that the terminal device requests the background of the settlement software to settle the target order, and then realizes the settlement of the target order through the background of the settlement software. After the settlement is successful, the background of the settlement software The settlement result can be returned to the terminal device.
  • FIG. 6 is a schematic diagram of an order settlement page provided by the present application.
  • a list of payment methods is displayed on the terminal page 100e, and the list includes three payment methods, specifically including a face-swiping payment method, a fingerprint payment method, and a password payment method.
  • the terminal device can display the service page 101e according to the user's selection operation for the payment method in the terminal page 100e (the selection operation can be the above-mentioned biological settlement operation), and the service page 101e can display the target photographed by the camera.
  • a cartoon image corresponding to the real image of the object.
  • the terminal device can also authenticate the target object based on the real image of the target object captured by the camera, or the terminal device can send the real image of the target object captured by the camera to the server in the background, so that the server can base the real image on the real image.
  • the service page 101e can be displayed to display the terminal page 102e, and the terminal page 102e can include the avatar 104e of the user account of the target object.
  • the terminal device can request the background of the settlement software to use the settlement account (which may be the default settlement account) associated with the target object to pay for the target order according to the confirmation operation (such as a click operation) of the target object on the "Confirm Payment" button in the terminal page 102e.
  • the terminal device can change from the display terminal page 102e to the display terminal page 103e according to the prompt information, and the terminal page 103e can prompt the target object that it has settled the target order. Success (ie, payment is successful).
  • the service page may not display the real photographed target object, but display the cartoon information of the photographed target object.
  • the psychological impact on the user caused by the biological information can reduce the psychological discomfort of the user, and can increase the user's interest in using biological information to settle the target order, and improve the utilization rate of related technologies for order settlement through biological information.
  • the cartoon information corresponding to the biological information of the target object is displayed on the service page, which also improves the security of the biological information of the target object.
  • FIG. 7 is a schematic flowchart of an information processing method provided by the present application.
  • the method described in this embodiment of the present application is the same method as the method described in the above-mentioned embodiment corresponding to FIG. 3 , except that the above-mentioned embodiment corresponding to FIG. 3 focuses on describing some content that the user can perceive, while the embodiment of this application focuses on describing some content that can be perceived by the user.
  • the execution body in the embodiment of the present application may be the execution body in the embodiment corresponding to FIG.
  • the method may include:
  • step S201 in response to the biological settlement operation for the target order, a service page is displayed, and biological information of the target object is collected.
  • the collection of biological information of the target object is described by taking the collection of face information of the target object as an example. It can be understood that in addition to the face information, other biological information (such as pupil information or palm print information, etc.). Therefore, after detecting that the target object triggers the biological settlement operation for the target order, the terminal device can call the camera to shoot the face of the target object in front of the camera, and obtain L face video frames of the target object, where L is the face obtained by shooting the target object The total number of video frames, L is a positive integer, and the specific value of L is determined according to the actual application scenario. The L face video frames can be used as the biological information of the target object.
  • Step S202 performing identity verification on the target object based on the biological information, and performing cartoon conversion on the biological information to obtain cartoon information corresponding to the biological information.
  • the process of performing identity verification on the target object based on biological information and the process of converting the biological information into cartoons to obtain cartoon information may be processes that are executed independently and in parallel.
  • the process of authenticating the target object through biological information may be:
  • the terminal device may select a face video frame from the above-mentioned L face video frames, use the selected face video frame as a target video frame, and perform identity verification on the target object according to the target video frame.
  • the optimal frame may be selected from the L face video frames as the target video frame, and the optimal frame may be the video frame with the highest definition among the L face video frames, or may be one of the L face video frames. The most complete video frame with face information, etc.
  • the manner in which the terminal device authenticates the target object based on the target video frame may be:
  • the terminal device When the terminal device collects the target video frame, it can also collect the depth video frame corresponding to the target video frame, the target video frame is a plane image, the target video frame includes the plane information of the face of the target object, and the depth video frame A frame may be understood as a stereoscopic image, which includes depth information of the face of the target object (which may be referred to as face depth information), and may be understood as including stereoscopic information of the face of the target object.
  • the target video frame is a plane image
  • the target video frame includes the plane information of the face of the target object
  • the depth video frame A frame may be understood as a stereoscopic image, which includes depth information of the face of the target object (which may be referred to as face depth information), and may be understood as including stereoscopic information of the face of the target object.
  • the terminal device can obtain the facial features plane information of the target object from the target video frame, wherein the facial features can refer to the two eyes, nose and two corners of the mouth of the target object, and the facial feature plane information can include the two eyes and nose of the target object. , the distance between the two corners of the mouth, etc.
  • the terminal device can obtain the facial features depth information of the target object from the depth video frame corresponding to the target video frame.
  • the facial features plane information and facial feature depth information of the target object obtained by the terminal device can be used as the five-point information of the target object, and the five-point information is sent to the background of the settlement software, and the background of the settlement software can compare the five-point information of the target object with The five-point information of all users stored in the database is compared to confirm the identity of the target object.
  • the user who belongs to the five-point information stored in the database that is very similar to the five-point information of the target object can be considered as the target object.
  • the background of the settlement software can return to the terminal device (eg, to the settlement software in the terminal device) a prompt message that the identity verification of the target object is successful.
  • the above-mentioned five-point information being extremely similar may specifically be understood as the similarity between two five-point pieces of information exceeding a preset threshold.
  • the biological information is taken as an example of the above-mentioned L face video frames for description.
  • the terminal device needs to perform cartoon conversion, it can pull and download the cartoon conversion model from the background (eg, the background of the settlement software).
  • the cartoon conversion model can be a pre-trained model for converting biological information into cartoon information. Therefore, the terminal device can input the L face video frames into the cartoon conversion model, and extract the partial face images included in each input face video frame (that is, only the target object that is captured) is extracted through the cartoon conversion model.
  • the cartoon face image corresponding to the partial face image included in the frame is the cartoon information corresponding to the biological information of the target object.
  • cartoon conversion is only performed on the captured face of the target object (which can be understood as the head).
  • the terminal device obtains the above-mentioned L face video frames in sequence, the L face video frames are successively obtained at different times, so the L face video frames may also be obtained at different times.
  • the cartoon conversion model is input successively. Each time the terminal device obtains a face video frame, the face video frame can be input into the cartoon conversion model, and only one face video frame can be input at a time. Therefore, the face video frame can be sequentially converted by L times Frame input cartoon conversion model, get the cartoon face image corresponding to each face video frame.
  • the above-mentioned L face video frames when the above-mentioned L face video frames are obtained, it is possible to capture part of the body (such as the neck and shoulders) of the target object. Therefore, when performing cartoon conversion on the L face video frames, you can It not only converts the captured face of the target object (such as the face in the above-mentioned partial image of the face), but also converts all parts of the target object captured in the face video frame (such as the head, neck, etc.) and shoulder) to perform cartoon conversion to obtain a corresponding cartoon image, and then the cartoon image can be used as the cartoon information corresponding to the biological information of the target object.
  • the target object such as the face in the above-mentioned partial image of the face
  • the cartoon image can be used as the cartoon information corresponding to the biological information of the target object.
  • the captured target object when performing cartoon conversion on L face video frames, not only the captured target object can be converted, but also the environment where the captured target object is located (that is, the target object in the face video frame. background) also perform cartoon conversion to obtain a corresponding cartoon image, and then the cartoon image can be used as the cartoon information corresponding to the biological information of the target object.
  • the above-mentioned cartoon conversion model can be obtained by terminal equipment training, and can also be obtained by background training of settlement software.
  • the above-mentioned cartoon conversion model obtained by terminal equipment training is used as an example to illustrate the training process of the above-mentioned cartoon conversion model.
  • the terminal device can obtain the initial cartoon conversion model, which is a Generative Adversarial Network (GAN, Generative Adversarial Networks), which is an unsupervised model.
  • the initial cartoon transformation model may include a cartoon generator (which may be referred to as a generator) and a cartoon discriminator (which may be referred to as a discriminator).
  • the training purpose of the generator is to adjust its own model parameters to generate an image with a cartoon texture (that is, cartoon texture) closest to the input image, so as to deceive the discriminator and let the discriminator identify the generated cartoon texture.
  • the image is a real image (that is, the real image of the target object), and the training purpose of the discriminator is to adjust its own model parameters to discriminate as accurately as possible that the comic-textured image generated by the generator is not real. image.
  • a sample face image can be input into the cartoon generator, the sample face image can be a real image obtained by photographing the face of a sample user, and a sample cartoon corresponding to the sample face image can be generated in the cartoon generator face image, and then the sample cartoon face image generated by the cartoon generator can be input into the cartoon discriminator, and the cartoon discriminator can judge the probability that the sample cartoon face image belongs to the cartoon type image, which is called the cartoon probability in this application.
  • the cartoon probability can also represent the probability that the sample cartoon face image is a cartoon-like image.
  • the model parameters of the cartoon generator and the model parameters of the cartoon discriminator can be modified through the cartoon probability obtained by the cartoon discriminator, and the revised model parameters of the cartoon generator and the revised model parameters of the cartoon discriminator can be obtained.
  • the above-mentioned sample face images can have several, and through the several sample face images, the model parameters of the cartoon generator and the model parameters of the cartoon discriminator can be iteratively revised with the same principle as above.
  • the cartoon generator at this time can be used as the above cartoon transformation model.
  • the model training standard may refer to the number of times of model parameter revision (which can be understood as the number of times of training) reaching a certain threshold (which can be set according to the actual application scenario), that is, when the number of model parameter revisions is greater than the certain threshold times , indicating that the model obtained after the model parameter correction satisfies the model training standard; or, the model training standard may mean that the corrected model parameters reach the convergence state, that is, when the corrected model parameters reach the convergence state, it indicates that after the model parameters are corrected The resulting model satisfies the model training criteria.
  • the specific model training standard can also be determined according to the actual application scenario, which is not limited.
  • the model training process can be divided into two stages.
  • Two stages including the first stage training process and the second stage training process.
  • the above cartoon probabilities include the cartoon probabilities of the two stages.
  • the cartoon probability obtained in the first stage of training can be called the first stage cartoon probability
  • the cartoon probability obtained in the second stage of training can be called the first stage.
  • the two-stage cartoon probability, the sample face images used in the first-stage training process and the sample face images used in the second-stage training process can be the same or different.
  • a sample face image can correspond to a cartoon probability.
  • the model parameters of the cartoon discriminator can be kept unchanged, and the model parameters of the cartoon generator can be modified according to the obtained first-stage cartoon probability. Make the cartoon probability in the first stage reach 50%. At this time, it is considered that the cartoon discriminator cannot distinguish between cartoon images and real images, which belongs to the state of guessing.
  • the revised model parameters of the cartoon generator can be obtained.
  • the revised model parameters of the cartoon generator (that is, the revised model parameters in the first-stage training process) can be kept unchanged.
  • the cartoon probability of the stage corrects the model parameters of the cartoon discriminator.
  • the goal of the correction can be to make the cartoon probability of the first stage reach 100%, that is, the cartoon discriminator can distinguish cartoon images to the maximum extent.
  • the revised cartoon discriminator can be obtained. model parameters.
  • the initial cartoon transformation model in the training process of the first stage, can be iteratively trained through several sample face images, and the training process of the second stage can also iteratively train the initial cartoon transformation model through several sample face images.
  • the subsequent training of the cartoon transformation model is to continue the training on the basis of the previous training for the initial cartoon transformation model, and it can be understood that performing one round of the first stage training process and one round of the second stage training process
  • One round of training of the conversion model can also perform several rounds of training on the initial cartoon conversion model, that is, the first-stage training process and the second-stage training process can be repeatedly performed iteratively until the initial conversion model (including When the cartoon generator and the cartoon discriminator obtained after the model parameters are modified reach the above-mentioned model training standard, the cartoon generator at this time can be used as the above-mentioned cartoon conversion model.
  • the initial cartoon conversion model 101f includes a cartoon generator 102f and a cartoon discriminator 103f.
  • a sample image (such as the above-mentioned sample face image) can be input into the cartoon generator 102f, and a cartoon image corresponding to the sample image can be generated by the cartoon generator 102f.
  • the cartoon image can be input into the cartoon discriminator 103f, and the cartoon probability for the cartoon image can be obtained through the cartoon discriminator 103f.
  • the cartoon probability is the first-stage cartoon probability
  • the cartoon probability can be back-propagated to the cartoon generator 102f, and the model parameters of the cartoon generator 102f can be corrected by the cartoon probability.
  • the cartoon probability is the second cartoon probability If the stage cartoon probability is determined, the cartoon probability can be back-propagated to the cartoon discriminator 103f, and the model parameters of the cartoon discriminator 103f can be corrected by the cartoon probability.
  • the cartoon generator 102f whose model parameters are corrected may be used as the final cartoon generator 104f, and the cartoon discriminator 103f whose model parameters are corrected may be used as the final cartoon discriminator 105f.
  • the trained initial cartoon conversion model 100f can be obtained, and the cartoon generator 104f in the trained initial cartoon conversion model 100f can be used as the above-mentioned cartoon conversion model.
  • FIG. 9 is a schematic diagram of a model training scenario provided by this application.
  • the first-stage training and second-stage training can be regarded as a principle or method of model training.
  • the first-stage training is to fix the model parameters of the cartoon discriminator, and correct the model of the cartoon generator through the cartoon probability.
  • the second stage of training is to fix the model parameters of the cartoon generator, and modify the model parameters of the cartoon discriminator through the cartoon probability.
  • a first-stage training and a second-stage training can be performed as one round of training for the initial cartoon conversion model, and n rounds of training can be performed on the initial cartoon conversion model (such as the first round of training here ⁇ The nth round of training), the specific value of n is determined according to the actual application scenario. After n rounds of training on the initial cartoon conversion model, it can be considered that the training of the initial cartoon conversion model is completed at this time, and the cartoon generator at this time can be used as the above-mentioned cartoon conversion model.
  • the efficiency of the algorithms involved in the initial cartoon conversion model can also be improved through a convolutional neural network, thereby improving the training efficiency, and in practical application of cartoon conversion.
  • the efficiency of cartoon conversion model improve the efficiency of cartoon conversion model to generate cartoon images.
  • Step S203 in the process of performing identity verification on the target object based on the biological information, displaying the cartoon information on the service page.
  • the terminal device in the process of authenticating the target object based on the biological information, can display the cartoon information corresponding to the biological information of the target object on the service page, because the L face video frames of the target object are shot successively at different times. Therefore, when performing cartoon conversion on L face video frames, the cartoon images corresponding to each face video frame are also converted in sequence to obtain the cartoon image corresponding to each face video frame.
  • Time synchronization (which can be understood as real-time) displays the cartoon image corresponding to the face video frame on the service page. Therefore, when the terminal device performs cartoon conversion on each face video frame to obtain the cartoon image corresponding to the face video frame , the cartoon image corresponding to the face video frame can be displayed on the service page. That is, the cartoon images corresponding to each of the L face video frames can also be displayed in sequence on the service page, so as to achieve the purpose of synchronously displaying the cartoon images corresponding to the face video frames on the service page when the face video frames are captured.
  • Step S204 displaying the biological settlement information of the target order.
  • This application displays the service page according to the biological settlement operation for the target order, and collects the biological information of the target object; in the process of authenticating the target object based on the biological information, the cartoon corresponding to the biological information of the target object is displayed on the service page.
  • Information displays biometric billing information for the target order.
  • the method proposed in the present application can display the cartoon information corresponding to the biological information of the target object on the service page, which improves the security of the biological information of the target object, and does not directly display the biological information of the target object.
  • FIG. 10 is a schematic flowchart of an order settlement provided by the present application.
  • application startup may refer to startup of settlement software.
  • the settlement software can pull the cartoon conversion model 108h from the background server 107h.
  • blocks 101h to 102h when a transaction is started in the activated settlement software (for example, when a biological settlement operation is detected), it is possible to prepare to identify the user in front of the camera (the camera of the terminal device where the settlement software is located) (for example, to The user's identity is verified and identified), and the camera is activated at this time (eg, block 103h).
  • an identification frame may be obtained through a camera, and the identification frame may be a video frame obtained by photographing the user through a camera (eg, the above-mentioned face video frame of the target object).
  • the terminal device may input the recognized frame into the cartoon conversion model 108h, and generate a cartoon frame 109h corresponding to the recognized frame (such as the cartoon video frame corresponding to the above-mentioned video frame) through the cartoon conversion model 108h.
  • the terminal device can play (ie display) the cartoon frame 109h on the service page through the player 110h.
  • the terminal device After acquiring the identification frame 104h, there can be multiple identification frames 104h, and the terminal device can select the optimal frame 105h (such as the above-mentioned target video frame) from the plurality of identification frames 104h, and then obtain the target object through the optimal frame
  • the five-point information 106h (which may include the facial features plane information and the facial features depth information of the target object), the terminal device can send the five-point information 106h to the background server 107h, and request the background server 107h to pass the five-point information 106h to the target object. identity verification.
  • the background server 107h can compare the five-point information 106h with the five-point information of the existing users in the settlement software in the database, so as to judge whether the target object is among the existing users. and after determining the user identity of the target object, the determined user identity of the target object can be returned to the terminal device (for example, an avatar that can represent the user identity of the target object is returned, and the avatar is the user of the target object. account avatar), the terminal device can display the settlement confirmation information including the user identity on the terminal page, and after detecting the confirmation operation for the settlement confirmation information, it can request the background server 107h to use the settlement account associated with the target object Settle the target order of the target object.
  • the terminal device for example, an avatar that can represent the user identity of the target object is returned, and the avatar is the user of the target object. account avatar
  • the terminal device can display the settlement confirmation information including the user identity on the terminal page, and after detecting the confirmation operation for the settlement confirmation information, it can request the background server 107h to use the settlement account associated with the
  • FIG. 11 is a schematic structural diagram of an information processing apparatus provided by the present application.
  • the information processing apparatus may be a computer program (including program code) running in a computer device, for example, the information processing apparatus is an application software, and the information processing apparatus may be used to execute corresponding steps in the methods provided in the embodiments of the present application .
  • the information processing apparatus 1 may include: a first information collection module 11 , a first information display module 12 and a first settlement module 13 ;
  • the first information collection module 11 is used to display the service page in response to the biological settlement operation for the target order, and collect the biological information of the target object;
  • the biological settlement operation is used to trigger the identity verification of the target object based on the biological information, and according to the identity Verify the result and settle the target order;
  • the first information display module 12 is used to display the cartoon information corresponding to the biological information of the target object in the service page during the process of performing the identity verification on the target object based on the biological information;
  • the first settlement module 13 is used to display the biological settlement information of the target order; the biological settlement information is determined at least according to the identity verification result for the target object.
  • the biological information of the target object includes the i-th face video frame and the j-th face video frame obtained by shooting the target object, where i is less than j, and both i and j are positive integers; the i-th face video frame and the jth frame human face video frame respectively have the face display attribute of the target object;
  • the cartoon information corresponding to the biological information of the target object includes the ith frame human face video frame corresponding cartoon human face video frame and the jth frame human face video frame Corresponding cartoon face video frame;
  • the first information display module 12 is specifically used for:
  • the cartoon corresponding to the jth frame of face video frame is displayed on the service page according to the face display attributes possessed by the jth frame of face video frame Face video frame.
  • the biological information of the target object includes a face image of the target object;
  • the cartoon information corresponding to the biological information of the target object includes a cartoon face image corresponding to the face image of the target object;
  • the first information display module 12 is specifically used for:
  • the face display attributes include at least one of the following: a face gesture attribute, a face expression attribute, and a face accessory attribute.
  • the biological information of the target object includes the palmprint image of the target object;
  • the cartoon information corresponding to the biological information of the target object includes the cartoon palmprint image corresponding to the palmprint image of the target object;
  • the first information display module 12 is specifically used for:
  • the palmprint display attribute includes at least one of the following: palmprint posture attribute and palmprint accessory attribute.
  • the biological information of the target object includes a pupil image of the target object
  • the cartoon information corresponding to the biological information of the target object includes a cartoon pupil image corresponding to the pupil image of the target object
  • the first information display module 12 is specifically used for:
  • the pupil display attribute includes at least one of the following: pupil opening and closing attribute, pupil accessory attribute.
  • the first information display module 12 is also used for:
  • the background selection list includes M kinds of background information; M is a positive integer;
  • the selected background information is determined as the target background information of the cartoon information
  • the first information display module 12 is specifically used for:
  • the biological settlement information when the identity verification of the target object based on the biological information succeeds, includes settlement success information; when the identity verification of the target object based on the biological information fails, the biological settlement information includes settlement failure information.
  • the biological settlement information includes settlement confirmation information;
  • the first settlement module 13 is specifically used for:
  • the settlement confirmation information will be displayed; the settlement confirmation information is used to support settlement for the target order;
  • the above-mentioned device 1 further includes: a settlement confirmation module, which is used for:
  • the target order is settled according to the confirmation operation for the settlement confirmation information.
  • the above settlement confirmation module is specifically used for:
  • the account selection list includes N settlement accounts associated with the target object, and N is a positive integer;
  • the selected settlement account is determined as the target settlement account
  • the steps involved in the information processing method shown in FIG. 3 can be performed by each module in the information processing apparatus 1 shown in FIG. 11 .
  • step S101 shown in FIG. 3 can be executed by the first information collection module 11 in FIG. 11
  • step S102 shown in FIG. 3 can be executed by the first information display module 12 in FIG. 11
  • the illustrated step S103 can be performed by the first settlement module 13 in FIG. 11 .
  • FIG. 12 is a schematic structural diagram of an information processing apparatus provided by the present application.
  • the information processing apparatus may be a computer program (including program code) running in a computer device, for example, the information processing apparatus is an application software, and the information processing apparatus may be used to execute corresponding steps in the methods provided in the embodiments of the present application .
  • the information processing apparatus 2 may include: a second information collection module 21 , an information conversion module 22 , a second information display module 23 and a second settlement module 24 ;
  • the second information collection module 21 is used to display the service page in response to the biological settlement operation for the target order, and collect the biological information of the target object;
  • the biological settlement operation is used to trigger the identity verification of the target object based on the biological information, and according to the identity Verify the result and settle the target order;
  • the information conversion module 22 is used for performing identity verification on the target object based on the biological information, and performing cartoon conversion on the biological information to obtain cartoon information corresponding to the biological information;
  • the second information display module 23 is used to display the cartoon information in the service page during the process of performing the identity verification on the target object based on the biological information;
  • the second settlement module 24 is configured to display the biological settlement information of the target order; the biological settlement information is determined at least according to the identity verification result for the target object.
  • the biological information includes L face video frames of the target object; L is a positive integer;
  • the information conversion module 22 is specifically used for:
  • the information conversion module 22 is specifically used for:
  • the depth video frame includes the face depth information of the target object
  • the target object is authenticated according to the facial features plane information and facial features depth information.
  • the information conversion module 22 is specifically used for:
  • the cartoon face images corresponding to the partial face images included in each face video frame are respectively generated;
  • the cartoon face image corresponding to the partial face image included in each face video frame is determined as cartoon information.
  • the above-mentioned device 2 also includes a model training module, which is used for:
  • the initial cartoon conversion model includes a cartoon generator and a cartoon discriminator
  • the cartoon generator is determined as the cartoon transformation model.
  • the cartoon probability includes the first-stage cartoon probability and the second-stage cartoon probability; the above model training module is specifically used for:
  • the model parameters of the cartoon discriminator are kept unchanged, and the model parameters of the cartoon generator are modified according to the first-stage cartoon probability to obtain the revised model parameters of the cartoon generator;
  • the steps involved in the information processing method shown in FIG. 7 may be performed by each module in the information processing apparatus 1 shown in FIG. 12 .
  • step S201 shown in FIG. 7 can be performed by the second information collection module 21 shown in FIG. 12
  • step S202 shown in FIG. 7 can be performed by the information conversion module 22 shown in FIG.
  • Step S203 may be performed by the second information display module 23 in FIG. 12
  • step S204 shown in FIG. 7 may be performed by the second settlement module 24 in FIG. 11 .
  • This application displays the service page according to the biological settlement operation for the target order, and collects the biological information of the target object; in the process of authenticating the target object based on the biological information, the cartoon corresponding to the biological information of the target object is displayed on the service page.
  • Information displays biometric billing information for the target order.
  • the device proposed in this application can display the cartoon information corresponding to the biological information of the target object on the service page, which improves the security of the biological information of the target object, and does not directly display the biological information of the target object.
  • each module in the information processing apparatus 1 shown in FIG. 11 and the information processing apparatus 2 shown in FIG. 12 may be respectively or all combined into one or several units to form, or one of them may be
  • the unit(s) can also be split into multiple sub-units with smaller functions, which can realize the same operation without affecting the realization of the technical effects of the embodiments of the present application.
  • the above modules are divided based on logical functions.
  • the function of one module may also be implemented by multiple units, or the functions of multiple modules may be implemented by one unit.
  • the information processing apparatus 1 and the information processing apparatus 2 may also include other units.
  • these functions may also be implemented with the assistance of other units, and may be implemented by cooperation of multiple units.
  • a general-purpose computer device such as a computer
  • a computer program (including program code) capable of executing the steps involved in the corresponding method as shown in FIG. 3 or FIG. 7 to construct the information processing apparatus 1 as shown in FIG. 11 or the information processing apparatus 2 as shown in FIG. 12 , and to implement the information processing method of the embodiment of the present application.
  • the above-mentioned computer program can be recorded on, for example, a computer-readable recording medium, loaded in the above-mentioned computing device via the computer-readable recording medium, and executed therein.
  • the computer device 1000 may include: a processor 1001 , a network interface 1004 and a memory 1005 , in addition, the computer device 1000 may further include: a user interface 1003 , and at least one communication bus 1002 .
  • the communication bus 1002 is used to realize the connection and communication between these components.
  • the user interface 1003 may include a display screen (Display) and a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may include a standard wired interface and a wireless interface (eg, a WI-FI interface).
  • the memory 1005 may be high-speed RAM memory or non-volatile memory, such as at least one disk memory.
  • the memory 1005 may also be at least one storage device located away from the aforementioned processor 1001 .
  • the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a device control application program.
  • the network interface 1004 can provide a network communication function; the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 A program to implement the information processing method provided by the embodiments of the present application.
  • the computer device 1000 described in the embodiment of the present application can execute the description of the above information processing method in the embodiment corresponding to FIG. 3 or FIG.
  • the description of 1 and the description of the above-mentioned information processing apparatus 2 in the embodiment corresponding to FIG. 12 above will not be repeated here.
  • the description of the beneficial effects of using the same method will not be repeated.
  • the present application also provides a computer-readable storage medium, and the computer-readable storage medium stores the computer programs executed by the information processing apparatus 1 and the information processing apparatus 2 mentioned above, and
  • the computer program includes program instructions, and when the processor executes the program instructions, it can execute the description of the information processing method in the embodiment corresponding to FIG. 3 or FIG. 7 , and therefore will not be repeated here.
  • the description of the beneficial effects of using the same method will not be repeated.
  • program instructions may be deployed and executed on one computer device, or on multiple computer devices located at one site, or alternatively, distributed across multiple sites and interconnected by a communication network.
  • Executed on a blockchain multiple computer devices distributed in multiple locations and interconnected by a communication network can form a blockchain network.
  • the above-mentioned computer-readable storage medium may be the information processing apparatus provided in any of the foregoing embodiments or an internal storage unit of the above-mentioned computer device, such as a hard disk or a memory of the computer device.
  • the computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (smart media card, SMC), a secure digital (secure digital, SD) card equipped on the computer device, Flash card (flash card), etc.
  • the computer-readable storage medium may also include both an internal storage unit of the computer device and an external storage device.
  • the computer-readable storage medium is used to store the computer program and other programs and data required by the computer device.
  • the computer-readable storage medium can also be used to temporarily store data that has been or will be output.
  • the present application provides a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium.
  • the processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the description of the above-mentioned information processing method in the corresponding embodiment of FIG. 3 or FIG. 7. Therefore, here No further description will be given. In addition, the description of the beneficial effects of using the same method will not be repeated.
  • the description of the beneficial effects of using the same method will not be repeated.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • Finance (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

提供了一种信息处理方法、装置、计算机设备和存储介质,方法包括:根据针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示目标对象的生物信息对应的卡通信息;显示目标订单的生物结算信息。

Description

信息处理方法、装置、计算机设备和存储介质
本申请要求于2021年04月23日提交中国专利局、申请号为2021104419353、申请名称为“信息处理方法、装置、计算机设备和存储介质”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
本申请涉及计算机技术领域,尤其涉及信息处理技术。
背景技术
随着计算机网络的不断发展,各种支付方式层出不穷,例如,目前比较普遍的通过识别人脸、指纹等生物特征来实现支付操作的方式。
相关技术中,用户在通过支付设备对订单进行人脸支付时,支付设备会采集用户的人脸信息,进而在设备页面中实时显示所拍摄的用户的人脸,此时,用户也可以在支付设备上查看到自己的人脸。在该种场景中,直接显示在设备页面中的用户人脸很容易被周围的用户或者其它设备窃取,难以保证用户的人脸信息的安全性。
发明内容
本申请提供了一种信息处理方法、装置、计算机设备和存储介质,可提高目标对象的生物信息的安全性。
本申请一方面提供了一种信息处理方法,由计算机设备执行,该方法包括:
响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;生物结算操作用于触发基于生物信息对目标对象进行身份验证,并根据身份验证结果进行针对目标订单的结算;
在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示目标对象的生物信息对应的卡通信息;
显示目标订单的生物结算信息;生物结算信息至少根据对于目标对象的身份验证结果确定。
本申请一方面提供了一种信息处理方法,由计算机设备执行,该方法包括:
响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;生物结算操作用于触发基于生物信息对目标对象进行身份验证,并根据身份验证结果进行针对目标订单的结算;
基于生物信息对目标对象进行身份验证,并对生物信息进行卡通转换,得到生物信息对应的卡通信息;
在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示卡通信息;
显示目标订单的生物结算信息;生物结算信息至少根据对于目标对象的身份验证结果确定。
本申请一方面提供了一种信息处理装置,该装置包括:
第一信息采集模块,用于响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;生物结算操作用于触发基于生物信息对目标对象进行身份验证,并根据身份验证结果进行针对目标订单的结算;
第一信息显示模块,用于在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示目标对象的生物信息对应的卡通信息;
第一结算模块,用于显示目标订单的生物结算信息;生物结算信息至少根据对于目标对象的身份验证结果确定。
本申请一方面提供了一种信息处理装置,该装置包括:
第二信息采集模块,用于响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;生物结算操作用于触发基于生物信息对目标对象进行身份验证,并根据身份验证结果进行针对目标订单的结算;
信息转换模块,用于基于生物信息对目标对象进行身份验证,并对生物信息进行卡通转换,得到生物信息对应的卡通信息;
第二信息显示模块,用于在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示卡通信息;
第二结算模块,用于显示目标订单的生物结算信息;生物结算信息至少根据对于目标对象的身份验证结果确定。
本申请一方面提供了一种计算机设备,包括存储器和处理器,存储器存储有计算机程序,计算机程序被处理器执行时,使得处理器执行本申请中一方面中的方法。
本申请一方面提供了一种计算机可读存储介质,该计算机可读存储介质存储有计算机程序,该计算机程序包括程序指令,该程序指令被处理器执行时使该处理器执行上述一方面中的方法。
根据本申请的一个方面,提供了一种计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该计算机设备执行上述一方面等各种可选方式中提供的方法。
本申请根据针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示目标对象的生物信息对应的卡通信息;显示目标订单的生物结算信息。由此可见,本申请提出的方法可以在服务页面显示目标对象的生物信息对应的卡通信息,提高了目标对象的生物信息的安全性,并且,不直接显示目标对象的生物信息,也可以减少因直接显示目标对象的生物信息而给 目标对象带来的视觉冲击,从而提高目标对象使用生物信息对目标订单进行结算的兴趣。
附图说明
图1是本申请实施例提供的一种网络架构的结构示意图;
图2是本申请提供的一种刷脸支付的场景示意图;
图3是本申请提供的一种信息处理方法的流程示意图;
图4是本申请提供的一种服务页面的页面示意图;
图5是本申请提供的一种选取背景信息的页面示意图;
图6是本申请提供的一种订单结算的页面示意图;
图7是本申请提供的一种信息处理方法的流程示意图;
图8是本申请提供的一种模型训练的场景示意图;
图9为本申请提供的一种模型训练的场景示意图;
图10是本申请提供的一种订单结算的流程示意图;
图11是本申请提供的一种信息处理装置的结构示意图;
图12是本申请提供的一种信息处理装置的结构示意图;
图13是本申请提供的一种计算机设备的结构示意图。
具体实施方式
下面将结合本申请中的附图,对本申请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申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
请参见图1,图1是本申请实施例提供的一种网络架构的结构示意图。如图1所示,网络架构可以包括服务器200和终端设备集群,终端设备集群可以包括一个或者多个终端设备,这里将不对终端设备的数量进行限制。如图1所示,多个终端设备具体可以包括终端设备100a、终端设备101a、终端设备102a、…、终端设备103a;如图1所示,终端设备100a、终端设备101a、终端设备102a、…、终端设备103a均可以与服务器200进行网络连接,以便每个终端设备通过网络连接与服务器200之间进行数据交互。
图1所示的服务器200可以是独立的物理服务器,也可以是多个物理服务器构成的服务器集群或者分布式系统,还可以是提供云服务、云数据库、云计算、云函数、云存储、网络服务、云通信、中间件服务、域名服务、安全服务、CDN、以及大数据和人工智能平台等基础云计算服务的云服务器。
终端设备100a、终端设备101a、终端设备102a、…、终端设备103a均可以是面向用户的终端设备,例如可以是智能手机、平板电脑、笔记本电脑、桌上型电脑、智能电视、青蛙设备(部署在线下、支持用户通过刷脸等操作完成订单支付的设备)等智能终端。用户可以通过上述终端设备请求服务器 200协同完成对于订单的刷脸支付,并且,在刷脸支付的过程中,终端设备在其显示界面上将显示用户的卡通图像,以利用该卡通图像替代实际采集的人脸图像。其中,该订单可以是目标用户通过购物应用(可以是下述购物平台)产生的商品订单,刷脸支付可以是在支付应用(等同于下述结算软件)中完成的,购物应用和支付应用可以是同一个应用,也可以是不同的应用,若购物应用与支付应用是不同的应用,则可以在通过购物应用对订单进行支付时调用支付应用来支付,服务器200可以是支付应用的后台服务器。下面以终端设备100a与服务器200之间进行通信为例,进行本申请实施例的具体描述。
请一并参见图2,图2是本申请提供的一种刷脸支付的场景示意图。如图2所示,终端设备100a可以响应用户通过支付应用触发的针对订单的刷脸支付操作,打开摄像头,采集用户的人脸视频帧(即拍摄的包括用户的人脸的图像),并且,终端设备100a可以向服务器200拉取卡通转换模型101b,该卡通转换模型101b可以将所拍摄的包括用户真实人脸的图像转换为卡通图像,该卡通转换模型101b的具体训练过程可以参见下述图7对应实施例中的描述。
进而,终端设备100a可以将采集到的用户的人脸视频帧输入卡通转换模型101b,通过该卡通转换模型101b可以生成用户的人脸视频帧对应的卡通视频帧102b(即卡通图像)。与此同时,终端设备100a还可以基于采集到的人脸视频帧对用户进行身份验证(如框100b),并且,终端设备100a在对用户进行身份验证的过程中,可以在终端页面中显示用户的卡通视频帧(如框103b)。在对用户进行身份验证的过程中,终端设备100a可以联合服务器200一起对用户进行身份验证,从而得到针对用户的身份验证结果104b,对用户进行身份验证的具体过程可以参见下述图7对应实施例中的描述。该身份验证结果104b可以表征对用户身份验证失败,或者表征对用户身份验证成功。
通过上述身份验证结果104b,终端设备可以得到针对用户的订单的支付结果105b,该支付结果105b可以表征用户的订单支付失败,或者可以表征用户的订单支付成功。具体的,若身份验证结果104b表征对用户的身份验证成功,则服务器200可以通过与用户相关联的支付账户(如用户通过上述支付应用注册的账户)对用户的订单进行支付;若得到对用户的订单支付成功的提示信息,服务器200可以将该对用户的订单支付成功的提示信息发送给终端设备100a,终端设备100a即可根据该对用户的订单支付成功的提示信息得到上述支付结果105b,此时的支付结果表征用户的订单支付成功的;若得到对用户的订单支付失败的提示信息,服务器200可以将该对用户的订单支付失败的提示信息发送给终端设备100a,终端设备100a即可根据该对用户的订单支付失败的提示信息得到上述支付结果105b,此时的支付结果表征用户的订单支付失败。相反,若身份验证结果104b表征对用户的身份验证失败, 则服务器200不能对用户的订单进行支付,此时可以得到对用户的订单支付失败的提示信息,服务器200可以将该对用户的订单支付失败的提示信息发送给终端设备100a,终端设备100a即可根据该对用户的订单支付失败的提示信息得到上述支付结果105b,此时的支付结果表征用户的订单支付失败。
通过本申请提供的方法,在用户的刷脸支付过程中,可以不显示用户的真实人脸,而显示与用户的真实人脸相似的卡通人脸,从而减少所显示的真实人脸对用户带来的视觉冲突感,增强用户对刷脸支付的兴趣。并且,通过显示卡通人脸,也可以提高用户的真实人脸的安全性。
请参见图3,图3是本申请提供的一种信息处理方法的流程示意图。本申请实施例中的执行主体可以是一个计算机设备、或者多个计算机设备构成的计算机设备集群。该计算机设备可以是服务器,也可以终端设备。因此,本申请实施例中的执行主体可以是服务器,也可以是终端设备,还可以由服务器和终端设备协同执行。此处,以本申请的执行主体为终端设备为例进行说明。如图3所示,该方法可以包括:
步骤S101,响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息。
本申请中,结算可以指支付,目标订单可以是任意一个需要支付结算的订单,例如目标订单可以是在购物平台中针对选购的商品的支付订单,又例如目标订单可以是针对在线下商店中选购的商品的线上支付订单。而生物结算操作就是对目标订单进行支付结算的操作,具体的,生物结算操作是指基于触发支付目标订单的目标对象的生物信息来对该目标对象进行身份验证,进而根据身份验证结果进行针对目标订单的结算支付的操作。目标订单可以是目标对象的订单,目标对象可以是任意用户,目标对象的生物信息是指任意可以用于对目标对象进行身份验证的生物信息,例如,目标对象的人脸信息、瞳孔信息、掌纹信息或者指纹信息等。
因此,终端设备可以根据目标对象针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息:该服务页面可以理解为是一个拍摄页面,在该服务页面中可以显示目标对象的生物信息对应的卡通信息,可以参见下述步骤S102。
可选的,终端设备可以在终端页面上显示结算方式列表,该结算方式列表中可以包括一种或者多种结算方式供目标对象选择,例如该结算方式列表中可以包括人脸结算方式、瞳孔结算方式、指纹结算方式以及掌纹结算方式等。终端设备可以根据目标对象针对该结算方式列表中的结算方式的选择操作,来显示服务页面,并采集目标对象选择的结算方式对应的生物信息。目标对象针对结算方式列表中的结算方式的选择操作即可以是上述生物结算操作。若目标对象选择的结算方式为人脸结算方式,则采集的目标对象的生物信息可以是目标对象的人脸信息;若目标对象选择的结算方式为瞳孔结算方 式,则采集的目标对象的生物信息可以是目标对象的瞳孔信息;若目标对象选择的结算方式为指纹结算方式,则采集的目标对象的生物信息可以是目标对象的指纹信息;若目标对象选择的结算方式为掌纹结算方式,则采集的目标对象的生物信息可以是目标对象的掌纹信息;等等。
步骤S102,在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示目标对象的生物信息对应的卡通信息。
本申请中,终端设备可以基于采集到的目标对象的生物信息对目标对象进行身份验证,或者,终端设备可以将采集到的目标对象的生物信息发送给后台的服务器,以使该服务器基于该生物信息对目标对象进行身份验证。在基于采集到的生物信息对目标对象进行身份验证的过程中,终端设备可以在服务页面中显示目标对象的生物信息对应的卡通信息,请参见下述内容描述。
在一种可能的实现方式中,终端设备采集到的目标对象的生物信息可以包括拍摄目标对象得到的第i帧人脸视频帧和第j帧人脸视频帧,该第i帧人脸视频帧和第j帧人脸视频帧包括目标对象的人脸图像,因此第i帧人脸视频帧和第j帧人脸视频帧包括目标对象的人脸信息,该第i帧人脸视频帧和第j帧人脸视频帧可以是终端设备在采集生物信息时拍摄目标对象得到的任意相邻的两帧人脸视频帧,一个人脸视频帧实质上为一个图像,i和j均为小于或者等于在采集目标对象的生物信息的过程中拍摄的全部人脸视频帧的总数量的正整数,第i帧人脸视频帧为第j帧人脸视频帧的前一帧人脸视频帧。第i帧人脸视频帧和第j帧人脸视频帧各自具备目标对象的人脸显示属性,该人脸显示属性可以包括以下至少一种:人脸姿态属性、人脸表情属性和人脸配置属性等,该人脸姿态属性可以表征目标对象的人脸的倾斜程度(如是否偏头、低头或者仰头等),该人脸表情属性可以表征目标对象的人脸的表情(如高兴的表情、难过的表情或者惊讶的表情等),该人脸配饰属性可以表征目标对象的人脸上所佩戴的配饰(如眼镜或者美瞳等配饰),以上人脸显示属性仅为举例。
更多的,目标对象的生物信息对应的卡通信息可以包括上述第i帧人脸视频帧对应的卡通人脸视频帧以及第j帧人脸视频帧对应的卡通人脸视频帧。因此,在第i帧人脸视频帧对应的第一时刻(该第一时刻可以理解为是采集到第i帧人脸视频帧的时刻),终端设备可以在服务页面中按照第i帧人脸视频帧具备的人脸显示属性,来显示第i帧人脸视频帧对应的卡通人脸视频帧,该卡通人脸视频帧包括第i帧人脸视频帧中所拍摄的目标对象的人脸对应的卡通人脸,该卡通人脸具有第i帧人脸视频帧所具有的人脸显示属性,只是第i帧人脸视频帧具有目标对象真实的人脸显示属性,而该卡通人脸具有目标对象卡通的人脸显示属性。
进而,当从上述第一时刻到达第j帧人脸视频帧对应的第二时刻(该第二时刻可以理解为是采集到第j帧人脸视频帧的时刻)时,终端设备可以在 服务页面中按照第j帧人脸视频帧具备的人脸显示属性,来显示第j帧人脸视频帧对应的卡通人脸视频帧,该卡通人脸视频帧包括第j帧人脸视频帧中所拍摄的目标对象的人脸对应的卡通人脸,该卡通人脸具有第j帧人脸视频帧所具有的人脸显示属性,只是第j帧人脸视频帧具有目标对象真实的人脸显示属性,而该卡通人脸具有目标对象卡通的人脸显示属性。
其中,可以理解为采集到目标对象的生物信息(如每个人脸视频帧)时,可以同步在服务页面中显示该生物信息对应的卡通信息(如每个人脸视频帧对应的卡通人脸视频帧),即采集生物信息与显示卡通信息(如采集一个人脸视频帧与显示该人脸视频帧对应的卡通人脸视频帧)之间的时延非常小,可以认为是同步的。
可选的,目标对象的生物信息可以包括采集到的目标对象的人脸图像,该人脸图像可以是在服务页面显示期间采集到的目标对象的任意一帧人脸视频帧。因此,目标对象的生物信息对应的卡通信息可以包括该人脸图像对应的卡通人脸图像,该卡通人脸图像可以理解为是该人脸图像对应的卡通人脸视频帧,该卡通人脸图像中包括与人脸图像中目标对象的真实人脸对应的卡通人脸。
因此,同理,终端设备可以在服务页面中按照该目标对象的人脸图像的人脸显示属性,来显示该卡通人脸图像。
可选的,目标对象的生物信息可以包括采集到的目标对象的掌纹图像,该掌纹图像可以是在服务页面显示期间采集到的目标对象的任意一帧掌纹视频帧,该掌纹图像可以是对目标对象的手掌进行拍摄得到的图像,该掌纹图像包括目标对象的掌纹信息。因此,目标对象的生物信息对应的卡通信息可以包括该掌纹图像对应的卡通掌纹图像,该卡通掌纹图像可以理解为是该掌纹图像对应的卡通掌纹视频帧,该卡通掌纹图像中包括掌纹图像中目标对象的真实手掌对应的卡通手掌。
因此,同理,终端设备可以在服务页面中按照该目标对象的掌纹图像的掌纹显示属性,来显示卡通掌纹图像。例如,该掌纹显示属性可以包括掌纹姿态属性以及掌纹配饰属性等属性中的至少一种,该掌纹姿态属性可以包括掌纹图像中目标对象的手掌的倾斜程度以及张合程度等,该掌纹配饰属性可以包括掌纹图像中目标对象的手掌上所佩戴的配饰(如戒指等)。该卡通掌纹图像具有掌纹图像所具有的掌纹显示属性,只是掌纹图像具有目标对象真实的掌纹显示属性,而该卡通掌纹图像具有目标对象卡通的掌纹显示属性。
可选的,目标对象的生物信息可以包括采集到的目标对象的瞳孔图像,该瞳孔图像可以是在服务页面显示期间采集到的目标对象的任意一帧瞳孔视频帧,该瞳孔图像可以是对目标对象的眼睛拍摄得到的图像,该瞳孔图像包括目标对象的瞳孔信息。因此,目标对象的生物信息对应的卡通信息可以包括该瞳孔图像对应的卡通瞳孔图像,该卡通瞳孔图像可以理解为是该瞳孔图 像对应的卡通瞳孔视频帧,该卡通瞳孔图像中包括瞳孔图像中目标对象的真实眼睛对应的卡通眼睛。
因此,同理,终端设备可以在服务页面中按照该目标对象的瞳孔图像的瞳孔显示属性,来显示卡通瞳孔图像。例如,该瞳孔显示属性可以包括瞳孔张合属性以及瞳孔配饰属性等属性中的至少一种,该瞳孔张合属性可以包括瞳孔图像中目标对象的瞳孔的张开或闭合的程度等,该瞳孔配饰属性可以包括瞳孔图像中目标对象的瞳孔上所佩戴的配饰(如美瞳等)。该卡通瞳孔图像具有瞳孔图像所具有的瞳孔显示属性,只是瞳孔图像具有目标对象真实的瞳孔显示属性,而该卡通瞳孔图像具有目标对象卡通的瞳孔显示属性。
总结而言,终端设备采集的目标对象的生物信息可以是对目标对象的某个生物部位(如人脸、瞳孔或者掌纹等部位)进行拍摄得到的若干视频帧(如上述人脸视频帧、瞳孔视频帧或者掌纹视频帧等),该若干视频帧包括所拍摄的目标对象的生物部位的信息(如人脸信息、瞳孔信息或者掌纹信息等),目标对象的生物信息对应的卡通信息包括每个视频帧对应的卡通视频帧(如上述卡通人脸视频帧、卡通瞳孔视频帧或者卡通掌纹视频帧等)。终端设备可以在采集到每个视频帧的同时,同步在服务页面依次显示该每个视频帧对应的卡通视频帧,以实现在拍摄目标对象的过程中,不显示真实拍摄的目标对象(如真实拍摄的目标对象的人脸),而显示真实拍摄的目标对象对应的卡通形象(如卡通人脸的形象、卡通掌纹的形象或者卡通瞳孔的形象等),并且,在拍摄过程中,目标对象做什么动作或者有什么改变,服务页面显示的卡通形象也可以产生同样的动作或者改变。可以理解的是,视频帧中的目标对象与该视频帧对应的卡通视频帧中的卡通形象是极为相似的,只是视频帧中包括拍摄的真实的目标对象,而卡通视频帧中包括所拍摄的目标对象对应的卡通形象。
请参见图4,图4是本申请提供的一种服务页面的页面示意图。服务页面中显示的目标对象的卡通信息可以是动态变化的,如图4所示,服务页面100c、服务页面101c和服务页面102c依次显示了目标对象的第1帧人脸视频帧对应的卡通人脸视频帧、目标对象的第2帧人脸视频帧对应的卡通人脸视频帧以及目标对象的第3帧人脸视频帧对应的卡通人脸视频帧。相邻的卡通人脸视频帧之间的间隔时长非常小,因此依次且连续地显示每个卡通人脸视频帧就是动态的显示效果,此时可以认为显示的是由若干卡通人脸视频帧构成的卡通人脸视频。
可选的,生物信息为对目标对象的某个生物部位进行拍摄得到的视频帧,生物信息对应的卡通信息为该视频帧对应的卡通视频帧时,该卡通视频帧中可以不包括视频帧中所拍摄的目标对象的背景,而只包括所拍摄的目标对象对应的卡通形象。因此,终端设备还可以在服务页面中显示背景选择列表,该背景选择列表可以包括M种背景信息,M为正整数,M的具体取值可以根 据实际应用场景决定,对此不作限制。终端设备可以根据目标对象针对该M种背景信息的选择操作,将目标对象所选择的背景信息作为卡通视频帧中目标对象的卡通形象的目标背景信息,并在服务页面中对卡通信息和该目标背景信息进行同步显示,可以理解为将目标背景信息与卡通视频帧进行合成,合成后的卡通视频帧包括所拍摄的目标对象的卡通形象和该目标背景信息。
请参见图5,图5是本申请提供的一种选取背景信息的页面示意图。如图5所示,服务页面100d中显示有拍摄目标对象得到的视频帧对应的卡通视频帧107d。在服务页面100d中还包括背景选择列表,该背景选择列表中包括背景信息101d、背景信息102d和背景信息103d等M种可供目标对象选择的背景信息。如图5所示,在服务页面100d中目标对象未选择背景信息,则所显示的卡通人脸视频帧中目标对象的卡通形象的背景是空白的。
当目标对象在服务页面100d中选中了背景信息101d时,终端设备可以由显示服务页面100d转变为显示服务页面104d,如服务页面104d所示,所显示的卡通人脸视频帧中目标对象的卡通形象的背景信息就为背景信息101d,即所显示的卡通人脸视频帧中目标对象的卡通形象的背景信息包括很多小三角形。
同理,当目标对象在服务页面100d中选中了背景信息102d时,终端设备可以由显示服务页面100d转变为显示服务页面105d,如服务页面105d所示,所显示的卡通人脸视频帧中目标对象的卡通形象的背景信息就为背景信息102d,即所显示的卡通人脸视频帧中目标对象的卡通形象的背景信息包括很多直线。
同理,当目标对象在服务页面100d中选中了背景信息103d时,终端设备可以由显示服务页面100d转变为显示服务页面106d,如服务页面106d所示,所显示的卡通人脸视频帧中目标对象的卡通形象的背景信息就为背景信息103d,即所显示的卡通人脸视频帧中目标对象的卡通形象的背景信息包括很多波浪线。
其中,上述背景信息101d、背景信息102d和背景信息103d仅为举例,背景信息包括的具体内容可以任意设置。
步骤S103,显示目标订单的生物结算信息。
本申请中,该生物结算信息可以在服务页面上显示,或者该生物结算信息也可以在非服务页面的新的页面上显示。当终端设备基于生物信息对目标对象的身份验证结束时,可以显示对应的生物结算信息,所显示的生物结算信息至少根据对于目标对象的身份验证结果确定。
该生物结算信息可以包括以下几种情况:
可选的,基于生物信息对目标对象的身份验证成功时,可以通过与目标对象相关联的结算账户对目标订单进行结算,并生成结算成功信息,该结算成功信息即可作为生物结算信息,此时的生物结算信息用于提示目标对象对 目标订单结算成功。
可选的,基于生物信息对目标对象的身份验证失败时,表明也获取不到与目标对象相关联的结算账户,此时对目标订单结算失败,终端设备可以生成结算失败信息,该结算失败信息即可作为生物结算信息,此时的生物结算信息用于提示目标对象对目标订单结算失败。
其中,上述目标订单可以是通过结算软件进行结算的,上述生物结算操作也可以是在该结算软件中操作的,目标对象可以是该结算软件的用户,即目标对象在该结算软件中注册有用户账号,因此,与目标对象相关联的结算账户可以是与该目标对象在结算软件中的用户账号相绑定的账户(例如在结算软件中的余额账户、或者银行账户等)。因此,可以理解的是,通过生物信息对目标对象的身份验证成功,可以指通过生物信息验证得到目标对象在结算软件中的用户账号。反之,通过生物信息对目标对象的身份验证失败,可以指通过生物信息未验证得到目标对象在结算软件中的用户账号。
可选的,基于生物信息对目标对象的身份验证成功时,终端设备还可以生成结算确认信息,该结算确认信息可以作为生物结算信息,此时生物结算信息用于支持用户对目标订单进行结算,即用于让用户进行确认后再对目标订单进行结算。例如,该结算确认信息可以包括在结算软件中验证得到的目标对象的用户账号的掩码(如与用户账号相关联的手机号码的掩码),或者可以包括目标对象的用户账号的头像等。终端设备可以根据目标对象针对该结算确认信息的确认操作,使用与目标对象相关联的结算账户对目标订单进行结算。
其中,与目标对象相关联的结算账户可以有多个(至少两个),因此,终端设备在检测到目标对象针对结算确认信息的确认操作后,还可以显示账户选择列表,该账户选择列表中可以包括与目标对象相关联的N个结算账户,N为正整数,N的具体取值根据实际应用场景决定。因此,终端设备还可以根据目标对象针对该账户选择列表中的N个结算账户的选择操作,将目标对象所选择的结算账户作为目标结算账户,并通过该目标结算账户对目标订单进行结算。
其中,终端设备对目标订单进行结算的操作,可以是终端设备向结算软件的后台请求对目标订单进行结算,进而通过结算软件的后台来实现对目标订单的结算,结算成功后,结算软件的后台可以向终端设备返回结算结果。
请参见图6,图6是本申请提供的一种订单结算的页面示意图。如图6所示,在终端页面100e中显示有支付方式的列表,该列表包括三种支付方式,具体包括刷脸支付的方式、指纹支付的方式以及密码支付的方式。终端设备可以根据用户针对终端页面100e中的刷脸支付的方式的选择操作(该选择操作可以为上述生物结算操作),显示服务页面101e,在该服务页面101e上可以显示与通过摄像头拍摄的目标对象的真实图像相对应的卡通图像。
同时,终端设备还可以基于摄像头拍摄的目标对象的真实图像对目标对象进行身份验证,或者,终端设备可以将摄像头拍摄的目标对象的真实图像发送给后台的服务器,以使该服务器基于该真实图像对目标对象进行身份验证,在对目标对象的身份验证成功时,可以由显示服务页面101e转变到显示终端页面102e,该终端页面102e可以包括目标对象的用户账号的头像104e。终端设备可以根据目标对象针对终端页面102e中的“确认支付”按钮的确认操作(如点击操作),请求结算软件的后台采用与目标对象相关联的结算账户(可以是默认结算账户)对目标订单进行结算,结算成功后向终端设备返回结算成功的提示信息,终端设备可以根据该提示信息从显示终端页面102e转变到显示终端页面103e,通过该终端页面103e可以提示目标对象其已经对目标订单结算成功(即支付成功)。
采用本申请所提供的方法,在基于生物信息对目标订单进行结算时,服务页面中可以不显示对真实拍摄的目标对象,而是显示所拍摄的目标对象的卡通信息,这可以减少因呈现真实的生物信息而对用户带来的心理冲击,减少用户的心理不适感,并可以提升用户使用生物信息对目标订单进行结算的兴趣,提高通过生物信息进行订单结算的相关技术的使用率。此外,在服务页面显示目标对象的生物信息对应的卡通信息,也提高了目标对象的生物信息的安全性。
请参见图7,图7是本申请提供的一种信息处理方法的流程示意图。本申请实施例描述的方法与上述图3对应实施例中描述的方法是同一个方法,只是上述图3对应实施例中侧重于对用户能感知到的一些内容进行描述,而本申请实施例侧重于对方法的具体实现原理进行描述,因此,本申请实施例中的执行主体可以就是图3对应实施例中的执行主体,本申请实施例描述的内容也可以与上述图3对应实施例中所述的内容相互结合。如图7所示,该方法可以包括:
步骤S201,响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息。
本申请中,此处采集目标对象的生物信息以采集目标对象的人脸信息为例进行说明,可以理解的是,除了人脸信息之外,也可以采集其他生物信息(如瞳孔信息或者掌纹信息等)。因此,终端设备在检测到目标对象针对目标订单触发生物结算操作后,可以调用摄像头拍摄镜头前的目标对象的人脸,得到目标对象的L个人脸视频帧,L为拍摄目标对象得到的人脸视频帧的总数量,L为正整数,L的具体取值根据实际应用场景决定。该L个人脸视频帧就可以作为目标对象的生物信息。
步骤S202,基于生物信息对目标对象进行身份验证,并对生物信息进行卡通转换,得到生物信息对应的卡通信息。
本申请中,可以理解的是,基于生物信息对目标对象进行身份验证的过 程,与对生物信息进行卡通转换得到卡通信息的过程,可以是相互独立并行执行的过程。
其中,通过生物信息对目标对象进行身份验证的过程可以是:
终端设备可以从上述L个人脸视频帧中选取出一个人脸视频帧,将选取出的人脸视频帧作为目标视频帧,根据该目标视频帧来对目标对象进行身份验证。其中,可以是从该L个人脸视频帧中选取最优帧作为目标视频帧,该最优帧可以是L个人脸视频帧中清晰度最高的视频帧,或者可以是该L个人脸视频帧中人脸信息拍摄得最完整的视频帧等。终端设备基于目标视频帧对目标对象进行身份验证的方式可以是:
终端设备在采集得到目标视频帧时,还可以采集到该目标视频帧对应的深度视频帧,该目标视频帧为平面图像,目标视频帧中包括目标对象的人脸的平面信息,而该深度视频帧可以理解为是立体的图像,其中包括目标对象的人脸的深度信息(可以称之为人脸深度信息),可以理解为包括目标对象的人脸的立体信息。
因此,终端设备可以从目标视频帧中获取目标对象的五官平面信息,其中,五官可以指目标对象的两只眼睛、鼻子以及两个嘴角,则五官平面信息可以包括目标对象的两只眼睛、鼻子、两个嘴角之间的间距等信息。终端设备可以从目标视频帧对应的深度视频帧中获取到目标对象的五官深度信息,该五官深度信息可以包括目标对象的两只眼睛、鼻子、两个嘴角的突出或者凹陷的轮廓等信息。可以将终端设备获取到的目标对象的五官平面信息和五官深度信息作为目标对象的五点信息,并且将该五点信息发送给结算软件的后台,结算软件后台可以将目标对象的五点信息与数据库中所存储的所有用户的五点信息做对比,以此来确认目标对象的身份,例如可以将数据库中存储的与目标对象的五点信息极为相似的五点信息所属的用户认为是目标对象,此时认为对目标对象的身份验证成功,结算软件的后台可以向终端设备(如向终端设备中的结算软件)返回对目标对象的身份验证成功的提示信息。而若是数据库中不存在与目标对象的五点信息极为相似的五点信息,则认为对目标对象的身份验证失败,结算软件的后台可以向终端设备(如向终端设备中的结算软件)返回对目标对象的身份验证失败的提示信息。应理解,上述五点信息极为相似具体可以理解为两个五点信息之间的相似度超过预设阈值。
其中,对生物信息进行卡通转换得到卡通信息的过程可以是:
此处还是以生物信息为上述L个人脸视频帧为例进行说明。终端设备在需要进行卡通转换时,可以从后台(如结算软件的后台)拉取并下载卡通转换模型,该卡通转换模型可以是预先训练得到的用于将生物信息转换为卡通信息的模型。因此,终端设备可以将L个人脸视频帧输入到该卡通转换模型中,通过该卡通转换模型分别提取所输入的每个人脸视频帧所包括的人脸局 部图像(即只包括所拍摄的目标对象的头部的图像),并可以通过卡通转换模型,生成每个人脸视频帧包括的人脸局部图像对应的卡通人脸图像(可以简称为卡通图像),通过卡通转换模型生成的每个人脸视频帧包括的人脸局部图像对应的卡通人脸图像即为目标对象的生物信息对应的卡通信息。此种情形是只对拍摄到的目标对象的人脸(可以理解为是头部)进行卡通转换。
其中,可以理解的是,由于终端设备是依次获取的上述L个人脸视频帧,该L个人脸视频帧是在不同时刻先后获取到的,因此,该L个人脸视频帧也可以是在不同时刻先后输入卡通转换模型,终端设备每获取到一个人脸视频帧就可以将该人脸视频帧输入卡通转换模型,一次可以只输入一个人脸视频帧,因此,可以通过L次依次将人脸视频帧输入卡通转换模型,得到每个人脸视频帧对应的卡通人脸图像。
可选的,在拍摄得到上述L个人脸视频帧时,有可能将目标对象的部分身体(如颈部和肩膀部分)也拍摄进去,因此,在对L个人脸视频帧进行卡通转换时,可以不仅仅只转换拍摄到的目标对象的人脸(如上述人脸局部图像中的人脸),还可以将人脸视频帧中所拍摄进去的目标对象的全部部位(如包括头部、颈部和肩膀的部位)进行卡通转换,得到对应的卡通图像,进而可以将该卡通图像作为目标对象的生物信息对应的卡通信息。
再可选的,在对L个人脸视频帧进行卡通转换时,可以不仅仅只转换所拍摄到的目标对象,还可以对所拍摄到的目标对象所在的环境(即人脸视频帧中目标对象的背景)也进行卡通转换,得到对应的卡通图像,进而可以将该卡通图像作为目标对象的生物信息对应的卡通信息。
更多的,上述卡通转换模型可以是终端设备训练得到的,也可以是由结算软件的后台训练得到的,此处以终端设备训练得到上述卡通转换模型为例进行说明,上述卡通转换模型的训练过程可以是:
首先,终端设备可以获取到初始卡通转换模型,该初始卡通转换模型为生成对抗网络(GAN,Generative Adversarial Networks),是一种无监督的模型。初始卡通转换模型可以包括卡通生成器(可以简称生成器)和卡通判别器(可以简称判别器)。
其中,生成器的训练目的是通过调整自己的模型参数,以生成与所输入的图像最接近的漫画质感(即卡通质感)的图像,从而欺骗判别器,让判别器判别该所生成的漫画质感的图像是真实的图像(即真实对目标对象进行拍摄的图像),而判别器的训练目的则是调整自己的模型参数,来尽可能准确地判别生成器所生成的漫画质感的图像不是真实的图像。
具体的,可以将样本人脸图像输入卡通生成器,该样本人脸图像可以是对样本用户的人脸进行拍摄得到的真实图像,在卡通生成器中可以生成该样本人脸图像对应的样本卡通人脸图像,继而可以将卡通生成器生成的样本卡通人脸图像输入卡通判别器,让卡通判别器来判别该样本卡通人脸图像属于 卡通类型图像的概率,本申请将该概率称为卡通概率,该卡通概率也可以表征样本卡通人脸图像为漫画质感的图像的概率。
因此,可以通过卡通判别器所得到的卡通概率,来修正卡通生成器的模型参数和卡通判别器的模型参数,得到卡通生成器的修正后的模型参数以及卡通判别器的修正后的模型参数,上述样本人脸图像可以有若干个,通过该若干个样本人脸图像可以以上述同样的原理,不断迭代地修正卡通生成器的模型参数和卡通判别器的模型参数,当经模型参数修正后得到的卡通生成器以及卡通判别器均满足模型训练标准时,可以将此时的卡通生成器作为上述卡通转换模型。
其中,该模型训练标准可以指模型参数修正的次数(可以理解为训练的次数)达到一定阈值次数(可以自行根据实际应用场景设定),即当对模型参数修正的次数大于该一定阈值次数时,表明经模型参数修正后得到的模型满足模型训练标准;或者,该模型训练标准可以指修正后的模型参数达到收敛状态,即当修正后的模型参数达到收敛状态时,表明经模型参数修正后得到的模型满足模型训练标准。其中,具体的模型训练标准也可以根据实际应用场景决定,对此不做限制。
其中,需要进行说明的是,对初始卡通转换模型的模型参数(包括卡通生成器的模型参数和卡通判别器的模型参数)进行修正时,可以分为两个阶段,即模型训练过程可以分为两个阶段,包括第一阶段训练过程和第二阶段训练过程。上述卡通概率包括该两个阶段的卡通概率,可以将在第一阶段训练过程中得到的卡通概率称之为第一阶段卡通概率,将在第二阶段训练过程中得到的卡通概率称之为第二阶段卡通概率,在第一阶段训练过程中使用的样本人脸图像和在第二阶段训练过程中使用的样本人脸图像可以相同也可以不同,在对初始卡通转换模型的一次训练过程中,一个样本人脸图像可以对应一个卡通概率。
具体的,在针对初始卡通转换模型的第一阶段训练过程中,可以保持卡通判别器的模型参数不变,根据得到的第一阶段卡通概率修正卡通生成器的模型参数,修正时的目标可以是使得第一阶段卡通概率达到50%,此时认为卡通判别器不能区分卡通图像和真实图像,属于瞎猜的状态,修正后,即可得到卡通生成器的修正后的模型参数。进而,在针对初始卡通转换模型的第二阶段训练过程中,可以保持卡通生成器的修正后的模型参数(即在第一阶段训练过程中修正后的模型参数)不变,根据得到的第二阶段卡通概率修正卡通判别器的模型参数,修正的目标可以是使得第一阶段卡通概率达到100%,即让卡通判别器能最大限度区分卡通图像,修正后,即可得到卡通判别器的修正后的模型参数。
其中,第一阶段训练过程中可以通过若干个样本人脸图像对初始卡通转换模型进行迭代训练,第二阶段训练过程也可以通过若干个样本人脸图像对 初始卡通转换模型进行迭代训练,对初始卡通转换模型的后一次训练是在针对初始卡通转换模型的前一次训练的基础上继续进行训练,并且,可以将执行一轮第一阶段训练过程和一轮第二阶段训练过程理解为对初始卡通转换模型的一轮训练,还可以对初始卡通转换模型进行若干轮的训练,即可以重复迭代执行第一阶段训练过程和第二阶段训练过程,直到经模型参数修正后得到的初始转换模型(包括经模型参数修正后得到的卡通生成器和卡通判别器)达到上述模型训练标准时,就可以将此时的卡通生成器作为上述卡通转换模型。
请参见图8,图8是本申请提供的一种模型训练的场景示意图。如图8所示,初始卡通转换模型101f包括卡通生成器102f和卡通判别器103f。可以将样本图像(如上述样本人脸图像)输入卡通生成器102f,通过卡通生成器102f可以生成该样本图像对应的卡通图像。进而可以将卡通图像输入卡通判别器103f,通过该卡通判别器103f可以得到针对卡通图像的卡通概率。进而,若该卡通概率为第一阶段卡通概率,则可以将该卡通概率反向传播给卡通生成器102f,通过该卡通概率来修正卡通生成器的102f的模型参数,若该卡通概率为第二阶段卡通概率,则可以将该卡通概率反向传播给卡通判别器103f,通过该卡通概率来修正卡通判别器103f的模型参数。
可以将模型参数修正完成的卡通生成器102f作为最终的卡通生成器104f,可以将模型参数修正完成的卡通判别器103f作为最终的卡通判别器105f。此时,就可以得到训练完成的初始卡通转换模型100f,可以将训练完成的初始卡通转换模型100f中的卡通生成器104f作为上述卡通转换模型。
请参见图9,图9为本申请提供的一种模型训练的场景示意图。实际上,上述第一阶段训练和第二阶段训练均可以看作为是对模型训练的一种原理或者方式,第一阶段训练就是固定卡通判别器的模型参数,通过卡通概率修正卡通生成器的模型参数,第二阶段训练就是固定卡通生成器的模型参数,通过卡通概率修正卡通判别器的模型参数。
如图9所示,可以将进行一次第一阶段训练以及一次第二阶段训练作为对初始卡通转换模型的一轮训练,可以对初始卡通转换模型进行n轮训练(如此处的第1轮训练~第n轮训练),n的具体取值根据实际应用场景决定。在对初始卡通转换模型进行n轮训练后,可以认为此时初始卡通转换模型训练完成,可以将此时的卡通生成器作为上述卡通转换模型。
可选的,训练上述初始卡通转换模型(即初始的GAN模型)时,还可以通过卷积神经网络来提升初始卡通转换模型所涉及的算法的效率,进而提升训练效率,并在实际应用卡通转换模型时,提升卡通转换模型生成卡通图像的效率。
步骤S203,在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示卡通信息。
本申请中,在基于生物信息对目标对象进行身份验证的过程中,终端设备可以在服务页面中显示目标对象的生物信息对应的卡通信息,由于目标对象的L个人脸视频帧是不同时刻先后拍摄到的,因此,在对L个人脸视频帧进行卡通转换时,也是先后依次进行转换得到每个人脸视频帧对应的卡通图像,而由于在采集到每个人脸视频帧后可以以极小的延时同步(可以理解为是实时)在服务页面显示该人脸视频帧对应的卡通图像,因此,终端设备在对每一个人脸视频帧进行卡通转换,得到该人脸视频帧对应的卡通图像时,就可以在服务页面显示该人脸视频帧对应的卡通图像。即L个人脸视频帧各自对应的卡通图像也可以是在服务页面依次进行显示的,以达到在拍摄得到人脸视频帧时在服务页面同步显示人脸视频帧对应的卡通图像的目的。
步骤S204,显示目标订单的生物结算信息。
本申请根据针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示目标对象的生物信息对应的卡通信息;显示目标订单的生物结算信息。由此可见,本申请提出的方法可以在服务页面显示目标对象的生物信息对应的卡通信息,提高了目标对象的生物信息的安全性,并且,不直接显示目标对象的生物信息,也可以减少因直接显示目标对象的生物信息而给目标对象带来的视觉冲击,从而提高目标对象使用生物信息对目标订单进行结算的兴趣。
请参见图10,图10是本申请提供的一种订单结算的流程示意图。如图10所示,首先如框100h,应用启动可以指启动结算软件。在启动结算软件后,结算软件可以向后台服务器107h拉取卡通转换模型108h。进而,如框101h~102h,在启动的结算软件中开始交易时(如检测到生物结算操作时),就可以准备对摄像头(结算软件所在的终端设备的摄像头)前的用户进行识别(如对用户的身份进行验证识别),此时启动摄像头(如框103h)。
进而如框104h,可以通过摄像头获取到识别帧,该识别帧可以是通过摄像头对用户进行拍摄得到的视频帧(如上述目标对象的人脸视频帧)。终端设备可以将该识别帧输入卡通转换模型108h中,通过该卡通转换模型108h生成识别帧对应的卡通帧109h(如上述视频帧对应的卡通视频帧)。进而,终端设备可以通过播放器110h在服务页面播放(即显示)该卡通帧109h。
在获取到识别帧104h后,该识别帧104h可以有多个,终端设备可以从该多个识别帧104h中选取最优帧105h(如上述目标视频帧),进而通过该最优帧得到目标对象的五点信息106h(可以包括目标对象的五官平面信息和五官深度信息),终端设备可以将该五点信息106h发送给后台服务器107h,向后台服务器107h请求通过该五点信息106h对目标对象的身份进行验证。后台服务器107h在获取到该五点信息106h之后,即可将该五点信息106h与数据库中结算软件中已有的用户的五点信息进行对比,以此来判断目标对象 是已有的用户中的哪个用户,并在确定目标对象的的用户身份后,可以向终端设备返回所判断出的目标对象的用户身份(如返回可以表示目标对象的用户身份的头像,该头像即为目标对象的用户账号的头像),终端设备可以在终端页面上显示包括该用户身份的结算确认信息,在检测到针对该结算确认信息的确认操作后,即可请求后台服务器107h采用与目标对象相关联的结算账户对目标对象的目标订单进行结算。
请参见图11,图11是本申请提供的一种信息处理装置的结构示意图。该信息处理装置可以是运行于计算机设备中的一个计算机程序(包括程序代码),例如该信息处理装置为一个应用软件,该信息处理装置可以用于执行本申请实施例提供的方法中的相应步骤。如图11所示,该信息处理装置1可以包括:第一信息采集模块11、第一信息显示模块12和第一结算模块13;
第一信息采集模块11,用于响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;生物结算操作用于触发基于生物信息对目标对象进行身份验证,并根据身份验证结果进行针对目标订单的结算;
第一信息显示模块12,用于在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示目标对象的生物信息对应的卡通信息;
第一结算模块13,用于显示目标订单的生物结算信息;生物结算信息至少根据对于目标对象的身份验证结果确定。
可选的,目标对象的生物信息包括拍摄目标对象得到的第i帧人脸视频帧和第j帧人脸视频帧,i小于j,i和j均为正整数;第i帧人脸视频帧和第j帧人脸视频帧各自具备目标对象的人脸显示属性;目标对象的生物信息对应的卡通信息包括第i帧人脸视频帧对应的卡通人脸视频帧和第j帧人脸视频帧对应的卡通人脸视频帧;
第一信息显示模块12具体用于:
在第i帧人脸视频帧对应的第一时刻,在服务页面中按照第i帧人脸视频帧具备的人脸显示属性,显示第i帧人脸视频帧对应的卡通人脸视频帧;
当从第一时刻到达第j帧人脸视频帧对应的第二时刻时,在服务页面中按照第j帧人脸视频帧具备的人脸显示属性,显示第j帧人脸视频帧对应的卡通人脸视频帧。
可选的,目标对象的生物信息包括目标对象的人脸图像;目标对象的生物信息对应的卡通信息包括与目标对象的人脸图像相对应的卡通人脸图像;
第一信息显示模块12具体用于:
在服务页面中按照目标对象的人脸图像的人脸显示属性,显示卡通人脸图像;
人脸显示属性包括以下至少一种:人脸姿态属性、人脸表情属性、人脸配饰属性。
可选的,目标对象的生物信息包括目标对象的掌纹图像;目标对象的生 物信息对应的卡通信息包括与目标对象的掌纹图像相对应的卡通掌纹图像;
第一信息显示模块12具体用于:
在服务页面中按照目标对象的掌纹图像的掌纹显示属性,显示卡通掌纹图像;
掌纹显示属性包括以下至少一种:掌纹姿态属性、掌纹配饰属性。
可选的,目标对象的生物信息包括目标对象的瞳孔图像;目标对象的生物信息对应的卡通信息包括与目标对象的瞳孔图像相对应的卡通瞳孔图像;
第一信息显示模块12具体用于:
在服务页面中按照目标对象的瞳孔图像的瞳孔显示属性,显示卡通瞳孔图像;
瞳孔显示属性包括以下至少一种:瞳孔张合属性、瞳孔配饰属性。
可选的,第一信息显示模块12还用于:
在服务页面中输出背景选择列表;背景选择列表包括M种背景信息;M为正整数;
根据针对M种背景信息的选择操作,将所选择的背景信息确定为卡通信息的目标背景信息;
第一信息显示模块12具体用于:
在服务页面中同步显示卡通信息和目标背景信息。
可选的,基于生物信息对目标对象的身份验证成功时,生物结算信息包括结算成功信息;基于生物信息对目标对象的身份验证失败时,生物结算信息包括结算失败信息。
可选的,生物结算信息包括结算确认信息;第一结算模块13具体用于:
若检测到基于生物信息对目标对象的身份验证成功,则显示结算确认信息;结算确认信息用于支持针对目标订单进行结算;
上述装置1还包括:结算确认模块,结算确认模块用于:
根据针对结算确认信息的确认操作,对目标订单进行结算。
可选的,上述结算确认模块具体用于:
根据确认操作显示账户选择列表;账户选择列表包括与目标对象相关联的N个结算账户,N为正整数;
根据针对账户选择列表中的N个结算账户的选择操作,将所选择的结算账户确定为目标结算账户;
采用目标结算账户对目标订单进行结算。
根据本申请的一个实施例,图3所示的信息处理方法所涉及的步骤可由图11所示的信息处理装置1中的各个模块来执行。例如,图3中所示的步骤S101可由图11中的第一信息采集模块11来执行,图3中所示的步骤S102可由图11中的第一信息显示模块12来执行;图3中所示的步骤S103可由图11中的第一结算模块13来执行。
请参见图12,图12是本申请提供的一种信息处理装置的结构示意图。该信息处理装置可以是运行于计算机设备中的一个计算机程序(包括程序代码),例如该信息处理装置为一个应用软件,该信息处理装置可以用于执行本申请实施例提供的方法中的相应步骤。如图12所示,该信息处理装置2可以包括:第二信息采集模块21、信息转换模块22、第二信息显示模块23和第二结算模块24;
第二信息采集模块21,用于响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;生物结算操作用于触发基于生物信息对目标对象进行身份验证,并根据身份验证结果进行针对目标订单的结算;
信息转换模块22,用于基于生物信息对目标对象进行身份验证,并对生物信息进行卡通转换,得到生物信息对应的卡通信息;
第二信息显示模块23,用于在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示卡通信息;
第二结算模块24,用于显示目标订单的生物结算信息;生物结算信息至少根据对于目标对象的身份验证结果确定。
可选的,生物信息包括目标对象的L个人脸视频帧;L为正整数;
信息转换模块22具体用于:
从L个人脸视频帧中选取目标视频帧;
根据目标视频帧对目标对象进行身份验证。
可选的,信息转换模块22具体用于:
获取目标视频帧对应的深度视频帧;深度视频帧包括目标对象的人脸深度信息;
从深度视频帧包括的人脸深度信息中获取目标对象的五官深度信息;
根据目标视频帧获取目标对象的五官平面信息;
根据五官平面信息和五官深度信息对目标对象进行身份验证。
可选的,信息转换模块22具体用于:
获取卡通转换模型;
通过卡通转换模型,分别提取L个人脸视频帧包括的人脸局部图像;
通过卡通转换模型中,分别生成每个人脸视频帧包括的人脸局部图像对应的卡通人脸图像;
将每个人脸视频帧包括的人脸局部图像对应的卡通人脸图像确定为卡通信息。
可选的,上述装置2还包括模型训练模块,该模型训练模块用于:
获取初始卡通转换模型;初始卡通转换模型包括卡通生成器和卡通判别器;
通过卡通生成器,根据样本人脸图像生成样本人脸图像对应的样本卡通人脸图像;
通过卡通判别器,根据样本卡通人脸图像判别样本卡通人脸图像属于卡通类型图像的卡通概率;
基于卡通概率,修正卡通生成器的模型参数和卡通判别器的模型参数;
当卡通生成器和卡通判别器均满足模型训练标准时,将卡通生成器确定为卡通转换模型。
可选的,卡通概率包括第一阶段卡通概率和第二阶段卡通概率;上述模型训练模块具体用于:
在针对初始卡通转换模型的第一阶段训练过程中,保持卡通判别器的模型参数不变,根据第一阶段卡通概率修正卡通生成器的模型参数,得到卡通生成器的修正后的模型参数;
在针对初始卡通转换模型的第二阶段训练过程中,保持卡通生成器的修正后的模型参数不变,根据第二阶段卡通概率修正卡通判别器的模型参数,得到卡通判别器的修正后的模型参数。
根据本申请的一个实施例,图7所示的信息处理方法所涉及的步骤可由图12所示的信息处理装置1中的各个模块来执行。例如,图7中所示的步骤S201可由图12中的第二信息采集模块21来执行,图7中所示的步骤S202可由图12中的信息转换模块22来执行;图7中所示的步骤S203可由图12中的第二信息显示模块23来执行,图7中所示的步骤S204可由图11中的第二结算模块24来执行。
本申请根据针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;在基于生物信息对目标对象进行身份验证的过程中,在服务页面中显示目标对象的生物信息对应的卡通信息;显示目标订单的生物结算信息。由此可见,本申请提出的装置可以在服务页面显示目标对象的生物信息对应的卡通信息,提高了目标对象的生物信息的安全性,并且,不直接显示目标对象的生物信息,也可以减少因直接显示目标对象的生物信息而给目标对象带来的视觉冲击,从而提高目标对象使用生物信息对目标订单进行结算的兴趣。
根据本申请的一个实施例,图11所示的信息处理装置1和图12所示的信息处理装置2中的各个模块可以分别或全部合并为一个或若干个单元来构成,或者其中的某个(些)单元还可以再拆分为功能上更小的多个子单元,可以实现同样的操作,而不影响本申请的实施例的技术效果的实现。上述模块是基于逻辑功能划分的,在实际应用中,一个模块的功能也可以由多个单元来实现,或者多个模块的功能由一个单元实现。在本申请的其它实施例中,信息处理装置1和信息处理装置2也可以包括其它单元,在实际应用中,这些功能也可以由其它单元协助实现,并且可以由多个单元协作实现。
根据本申请的一个实施例,可以通过在包括中央处理单元(CPU)、随机存取存储介质(RAM)、只读存储介质(ROM)等处理元件和存储元件的 例如计算机的通用计算机设备上运行能够执行如图3或图7中所示的相应方法所涉及的各步骤的计算机程序(包括程序代码),来构造如图11中的信息处理装置1或图12中所示的信息处理装置2,以及来实现本申请实施例的信息处理方法。上述计算机程序可以记载于例如计算机可读记录介质上,并通过计算机可读记录介质装载于上述计算设备中,并在其中运行。
请参见图13,图13是本申请提供的一种计算机设备的结构示意图。如图13所示,计算机设备1000可以包括:处理器1001,网络接口1004和存储器1005,此外,计算机设备1000还可以包括:用户接口1003,和至少一个通信总线1002。其中,通信总线1002用于实现这些组件之间的连接通信。其中,用户接口1003可以包括显示屏(Display)、键盘(Keyboard),可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如WI-FI接口)。存储器1005可以是高速RAM存储器,也可以是非不稳定的存储器(non-volatile memory),例如至少一个磁盘存储器。存储器1005可选的还可以是至少一个位于远离前述处理器1001的存储装置。如图13所示,作为一种计算机存储介质的存储器1005中可以包括操作系统、网络通信模块、用户接口模块以及设备控制应用程序。
在图13所示的计算机设备1000中,网络接口1004可提供网络通讯功能;而用户接口1003主要用于为用户提供输入的接口;而处理器1001可以用于调用存储器1005中存储的设备控制应用程序,以实现本申请实施例提供的信息处理方法。
应当理解,本申请实施例中所描述的计算机设备1000可执行前文图3或图7对应实施例中对上述信息处理方法的描述,也可执行前文图11所对应实施例中对上述信息处理装置1的描述以及前文图12所对应实施例中对上述信息处理装置2的描述,在此不再赘述。另外,对采用相同方法的有益效果描述,也不再进行赘述。
此外,这里需要指出的是:本申请还提供了一种计算机可读存储介质,且计算机可读存储介质中存储有前文提及的信息处理装置1和信息处理装置2所执行的计算机程序,且计算机程序包括程序指令,当处理器执行程序指令时,能够执行前文图3或图7所对应实施例中对信息处理方法的描述,因此,这里将不再进行赘述。另外,对采用相同方法的有益效果描述,也不再进行赘述。对于本申请所涉及的计算机存储介质实施例中未披露的技术细节,请参照本申请方法实施例的描述。
作为示例,上述程序指令可被部署在一个计算机设备上执行,或者被部署位于一个地点的多个计算机设备上执行,又或者,在分布在多个地点且通过通信网络互连的多个计算机设备上执行,分布在多个地点且通过通信网络互连的多个计算机设备可以组成区块链网络。
上述计算机可读存储介质可以是前述任一实施例提供的信息处理装置或者上述计算机设备的内部存储单元,例如计算机设备的硬盘或内存。该计算机可读存储介质也可以是该计算机设备的外部存储设备,例如该计算机设备上配备的插接式硬盘,智能存储卡(smart media card,SMC),安全数字(secure digital,SD)卡,闪存卡(flash card)等。进一步地,该计算机可读存储介质还可以既包括该计算机设备的内部存储单元也包括外部存储设备。该计算机可读存储介质用于存储该计算机程序以及该计算机设备所需的其他程序和数据。该计算机可读存储介质还可以用于暂时地存储已经输出或者将要输出的数据。
本申请提供了一种计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该计算机设备执行前文图3或图7对应实施例中对上述信息处理方法的描述,因此,这里将不再进行赘述。另外,对采用相同方法的有益效果描述,也不再进行赘述。对于本申请所涉及的计算机可读存储介质实施例中未披露的技术细节,请参照本申请方法实施例的描述。
以上所揭露的仅为本申请较佳实施例而已,当然不能以此来限定本申请之权利范围,因此依本申请权利要求所作的等同变化,仍属本申请所涵盖的范围。

Claims (20)

  1. 一种信息处理方法,由计算机设备执行,所述方法包括:
    响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;所述生物结算操作用于触发基于所述生物信息对所述目标对象进行身份验证,并根据身份验证结果进行针对所述目标订单的结算;
    在基于所述生物信息对所述目标对象进行身份验证的过程中,在所述服务页面中显示所述目标对象的生物信息对应的卡通信息;
    显示所述目标订单的生物结算信息;所述生物结算信息至少根据对于所述目标对象的身份验证结果确定。
  2. 根据权利要求1所述的方法,所述目标对象的生物信息包括拍摄所述目标对象得到的第i帧人脸视频帧和第j帧人脸视频帧,i小于j,i和j均为正整数;所述第i帧人脸视频帧和第j帧人脸视频帧各自具备所述目标对象的人脸显示属性;所述目标对象的生物信息对应的卡通信息包括所述第i帧人脸视频帧对应的卡通人脸视频帧和所述第j帧人脸视频帧对应的卡通人脸视频帧;
    所述在所述服务页面中显示所述目标对象的生物信息对应的卡通信息,包括:
    在所述第i帧人脸视频帧对应的第一时刻,在所述服务页面中按照所述第i帧人脸视频帧具备的人脸显示属性,显示所述第i帧人脸视频帧对应的卡通人脸视频帧;
    当从所述第一时刻到达所述第j帧人脸视频帧对应的第二时刻时,在所述服务页面中按照所述第j帧人脸视频帧具备的人脸显示属性,显示所述第j帧人脸视频帧对应的卡通人脸视频帧。
  3. 根据权利要求1所述的方法,所述目标对象的生物信息包括所述目标对象的人脸图像;所述目标对象的生物信息对应的卡通信息包括与所述目标对象的人脸图像相对应的卡通人脸图像;
    所述在所述服务页面中显示所述目标对象的生物信息对应的卡通信息,包括:
    在所述服务页面中按照所述目标对象的人脸图像的人脸显示属性,显示所述卡通人脸图像;
    所述人脸显示属性包括以下至少一种:人脸姿态属性、人脸表情属性、人脸配饰属性。
  4. 根据权利要求1所述的方法,所述目标对象的生物信息包括所述目标对象的掌纹图像;所述目标对象的生物信息对应的卡通信息包括与所述目标对象的掌纹图像相对应的卡通掌纹图像;
    所述在所述服务页面中显示所述目标对象的生物信息对应的卡通信息,包括:
    在所述服务页面中按照所述目标对象的掌纹图像的掌纹显示属性,显示所述卡通掌纹图像;
    所述掌纹显示属性包括以下至少一种:掌纹姿态属性、掌纹配饰属性。
  5. 根据权利要求1所述的方法,所述目标对象的生物信息包括所述目标对象的瞳孔图像;所述目标对象的生物信息对应的卡通信息包括与所述目标对象的瞳孔图像相对应的卡通瞳孔图像;
    所述在所述服务页面中显示所述目标对象的生物信息对应的卡通信息,包括:
    在所述服务页面中按照所述目标对象的瞳孔图像的瞳孔显示属性,显示所述卡通瞳孔图像;
    所述瞳孔显示属性包括以下至少一种:瞳孔张合属性、瞳孔配饰属性。
  6. 根据权利要求1所述的方法,所述方法还包括:
    在所述服务页面中显示背景选择列表;所述背景选择列表包括M种背景信息;M为正整数;
    根据针对所述M种背景信息的选择操作,将所选择的背景信息确定为所述卡通信息的目标背景信息;
    所述在所述服务页面中显示所述目标对象的所述生物信息对应的卡通信息,包括:
    在所述服务页面中同步显示所述卡通信息和所述目标背景信息。
  7. 根据权利要求1所述的方法,其特征在于,基于所述生物信息对所述目标对象的身份验证成功时,所述生物结算信息包括结算成功信息;基于所述生物信息对所述目标对象的身份验证失败时,所述生物结算信息包括结算失败信息。
  8. 根据权利要求1所述的方法,所述生物结算结果包括结算确认信息;所述显示所述目标订单的生物结算结果,包括:
    若检测到基于所述生物信息对所述目标对象的身份验证成功,则显示所述结算确认信息;所述结算确认信息用于支持针对所述目标订单进行结算;
    所述方法还包括:
    根据针对所述结算确认信息的确认操作,对所述目标订单进行结算。
  9. 根据权利要求8所述的方法,所述根据针对所述结算确认信息的确认操作,对所述目标订单进行结算,包括:
    根据所述确认操作显示账户选择列表;所述账户选择列表包括与所述目标对象相关联的N个结算账户,N为正整数;
    根据针对所述账户选择列表中的N个结算账户的选择操作,将所选择的结算账户确定为目标结算账户;
    采用所述目标结算账户对所述目标订单进行结算。
  10. 一种信息处理方法,由计算机设备执行,所述方法包括:
    响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;所述生物结算操作用于触发基于所述生物信息对所述目标对象进行身份验证,并根据身份验证结果进行针对所述目标订单的结算;
    基于所述生物信息对所述目标对象进行身份验证,并对所述生物信息进行卡通转换,得到所述生物信息对应的卡通信息;
    在基于所述生物信息对所述目标对象进行身份验证的过程中,在所述服务页面中显示所述卡通信息;
    显示所述目标订单的生物结算信息;所述生物结算信息至少根据对于所述目标对象的身份验证结果确定。
  11. 根据权利要求10所述的方法,所述生物信息包括所述目标对象的L个人脸视频帧;L为正整数;
    所述基于所述生物信息对所述目标对象进行身份验证,包括:
    从所述L个人脸视频帧中选取目标视频帧;
    根据所述目标视频帧对所述目标对象进行身份验证。
  12. 根据权利要求11所述的方法,所述根据所述目标视频帧对所述目标对象进行身份验证,包括:
    获取所述目标视频帧对应的深度视频帧;所述深度视频帧包括所述目标对象的人脸深度信息;
    从所述深度视频帧包括的所述人脸深度信息中获取所述目标对象的五官深度信息;
    根据所述目标视频帧获取所述目标对象的五官平面信息;
    根据所述五官平面信息和所述五官深度信息,对所述目标对象进行身份验证。
  13. 根据权利要求11所述的方法,所述对所述生物信息进行卡通转换,得到所述生物信息对应的卡通信息,包括:
    获取卡通转换模型;
    通过所述卡通转换模块,分别提取所述L个人脸视频帧包括的人脸局部图像;
    通过所述卡通转换模型,分别生成每个所述人脸视频帧包括的人脸局部图像对应的卡通人脸图像;
    将每个所述人脸视频帧包括的人脸局部图像对应的卡通人脸图像确定为所述卡通信息。
  14. 根据权利要求13所述的方法,所述方法还包括:
    获取初始卡通转换模型;所述初始卡通转换模型包括卡通生成器和卡通判别器;
    通过所述卡通生成器,根据样本人脸图像生成所述样本人脸图像对应的样本卡通人脸图像;
    通过所述卡通判别器,根据所述样本卡通人脸图像,判别所述样本卡通人脸图像属于卡通类型图像的卡通概率;
    基于所述卡通概率,修正所述卡通生成器的模型参数和所述卡通判别器的模型参数;
    当所述卡通生成器和所述卡通判别器均满足模型训练标准时,将所述卡通生成器确定为所述卡通转换模型。
  15. 根据权利要求14所述的方法,所述卡通概率包括第一阶段卡通概率和第二阶段卡通概率;
    所述基于所述卡通概率,修正所述卡通生成器的模型参数和所述卡通判别器的模型参数,包括:
    在针对所述初始卡通转换模型的第一阶段训练过程中,保持所述卡通判别器的模型参数不变,根据所述第一阶段卡通概率修正所述卡通生成器的模型参数,得到所述卡通生成器的修正后的模型参数;
    在针对所述初始卡通转换模型的第二阶段训练过程中,保持所述卡通生成器的修正后的模型参数不变,根据所述第二阶段卡通概率修正所述卡通判别器的模型参数,得到所述卡通判别器的修正后的模型参数。
  16. 一种信息处理装置,所述装置包括:
    第一信息采集模块,用于响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;所述生物结算操作用于触发基于所述生物信息对所述目标对象进行身份验证,并根据身份验证结果进行针对所述目标订单的结算;
    第一信息显示模块,用于在基于所述生物信息对所述目标对象进行身份验证的过程中,在所述服务页面中显示所述目标对象的生物信息对应的卡通信息;
    第一结算模块,用于显示所述目标订单的生物结算信息;所述生物结算信息至少根据对于所述目标对象的身份验证结果确定。
  17. 一种信息处理装置,所述装置包括:
    第二信息采集模块,用于响应于针对目标订单的生物结算操作,显示服务页面,并采集目标对象的生物信息;所述生物结算操作用于触发基于所述生物信息对所述目标对象进行身份验证,并根据身份验证结果进行针对所述目标订单的结算;
    信息转换模块,用于基于所述生物信息对所述目标对象进行身份验证,并对所述生物信息进行卡通转换,得到所述生物信息对应的卡通信息;
    第二信息显示模块,用于在基于所述生物信息对所述目标对象进行身份验证的过程中,在所述服务页面中显示所述卡通信息;
    第二结算模块,用于显示所述目标订单的生物结算信息;所述生物结算信息至少根据对于所述目标对象的身份验证结果确定。
  18. 一种计算机设备,其特征在于,包括存储器和处理器,所述存储器存储有计算机程序,所述计算机程序被所述处理器执行时,使得所述处理器执行权利要求1-15中任一项所述方法的步骤。
  19. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质存储有计算机程序,所述计算机程序适用于由处理器加载并执行权利要求1-15任一项所述的方法。
  20. 一种计算机程序产品,包括指令,当其在计算机上运行时,使得计算机实现如权利要求1-15中任一项所述的方法。
PCT/CN2022/084826 2021-04-23 2022-04-01 信息处理方法、装置、计算机设备和存储介质 WO2022222735A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/993,208 US20230082150A1 (en) 2021-04-23 2022-11-23 Information processing method and apparatus, computer device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110441935.3 2021-04-23
CN202110441935.3A CN113762969B (zh) 2021-04-23 2021-04-23 信息处理方法、装置、计算机设备和存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/993,208 Continuation US20230082150A1 (en) 2021-04-23 2022-11-23 Information processing method and apparatus, computer device, and storage medium

Publications (1)

Publication Number Publication Date
WO2022222735A1 true WO2022222735A1 (zh) 2022-10-27

Family

ID=78786921

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/084826 WO2022222735A1 (zh) 2021-04-23 2022-04-01 信息处理方法、装置、计算机设备和存储介质

Country Status (3)

Country Link
US (1) US20230082150A1 (zh)
CN (1) CN113762969B (zh)
WO (1) WO2022222735A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113762969B (zh) * 2021-04-23 2023-08-08 腾讯科技(深圳)有限公司 信息处理方法、装置、计算机设备和存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106611114A (zh) * 2015-10-21 2017-05-03 中兴通讯股份有限公司 一种设备使用权限的确定方法和装置
JP2017208638A (ja) * 2016-05-17 2017-11-24 レノボ・シンガポール・プライベート・リミテッド 虹彩認証装置、虹彩認証方法、及びプログラム
CN112106046A (zh) * 2018-05-14 2020-12-18 三星电子株式会社 用于执行生物特征认证的电子设备及其操作方法
WO2021039229A1 (ja) * 2019-08-30 2021-03-04 日本電気株式会社 処理装置、処理システム、処理方法及びプログラム
CN113762969A (zh) * 2021-04-23 2021-12-07 腾讯科技(深圳)有限公司 信息处理方法、装置、计算机设备和存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101555347B1 (ko) * 2009-04-09 2015-09-24 삼성전자 주식회사 비디오 기반 얼굴 애니메이션 생성 장치 및 방법
CN105118023B (zh) * 2015-08-31 2017-12-15 电子科技大学 基于人脸特征点的实时视频人脸卡通化生成方法
CN109508974B (zh) * 2018-11-29 2023-08-22 华南理工大学 一种基于特征融合的购物结账系统和方法
CN111625793B (zh) * 2019-02-27 2023-06-23 阿里巴巴集团控股有限公司 身份识别、订单支付、子人脸库建立方法、装置及设备、订单支付系统
CN109871834A (zh) * 2019-03-20 2019-06-11 北京字节跳动网络技术有限公司 信息处理方法和装置
CN110689352A (zh) * 2019-08-29 2020-01-14 广州织点智能科技有限公司 人脸支付确认方法、装置、计算机设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106611114A (zh) * 2015-10-21 2017-05-03 中兴通讯股份有限公司 一种设备使用权限的确定方法和装置
JP2017208638A (ja) * 2016-05-17 2017-11-24 レノボ・シンガポール・プライベート・リミテッド 虹彩認証装置、虹彩認証方法、及びプログラム
CN112106046A (zh) * 2018-05-14 2020-12-18 三星电子株式会社 用于执行生物特征认证的电子设备及其操作方法
WO2021039229A1 (ja) * 2019-08-30 2021-03-04 日本電気株式会社 処理装置、処理システム、処理方法及びプログラム
CN113762969A (zh) * 2021-04-23 2021-12-07 腾讯科技(深圳)有限公司 信息处理方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
CN113762969A (zh) 2021-12-07
US20230082150A1 (en) 2023-03-16
CN113762969B (zh) 2023-08-08

Similar Documents

Publication Publication Date Title
US11017070B2 (en) Visual data processing of response images for authentication
US11936647B2 (en) Identity verification method and apparatus, storage medium, and computer device
AU2021206815B2 (en) Method of Host-Directed Illumination and System for Conducting Host-Directed Illumination
EP3528156B1 (en) Virtual reality environment-based identity authentication method and apparatus
US10430679B2 (en) Methods and systems for detecting head motion during an authentication transaction
US20150186708A1 (en) Biometric identification system
CN112364825B (zh) 用于人脸识别的方法、装置和计算机可读存储介质
CN112396004A (zh) 用于人脸识别的方法、装置和计算机可读存储介质
WO2022222735A1 (zh) 信息处理方法、装置、计算机设备和存储介质
WO2023034251A1 (en) Spoof detection based on challenge response analysis
US20220277311A1 (en) A transaction processing system and a transaction method based on facial recognition
US20240028698A1 (en) System and method for perfecting and accelerating biometric identification via evolutionary biometrics via continual registration
US11792189B1 (en) Systems and methods for authenticating a user using an image capture device
WO2022089220A1 (zh) 图像数据处理方法、装置、设备、存储介质及产品
CN113642519A (zh) 一种人脸识别系统和人脸识别方法
CN112487885A (zh) 支付方法、装置、电子设备及可读存储介质
CN115497146B (zh) 模型的训练方法和装置、身份验证方法和装置
US20240115175A1 (en) Communication apparatus, communication method, and non-transitory computer-readable storage medium
CN115690922A (zh) 生物识别方法、装置、计算机设备、存储介质和程序产品
CN111598031A (zh) 一种人脸识别方法及系统
CN115578089A (zh) 资源转移方法、装置、计算机设备和存储介质
CN115204829A (zh) 双人人脸识别的合约处理方法、系统、设备、存储介质
CN113961297A (zh) 眨眼截屏方法、系统、装置及存储介质
CN112270219A (zh) 一种用于人脸识别方法及系统

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: 22790844

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 22.02.2024)