Bank property protection method and device based on face recognition payment

Abstract

The invention discloses a bank property protection method and device based on face recognition payment, and the method comprises the steps: displaying an image collection page when a payment request carrying a user account is received; obtaining a to-be-recognized face image shot by a user based on the prompt information in the image acquisition page, and obtaining a first face image and a second face image of a user account in an image database; inputting the to-be-recognized face image, the first face image and the second face image into a pre-trained face model to obtain a face recognition result; and when the facial recognition result indicates that the to-be-recognized facial image is consistent with the first facial image and the to-be-recognized facial image contains facial features, displaying prompt information of payment abnormity, and locking the user account. By comparing the to-be-recognized facial image with the first facial image and the second facial image, if the to-be-recognized facial image is matched with the first facial image but not matched with the second facial image, the system recognizes the risk and locks the account, so that the property safety is ensured, and the financial loss is avoided.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and in particular to a bank property protection method and device based on face recognition payment. Background Art

[0002] In recent years, telecommunications fraud has indeed posed a great challenge to the property safety of the elderly. Although the state and all sectors of society have taken a variety of preventive measures, the elderly are still vulnerable to fraud.

[0003] At present, many local governments or financial institutions have launched special anti-fraud apps, which can monitor fraudulent calls, text messages, apps, etc. in real time, automatically identify potential fraud information, and issue warnings to users in a timely manner. However, as fraud methods are constantly updated and changed, the identification technology of anti-fraud apps may lag behind and fail to identify new fraud methods in a timely manner, resulting in property losses.

[0004] Therefore, how to ensure that property safety is not threatened and avoid any form of financial loss has become an urgent problem to be solved in this field. Summary of the invention

[0005] The present application provides a bank property protection method and device based on face recognition payment, the purpose of which is to ensure that property security is not threatened and avoid any form of financial loss.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] A bank property protection method based on face recognition payment, comprising:

[0008] When a payment request is received with a user account, the image acquisition page is displayed;

[0009] Acquire a facial image to be recognized taken by the user based on the prompt information in the image acquisition page, and acquire a first facial image and a second facial image corresponding to the user account pre-stored in an image database; wherein the first facial image is used for normal payment, and the second facial image includes facial features;

[0010] Inputting the facial image to be recognized, the first facial image, and the second facial image into a pre-trained facial model to obtain a facial recognition result;

[0011] When the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image, and the facial image to be recognized contains the facial features, displaying a prompt message indicating payment abnormality and locking the user account;

[0012] After the user account is locked, a prompt message of the payment anomaly is sent to the abnormal contact person of the user account.

[0013] Optionally, before displaying the image acquisition page in response to the payment request triggered by the user, the method further includes:

[0014] When receiving a request to establish a user account, collecting a first facial image and a second facial image of the user;

[0015] Obtaining contact information of abnormal contacts of the user account;

[0016] An association relationship is established between the first facial image, the second facial image, the contact information of the abnormal contact, and the user account.

[0017] Optionally, before displaying the image acquisition page in response to the payment request triggered by the user, the method further includes:

[0018] When receiving a request to establish a user account, collecting a first facial image and a plurality of second facial images of the user; wherein one of the second facial images includes a facial feature;

[0019] Obtaining contact information of at least one abnormal contact of the user account;

[0020] For each of the second facial images, setting a risk level for the second facial image; wherein the risk level includes a low risk level, a medium risk level, and a high risk level;

[0021] determining, according to the risk level, contact information of an abnormal contact of the user account corresponding to the second facial image;

[0022] An association relationship is established between the first facial image, the second facial image, the contact information of the abnormal contact of the user account corresponding to the second facial image, and the user account.

[0023] Optionally, also include:

[0024] When the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image, and the facial image to be recognized includes the facial feature, determining a second facial image corresponding to the facial feature;

[0025] When the risk level of the second facial image is a high risk level, location information of the mobile terminal to which the user account belongs is obtained, and the location information is sent to an abnormal contact person corresponding to the highest risk level.

[0026] Optionally, the step of inputting the facial image to be recognized, the first facial image, and the second facial image into a pre-trained facial model to obtain a facial recognition result includes:

[0027] Inputting the facial image to be identified and the first facial image into a first subnetwork to obtain a first result; wherein the first result indicates whether the facial image to be identified and the first facial image are consistent;

[0028] Inputting the facial image to be identified and the second facial image into a second sub-network to obtain a second result; wherein the second result indicates whether the facial image to be identified contains the facial features;

[0029] The first result and the second result are input into a joint discriminant network to obtain a facial recognition result.

[0030] Optionally, also include:

[0031] When an account recovery request is received within the lock time of the user account, displaying an interface for obtaining the first account status recovery password;

[0032] When receiving the first account status recovery password input on the first account status recovery password acquisition interface, sending acquisition information of the second account status recovery password to the abnormal contact of the user account;

[0033] When the second account status recovery password sent by the abnormal contact is received, the user account is restored to a normal state.

[0034] Optionally, also include:

[0035] When an account recovery request is received within the lock time of the user account, displaying a group photo collection interface;

[0036] When a group photo of the abnormal contact and the user taken based on the prompt information in the group photo collection interface is received, the user account is restored to a normal state.

[0037] A bank property protection device based on face recognition payment, comprising:

[0038] A display unit, configured to display an image acquisition page when receiving a payment request carrying a user account;

[0039] an acquisition unit, configured to acquire a facial image to be recognized taken by the user based on the prompt information in the image acquisition page, and to acquire a first facial image and a second facial image corresponding to the user account pre-stored in an image database; wherein the first facial image is used for normal payment, and the second facial image includes facial features;

[0040] A recognition unit, configured to input the facial image to be recognized, the first facial image, and the second facial image into a pre-trained facial model to obtain a facial recognition result;

[0041] a locking unit, configured to display payment abnormality prompt information and lock the user account when the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image and the facial image to be recognized contains the facial features;

[0042] The sending unit is used to send the payment abnormality prompt information to the abnormal contact person of the user account after the user account is locked.

[0043] Optionally, also include:

[0044] A first collecting unit is used to collect a first facial image and a second facial image of a user when receiving a request to establish a user account;

[0045] A first target acquisition unit, configured to acquire contact information of an abnormal contact of the user account;

[0046] The first establishing unit is used to establish an association relationship between the first facial image, the second facial image, the contact information of the abnormal contact and the user account.

[0047] Optionally, also include:

[0048] A second collection unit is used to collect a first facial image and a plurality of second facial images of the user when receiving a request to establish a user account; wherein one of the second facial images contains a facial feature;

[0049] A second target acquisition unit, configured to acquire contact information of at least one abnormal contact of the user account;

[0050] A setting unit, configured to set a risk level for each of the second facial images; wherein the risk level includes a low risk level, a medium risk level, and a high risk level;

[0051] a first determining unit, configured to determine, according to the risk level, contact information of an abnormal contact of the user account corresponding to the second facial image;

[0052] The second establishing unit is used to establish an association relationship between the first facial image, the second facial image, the contact information of the abnormal contact of the user account corresponding to the second facial image, and the user account.

[0053] The technical solution provided by the present application is to display an image acquisition page when a payment request carrying a user account is received; obtain a facial image to be identified taken by the user based on the prompt information in the image acquisition page, and obtain a first facial image and a second facial image corresponding to the user account pre-stored in an image database; input the facial image to be identified, the first facial image, and the second facial image into a pre-trained facial model to obtain a facial recognition result; when the facial recognition result indicates that the facial image to be identified is consistent with the first facial image, and the facial image to be identified contains facial features, display a payment abnormality prompt message and lock the user account; when the user account is locked, send a payment abnormality prompt message to the abnormal contact of the user account. By comparing the facial image to be identified, the first facial image, and the second facial image, it can be identified that the facial image to be identified is consistent with the first facial image, but does not match the features of the second facial image, indicating that the user account may be at risk, and the user account will be locked to ensure that the property safety is not threatened, thereby avoiding any form of financial loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 A flow chart of a bank property protection method based on face recognition payment provided in an embodiment of the present application;

[0056] Figure 2 A flowchart of a method for establishing an association relationship between a user account and an abnormal contact provided in an embodiment of the present application;

[0057] Figure 3 A flowchart of another method for establishing an association relationship between a user account and an abnormal contact provided in an embodiment of the present application;

[0058] Figure 4 A flowchart of a method for identifying a facial image to be identified provided in an embodiment of the present application;

[0059] Figure 5 A flowchart of a method for restoring a user account provided in an embodiment of the present application;

[0060] Figure 6 A schematic diagram of the architecture of a bank property protection device based on face recognition payment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0062] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0063] like Figure 1 As shown, it is a flow chart of a bank property protection method based on face recognition payment provided by an embodiment of the present application, comprising the following steps:

[0064] S101: When a payment request carrying a user account is received, an image acquisition page is displayed.

[0065] When a payment request carrying a user account is received from a client, an image acquisition page is displayed so that the user can perform image acquisition according to the prompt information on the image acquisition page.

[0066] Optionally, before step S101, it is necessary to pre-establish an association relationship between the user account and the abnormal contact person to ensure the security of the user account and prevent property loss when the user account is stolen. Therefore, a method for establishing an association relationship between a user account and an abnormal contact person is provided in another embodiment of the present application, such as Figure 2 As shown, the following steps are included:

[0067] S201: When a request to establish a user account is received, a first facial image and a second facial image of the user are collected.

[0068] The first facial image is used for normal payment, and the second facial image includes facial features, which include at least facial expressions and facial movements.

[0069] Optionally, facial expressions include but are not limited to: slightly closed eyes and sleepy expression, and facial movements include but are not limited to: biting the upper lip, slightly sticking out the tongue and other non-subconscious movements.

[0070] S202: Obtain contact information of abnormal contacts of the user account.

[0071] Among them, abnormal contacts include but are not limited to user relatives or bank specialists, and contact information includes but is not limited to: telephone number.

[0072] S203: Establishing an association relationship between the first facial image, the second facial image, the contact information of the abnormal contact, and the user account.

[0073] It is understandable that the association between the first facial image, the second facial image, the contact information of the abnormal contact and the user account is established to enhance the security of the user account. Specifically, this association may be used for identity authentication or recovery process, such as confirming the identity of the account holder through facial recognition or verifying contact information.

[0074] Optionally, before step S101, it is necessary to pre-establish associations between the user account and multiple abnormal contacts. When the user account is stolen, different processes are performed according to the risk level of the theft, thereby reducing the impact of a single security vulnerability on the account. Therefore, another method for establishing an association between a user account and an abnormal contact is provided in another embodiment of the present application, such as Figure 3 As shown, the following steps are included:

[0075] S301: When a request for establishing a user account is received, a first facial image and a plurality of second facial images of the user are collected.

[0076] Wherein, a second facial image includes a facial feature.

[0077] It is understandable that when a request to establish a user account is received, a first facial image and at least two second facial images of the user are collected, different second facial images include different facial expressions or facial movements, and different facial expressions or facial movements correspond to different abnormal contacts.

[0078] S302: Obtain contact information of at least one abnormal contact of the user account.

[0079] It should be noted that the specific implementation of step S302 may refer to step S202 accordingly, and will not be repeated here.

[0080] S303: For each second facial image, set a risk level for the second facial image.

[0081] Among them, risk levels include low risk level, medium risk level, and high risk level.

[0082] It can be understood that by establishing different risk levels for different facial features, different risk levels are established for different second facial images.

[0083] For example, there are three second facial images, namely second facial image 1, second facial image 2, and second facial image 3. For each second facial image, the risk level set for second facial image 1 is a low risk level, the risk level set for second facial image 3 is a high risk level, and the risk level set for second facial image 2 is a medium risk level.

[0084] S304: Determine contact information of abnormal contacts of the user account corresponding to the second facial image according to the risk level.

[0085] It can be understood that the contact information of the abnormal contact of the user account corresponding to the second facial image is determined according to the risk level. Specifically, when the risk level of the second facial image is low risk level and medium risk level, the abnormal contact of the user account corresponding to the second facial image is the user's relative or a bank specialist; when the risk level of the second facial image is high risk level, the abnormal contact of the user account corresponding to the second facial image is an emergency handler.

[0086] S305: Establishing an association relationship between the first facial image, the second facial image, the contact information of the abnormal contact of the user account corresponding to the second facial image, and the user account.

[0087] It should be noted that the specific implementation of step S305 may refer to step S203 accordingly, and will not be repeated here.

[0088] Optionally, after step S305, when the facial recognition result indicates that the facial image to be identified is consistent with the first facial image, and the facial image to be identified contains facial features, corresponding processing is performed according to the risk level corresponding to the facial features, and different levels of theft can be intervened to different degrees, avoiding overreaction to low-risk theft, while ensuring that high-risk theft can be handled in a timely and strict manner, thereby improving overall efficiency and security. Therefore, in another embodiment of the present application, a high-risk level processing method is provided, including:

[0089] When the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image, and the facial image to be recognized includes facial features, a second facial image corresponding to the facial features is determined.

[0090] It can be understood that when the facial recognition result indicates that the facial image to be identified is consistent with the first facial image, and the facial image to be identified contains facial features, it means that there is a certain risk in the user account at this time, and the second facial image corresponding to the facial features is first obtained so that the corresponding alarm operation can be performed based on the second facial image later.

[0091] When the risk level of the second facial image is a high risk level, the location information of the mobile terminal to which the user account belongs is obtained, and the location information is sent to the abnormal contact person corresponding to the highest risk level.

[0092] It can be understood that when the risk level of the second facial image is a high risk level, the contact information of the abnormal contact is the emergency number. The emergency number is dialed first, and then the location information of the mobile terminal to which the user account belongs is obtained, and the location information is sent to the abnormal contact corresponding to the highest risk level.

[0093] S102: Acquire a facial image to be recognized that is taken by the user based on prompt information in the image acquisition page, and acquire a first facial image and a second facial image corresponding to the user account that are pre-stored in an image database.

[0094] The first facial image is used for normal payment, and the second facial image includes facial features.

[0095] It can be understood that the first facial image and the second facial image corresponding to the user account are obtained so as to compare the facial image to be identified based on the first facial image and the second facial image to confirm whether the image to be identified uses the image of the user of the user account.

[0096] S103: Inputting the facial image to be recognized, the first facial image and the second facial image into a pre-trained facial model to obtain a facial recognition result.

[0097] When the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image and the facial image to be recognized does not contain facial features, the payment operation is completed.

[0098] It should be noted that the facial model is a pre-trained model, which is pre-trained based on sample facial images as input and the facial recognition results of the sample facial images manually annotated as training targets. Specifically, the facial model can be a convolutional neural network model or a deep neural network model.

[0099] Optionally, in another embodiment of the present application, the specific implementation of step S103 is as follows: Figure 4 As shown, the following steps are included:

[0100] S401: Inputting a facial image to be recognized and a first facial image into a first sub-network to obtain a first result.

[0101] The first result indicates whether the facial image to be recognized is consistent with the first facial image.

[0102] It can be understood that by inputting the facial image to be identified and the first facial image into the first subnetwork, a first result is obtained, that is, whether the user account corresponding to the first facial image is the user account of the facial image to be identified, that is, whether the user corresponding to the facial image to be identified is the holder of the user account.

[0103] S402: Input the facial image to be recognized and the second facial image into the second sub-network to obtain a second result.

[0104] The second result indicates whether the facial image to be identified contains facial features.

[0105] It can be understood that the facial image to be identified and the second facial image are input into the second sub-network, and the second result obtained is the result of whether the facial image to be identified contains the facial features carried by the second facial image.

[0106] S403: Input the first result and the second result into a joint discriminant network to obtain a facial recognition result.

[0107] It can be understood that when the first result and the second result are input into the joint discriminant network, the facial recognition results obtained are: the facial image to be identified is consistent with the first facial image, and the facial image to be identified contains facial features, the facial image to be identified is consistent with the first facial image, and the facial image to be identified does not contain facial features, the facial image to be identified is inconsistent with the first facial image, and the facial image to be identified contains facial features, and the facial image to be identified is inconsistent with the first facial image, and the facial image to be identified does not contain facial features.

[0108] It is understandable that when the facial image to be identified is inconsistent with the first facial image, the user corresponding to the facial image to be identified is not the holder of the user account, and a prompt message indicating payment failure is fed back.

[0109] S104: When the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image, and the facial image to be recognized contains facial features, a prompt message of payment abnormality is displayed, and the user account is locked.

[0110] It can be understood that when the facial recognition result indicates that the facial image to be identified is consistent with the first facial image and the facial image to be identified contains facial features, it means that the user account is at risk at this time. In order to ensure the property of the user account, a prompt message of payment abnormality is displayed and the user account is locked.

[0111] It should be emphasized that a prompt message of payment abnormality is displayed, and the user account is locked for a preset time (for example, 30 minutes).

[0112] S105: After the user account is locked, a payment abnormality prompt message is sent to the abnormal contact person of the user account.

[0113] When a user's account is locked and payment anomalies occur, the user's emergency contacts or abnormal contacts will be contacted to ensure the security of the account. These contacts may be trusted people set by the user in advance, or third parties marked as contacts in the system. By notifying these contacts in a timely manner, malicious or unauthorized operations can be prevented from continuing, thereby reducing the risk of account abuse or theft.

[0114] Optionally, after step S105, by providing an account recovery step, it can be ensured that the recovery request is initiated by the legitimate owner of the account, in order to ensure the security of account recovery and avoid unauthorized access. Therefore, in another embodiment of the present application, a method for recovering a user account is provided, such as Figure 5 As shown, the following steps are included:

[0115] S501: When an account recovery request is received within the lock time of the user account, an interface for obtaining a first account status recovery password is displayed.

[0116] It is understandable that when an account recovery request is received within the lock time of the user account, an interface for obtaining the first account status recovery password is displayed. Displaying the interface for obtaining the recovery password can clearly tell the user the status of the current account and provide clear recovery steps so that the user account can quickly return to normal.

[0117] S502: When the first account status recovery password inputted in the first account status recovery password acquisition interface is received, information for acquiring the second account status recovery password is sent to the abnormal contact of the user account.

[0118] Optionally, the first account status recovery password includes but is not limited to: SMS verification code, ID card number.

[0119] S503: When the second account status recovery password sent by the abnormal contact is received, the user account is restored to a normal state.

[0120] Optionally, the second account status recovery password includes but is not limited to: an email address and a password to the email address.

[0121] It can be understood that when the first account status recovery password and the second account status recovery password are received, it means that there is no risk in the user account at this time and the user account can be restored to a normal state.

[0122] Optionally, after step S105, another account recovery step is provided to simplify the user account recovery step. Simplifying the account recovery step can significantly improve the user experience and reduce the troubles and inconveniences caused by account problems. Therefore, another user account recovery method is provided in another embodiment of the present application, including:

[0123] When an account recovery request is received within the lock time of the user account, a group photo collection interface is displayed.

[0124] It is understandable that when an account recovery request is received within the lock time of the user account, a group photo collection interface is displayed to collect group photos of the abnormal contact and the user.

[0125] When a group photo of the abnormal contact and the user taken based on the prompt information in the group photo collection interface is received, the user account is restored to a normal state.

[0126] Among them, when a photo of an abnormal contact and the user taken based on the prompt information in the photo collection interface is received, it means that there is no risk in the user account at this time, and the user account can be restored to a normal state.

[0127] To summarize, by comparing the facial image to be identified, the first facial image and the second facial image, it can be identified that when the facial image to be identified is consistent with the first facial image but does not match the features of the second facial image, it indicates that the user account may be at risk, and the user account will be locked to ensure that property safety is not threatened, thereby avoiding any form of financial loss.

[0128] like Figure 6 As shown, it is a schematic diagram of the architecture of a bank property protection device based on face recognition payment provided in an embodiment of the present application. The bank property protection device includes: a display unit 100, an acquisition unit 200, an identification unit 300, a locking unit 400 and a sending unit 500.

[0129] The display unit 100 is used to display the image acquisition page when receiving a payment request carrying a user account.

[0130] The acquisition unit 200 is used to acquire the facial image to be identified taken by the user based on the prompt information in the image acquisition page, and to acquire the first facial image and the second facial image corresponding to the user account pre-stored in the image database; wherein the first facial image is used for normal payment, and the second facial image includes facial features.

[0131] The recognition unit 300 is used to input the facial image to be recognized, the first facial image and the second facial image into a pre-trained facial model to obtain a facial recognition result.

[0132] The recognition unit 300 is specifically used to: input the facial image to be recognized and the first facial image into the first subnetwork to obtain a first result; wherein the first result indicates whether the facial image to be recognized and the first facial image are consistent; input the facial image to be recognized and the second facial image into the second subnetwork to obtain a second result; wherein the second result indicates whether the facial image to be recognized contains facial features; input the first result and the second result into the joint discriminant network to obtain a facial recognition result.

[0133] The locking unit 400 is used to display payment abnormality prompt information and lock the user account when the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image and the facial image to be recognized contains facial features.

[0134] The sending unit 500 is used to send payment abnormality prompt information to the abnormal contact person of the user account after the user account is locked.

[0135] To summarize, by comparing the facial image to be identified, the first facial image and the second facial image, it can be identified that when the facial image to be identified is consistent with the first facial image but does not match the features of the second facial image, it indicates that the user account may be at risk, and the user account will be locked to ensure that property safety is not threatened, thereby avoiding any form of financial loss.

[0136] Preferably, combined Figure 6 As shown in the figure, the bank property protection device also includes: a first acquisition unit, a first target acquisition unit and a first establishment unit.

[0137] The first collecting unit is used to collect the first facial image and the second facial image of the user when receiving a request to establish a user account.

[0138] The first target acquisition unit is used to acquire contact information of abnormal contacts of the user account.

[0139] The first establishing unit is used to establish an association relationship between the first facial image, the second facial image, the contact information of the abnormal contact and the user account.

[0140] Preferably, combined Figure 6 According to the content shown, the bank property protection device also includes: a second collection unit, a second target acquisition unit, a setting unit, a first determination unit and a second establishment unit.

[0141] The second collection unit is used to collect a first facial image and multiple second facial images of the user when receiving a request to establish a user account; wherein a second facial image contains a facial feature.

[0142] The second target acquisition unit is used to acquire contact information of at least one abnormal contact of the user account.

[0143] The setting unit is used to set a risk level for each second facial image; wherein the risk level includes a low risk level, a medium risk level, and a high risk level.

[0144] The first determining unit is used to determine the contact information of the abnormal contact of the user account corresponding to the second facial image according to the risk level.

[0145] The second establishing unit is used to establish an association relationship between the first facial image, the second facial image, the contact information of the abnormal contact of the user account corresponding to the second facial image, and the user account.

[0146] Preferably, combined Figure 6 As shown in the figure, the bank property protection device also includes: a second determining unit and a first information sending unit.

[0147] The second determining unit is used to determine a second facial image corresponding to the facial features when the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image and the facial image to be recognized contains facial features.

[0148] The first information sending unit is used to obtain the location information of the mobile terminal to which the user account belongs when the risk level of the second facial image is a high risk level, and send the location information to the abnormal contact person corresponding to the highest risk level.

[0149] Preferably, combined Figure 6 As shown in the content, the bank property protection device also includes: a first interface display unit, a second information sending unit and a first recovery unit.

[0150] The first interface display unit is used to display an interface for obtaining a first account status recovery password when an account recovery request is received within the lock time of the user account.

[0151] The second information sending unit is configured to send information for obtaining the second account status recovery password to an abnormal contact of the user account when receiving the first account status recovery password input on the first account status recovery password obtaining interface.

[0152] The first restoring unit is configured to restore the user account to a normal state upon receiving a second account status recovery password sent by the abnormal contact.

[0153] Preferably, combined Figure 6 As shown in the figure, the bank property protection device also includes: a second interface display unit and a second recovery unit.

[0154] A second interface display unit, configured to display a group photo collection interface when an account recovery request is received within the lock time of the user account;

[0155] The second restoring unit is configured to restore the user account to a normal state when receiving a group photo of the abnormal contact and the user taken based on the prompt information in the group photo collection interface.

[0156] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative work.

[0157] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0158] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A bank property protection method based on face recognition payment, characterized in that: include: When a payment request is received with a user account, the image acquisition page is displayed; Acquire a facial image to be recognized taken by the user based on the prompt information in the image acquisition page, and acquire a first facial image and a second facial image corresponding to the user account pre-stored in an image database; wherein the first facial image is used for normal payment, and the second facial image includes facial features; Inputting the facial image to be recognized, the first facial image, and the second facial image into a pre-trained facial model to obtain a facial recognition result; When the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image, and the facial image to be recognized contains the facial features, displaying a prompt message indicating payment abnormality and locking the user account; After the user account is locked, a prompt message of the payment anomaly is sent to the abnormal contact person of the user account.

2. The method according to claim 1, characterized in that The method further includes, before displaying the image acquisition page in response to the payment request triggered by the user: When receiving a request to establish a user account, collecting a first facial image and a second facial image of the user; Obtaining contact information of abnormal contacts of the user account; An association relationship is established between the first facial image, the second facial image, the contact information of the abnormal contact, and the user account.

3. The method according to claim 1, characterized in that The method further includes, before displaying the image acquisition page in response to the payment request triggered by the user: When receiving a request to establish a user account, collecting a first facial image and a plurality of second facial images of the user; wherein one of the second facial images includes a facial feature; Obtaining contact information of at least one abnormal contact of the user account; For each of the second facial images, setting a risk level for the second facial image; wherein the risk level includes a low risk level, a medium risk level, and a high risk level; determining, according to the risk level, contact information of an abnormal contact of the user account corresponding to the second facial image; An association relationship is established between the first facial image, the second facial image, the contact information of the abnormal contact of the user account corresponding to the second facial image, and the user account.

4. The method according to claim 3, characterized in that Also includes: When the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image, and the facial image to be recognized includes the facial feature, determining a second facial image corresponding to the facial feature; When the risk level of the second facial image is a high risk level, location information of the mobile terminal to which the user account belongs is obtained, and the location information is sent to an abnormal contact person corresponding to the highest risk level.

5. The method according to claim 1, characterized in that The step of inputting the facial image to be recognized, the first facial image, and the second facial image into a pre-trained facial model to obtain a facial recognition result includes: Inputting the facial image to be identified and the first facial image into a first subnetwork to obtain a first result; wherein the first result indicates whether the facial image to be identified and the first facial image are consistent; Inputting the facial image to be identified and the second facial image into a second sub-network to obtain a second result; wherein the second result indicates whether the facial image to be identified contains the facial features; The first result and the second result are input into a joint discriminant network to obtain a facial recognition result.

6. The method according to claim 1, characterized in that Also includes: When an account recovery request is received within the lock time of the user account, displaying an interface for obtaining the first account status recovery password; When receiving the first account status recovery password input on the first account status recovery password acquisition interface, sending acquisition information of the second account status recovery password to the abnormal contact of the user account; When the second account status recovery password sent by the abnormal contact is received, the user account is restored to a normal state.

7. The method according to claim 1, characterized in that Also includes: When an account recovery request is received within the lock time of the user account, displaying a group photo collection interface; When a group photo of the abnormal contact and the user taken based on the prompt information in the group photo collection interface is received, the user account is restored to a normal state.

8. A bank property protection device based on face recognition payment, characterized in that: include: A display unit, configured to display an image acquisition page when receiving a payment request carrying a user account; an acquisition unit, configured to acquire a facial image to be recognized taken by the user based on the prompt information in the image acquisition page, and to acquire a first facial image and a second facial image corresponding to the user account pre-stored in an image database; wherein the first facial image is used for normal payment, and the second facial image includes facial features; A recognition unit, configured to input the facial image to be recognized, the first facial image, and the second facial image into a pre-trained facial model to obtain a facial recognition result; a locking unit, configured to display payment abnormality prompt information and lock the user account when the facial recognition result indicates that the facial image to be recognized is consistent with the first facial image and the facial image to be recognized contains the facial features; The sending unit is used to send the payment abnormality prompt information to the abnormal contact person of the user account after the user account is locked.

9. The device according to claim 8, characterized in that Also includes: A first collecting unit is used to collect a first facial image and a second facial image of a user when receiving a request to establish a user account; A first target acquisition unit, configured to acquire contact information of an abnormal contact of the user account; The first establishing unit is used to establish an association relationship between the first facial image, the second facial image, the contact information of the abnormal contact and the user account.

10. The device according to claim 8, characterized in that Also includes: A second collection unit is used to collect a first facial image and a plurality of second facial images of the user when receiving a request to establish a user account; wherein one of the second facial images contains a facial feature; A second target acquisition unit, configured to acquire contact information of at least one abnormal contact of the user account; A setting unit, configured to set a risk level for each of the second facial images; wherein the risk level includes a low risk level, a medium risk level, and a high risk level; a first determining unit, configured to determine, according to the risk level, contact information of an abnormal contact of the user account corresponding to the second facial image; The second establishing unit is used to establish an association relationship between the first facial image, the second facial image, the contact information of the abnormal contact of the user account corresponding to the second facial image, and the user account.

Images