Identity authentication method and electronic device

Abstract

The disclosed embodiment discloses an identity authentication method and electronic device, the method comprising: obtaining first authentication operation information and second authentication operation information; obtaining speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information according to the second authentication operation information; obtaining a pre-trained target authentication operation detection model, taking the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information as input, and inputting the target authentication operation detection model to obtain an authentication operation detection result; when the authentication operation detection result meets the target authentication operation detection requirement, performing identity authentication according to the first authentication operation information. This technical solution can improve the reliability of identity authentication under the premise of low cost of identity authentication.

Description

Technical Field

[0001] The present disclosure relates to the technical field of identity authentication, and in particular to an identity authentication method and electronic device. Background Art

[0002] In recent years, with the development of communication technology, people have become increasingly dependent on the Internet in all aspects of daily life. In daily use, before a terminal device runs a more sensitive application such as a financial transaction application or a social application, it is necessary to authenticate the user of the terminal device to ensure that the user has the authority to use the application through the terminal device or the authority to use some functions of the application.

[0003] In the related art, the identity authentication password input by the user through the touch screen can be obtained by the terminal device to authenticate the user. However, when the user inputs the identity authentication password through the touch screen, it is easy for others to see it, which may lead to the leakage of the identity authentication password, and the reliability of the identity authentication is poor. In another technical solution, the user's physiological characteristics such as fingerprints, irises, and faces can be obtained, and the user can be authenticated based on the physiological characteristics of the user. Although the above-mentioned physiological characteristics are not easy to leak and the reliability of identity authentication is good, the cost of obtaining the above-mentioned physiological characteristics is high, which increases the cost of identity authentication. Therefore, how to improve the reliability of identity authentication while ensuring that the cost of identity authentication is low is a problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve the problems in the related art, the embodiments of the present disclosure provide an identity authentication method and an electronic device.

[0005] In a first aspect, an embodiment of the present disclosure provides an identity authentication method, which is applied to a terminal device and includes:

[0006] Acquire first authentication operation information and second authentication operation information, the first authentication operation information including image data of the touch trajectory, and the second authentication operation information including touch positions, touch time, touch force, and touch area of ​​multiple sampling points in the touch trajectory;

[0007] acquiring, according to the second authentication operation information, speed distribution information corresponding to the touch position and touch time, acceleration distribution information corresponding to the touch position and touch time, touch area distribution information corresponding to the touch position and touch time, and touch force distribution information corresponding to the touch position and touch time;

[0008] Obtain a pre-trained target authentication operation detection model, take the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information as input, and input the target authentication operation detection model to obtain an authentication operation detection result;

[0009] When the authentication operation detection result meets the target authentication operation detection requirement, identity authentication is performed according to the first authentication operation information.

[0010] In an implementation of the present disclosure, before obtaining the first authentication operation information and the second authentication operation information, the method further includes:

[0011] receiving the updated weight parameters sent by the edge server, and updating the private authentication operation detection model according to the updated weight parameters;

[0012] Obtaining a real-time identity authentication log, the real-time identity authentication log including first authentication operation information, second authentication operation information, and identity authentication result corresponding to at least one identity authentication operation collected in real time;

[0013] acquiring speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to each identity authentication operation according to second authentication operation information corresponding to each identity authentication operation;

[0014] Taking first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to the authentication operation in the real-time authentication log as input, and taking the authentication result corresponding to the authentication operation in the real-time authentication log as output, training the updated private authentication operation detection model;

[0015] When the trained private authentication operation detection model has not converged, a gradient update vector is obtained according to the trained private authentication operation detection model, and the gradient update vector is sent, and the edge server is used to aggregate the gradient update vector, and update the weight parameter of the shared authentication operation detection model of the edge server according to the aggregated gradient update vector to obtain the updated weight parameter;

[0016] When the trained private authentication operation detection model converges, a target authentication operation detection model is obtained according to the trained private authentication operation detection model.

[0017] In one implementation of the present disclosure, the identity authentication result of an adjacent identity authentication operation adjacent to a successful identity authentication operation whose corresponding identity authentication result in a real-time identity authentication log is successful authentication is also successful authentication, and the identity authentication method of the adjacent identity authentication operation is different from the identity authentication method of the successful identity authentication operation, and the time difference between the identity authentication moment of the adjacent identity authentication operation and the identity authentication moment of the successful identity authentication operation is less than or equal to the identity authentication time difference threshold.

[0018] In an implementation of the present disclosure, before receiving the updated weight parameter sent by the edge server and updating the private authentication operation detection model according to the updated weight parameter, the method further includes:

[0019] Receive private data upload instructions;

[0020] In response to a private data upload instruction, send a real-time identity authentication log;

[0021] Receiving initial weight parameters sent by the edge server;

[0022] The initial authentication operation detection model is updated according to the initial weight parameters to obtain a private authentication operation detection model.

[0023] In one implementation of the present disclosure, in response to the private data upload instruction, before sending the real-time identity authentication log, the method further includes:

[0024] Adding noise to the real-time authentication log to obtain a noisy real-time authentication log;

[0025] Send real-time authentication logs, including:

[0026] Send Noise real-time authentication logs.

[0027] In one implementation of the present disclosure, before receiving the private data upload instruction, the method further includes:

[0028] Send user characteristic information, which includes the gender information, age information, education level information, left-right hand preference information, identity authentication method preference information and application preference information of the user corresponding to the terminal device. The edge server is used to determine multiple target terminal devices based on the user characteristic information and send private data upload instructions to the target terminal devices.

[0029] In a second aspect, an embodiment of the present disclosure provides an identity authentication method, which is applied to an edge server and includes:

[0030] Receiving a gradient update vector sent by a terminal device;

[0031] Aggregating the gradient update vectors, and updating the weight parameters of the shared authentication operation detection model according to the aggregated gradient update vectors to obtain updated weight parameters;

[0032] The updated weight parameter is sent, and the terminal device is used to update the private authentication operation detection model according to the updated weight parameter.

[0033] In an implementation of the present disclosure, before receiving the gradient update vector sent by the terminal device, the method further includes:

[0034] Determine multiple target terminal devices, and send private data upload instructions to the target terminal devices;

[0035] Receiving a real-time identity authentication log sent by a target terminal device, the real-time identity authentication log including first authentication operation information, second authentication operation information, and identity authentication result corresponding to at least one identity authentication operation collected in real time;

[0036] Obtain a shared identity authentication log according to the real-time identity authentication log, use the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to the identity authentication operation in the shared identity authentication log as input, use the identity authentication result corresponding to the identity authentication operation in the shared identity authentication log as output, and train the initial authentication operation detection model to obtain a shared authentication operation detection model;

[0037] Initial weight parameters are obtained according to the shared authentication operation detection model and the initial weight parameters are sent. The terminal device is used to update the initial authentication operation detection model of the terminal device according to the initial weight parameters to obtain a private authentication operation detection model.

[0038] In an implementation of the present disclosure, before determining a plurality of target terminal devices, the method further includes:

[0039] Receiving user characteristic information sent by multiple terminal devices, the user characteristic information including gender information, age information, education level information, left-hand preference information, identity authentication method preference information, and application preference information of users corresponding to the terminal devices;

[0040] Identify multiple target end devices, including:

[0041] A plurality of target terminal devices are determined according to the user characteristic information, and a private data upload instruction is sent to the target terminal devices.

[0042] In a third aspect, an embodiment of the present disclosure provides an electronic device, the electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement any one of the methods in the first aspect or any one of the second aspect.

[0043] In a fourth aspect, a computer-readable storage medium is provided in an embodiment of the present disclosure, on which computer instructions are stored, wherein the computer instructions, when executed by a processor, implement any method in the first aspect or any method in the second aspect.

[0044] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0045] In the above technical solution, by obtaining the first authentication operation information and the second authentication operation information, the first authentication operation information includes the image data of the touch trajectory, and the second authentication operation information includes the touch position, touch time, touch force and touch area of ​​multiple sampling points in the touch trajectory; according to the second authentication operation information, the speed distribution information corresponding to the touch position and touch time, the acceleration distribution information corresponding to the touch position and touch time, the touch area distribution information corresponding to the touch position and touch time, and the touch force distribution information corresponding to the touch position and touch time are obtained; the pre-trained target authentication operation detection model is obtained, and the first authentication operation information, the speed distribution information, the acceleration distribution information, the touch area distribution information and the touch force distribution information are used as inputs, and the target authentication operation detection model is input to obtain the authentication operation detection result; when the authentication operation detection result meets the target authentication operation detection requirements, identity authentication is performed according to the first authentication operation information. Among them, since the speed distribution information, the acceleration distribution information, the touch area distribution information and the touch force distribution information obtained according to the second authentication operation information can feedback the behavioral characteristics of the user in the process of inputting the touch trajectory, the behavioral characteristics are usually closely related to the user's personal input habits, and the personal input habits of different users usually have certain differences. Therefore, even if the first authentication operation information corresponding to the authentication operation of any two users is the same (that is, the shape of the touch trajectory is the same), the second authentication operation information corresponding to the authentication operation of the any two users also has certain differences. Therefore, the authentication operation detection results obtained according to the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information corresponding to the authentication operation of different users are different. When the authentication operation detection result meets the target authentication operation detection requirements, it can be confirmed that the authentication operation is made by the user corresponding to the terminal device, and the identity authentication operation can be performed according to the first authentication operation information. Therefore, the technical solution of the present application improves the reliability of identity authentication under the premise of low cost of identity authentication.

[0046] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Other features, objectives and advantages of the present disclosure will become more apparent through the following detailed description of non-limiting embodiments in conjunction with the accompanying drawings. In the accompanying drawings:

[0048] Figure 1 A schematic structural block diagram of an identity authentication system according to an embodiment of the present disclosure is shown;

[0049] Figure 2 A schematic flow chart showing an identity authentication method according to an embodiment of the present disclosure;

[0050] Figure 3 A schematic flow chart showing an identity authentication method according to an embodiment of the present disclosure;

[0051] Figure 4 A schematic structural block diagram of an identity authentication device according to an embodiment of the present disclosure is shown;

[0052] Figure 5 A schematic structural block diagram of an identity authentication device according to an embodiment of the present disclosure is shown;

[0053] Figure 6 A schematic structural block diagram of an electronic device according to an embodiment of the present disclosure is shown;

[0054] Figure 7 It is a structural diagram of an electronic device suitable for implementing the identity authentication method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0055] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0056] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, behaviors, components, parts, or a combination thereof disclosed in the specification, and do not exclude the possibility that one or more other features, numbers, steps, behaviors, components, parts, or a combination thereof exist or are added.

[0057] It should also be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0058] The details of the embodiments of the present disclosure are described in detail below through specific examples.

[0059] In recent years, with the development of communication technology, people have become increasingly dependent on the Internet in all aspects of their daily lives. Usually, the terminal devices used by people can access the Internet through network devices that are closer to them. Among them, the terminal devices can be smart mobile communication terminals, wearable devices, desktops, laptops, tablets, etc., and the terminal devices can be wireless routers, wired routers, wireless gateways, etc.

[0060] In daily use, before a terminal device runs a more sensitive application such as a financial transaction application or a social application, it is necessary to authenticate the user of the terminal device to ensure that the user has the authority to use the application through the terminal device or the authority to use some of the functions in the application.

[0061] For example, before a user uses the payment function of a payment application running on a terminal device to pay for an order, the user using the terminal device needs to be authenticated to confirm that the account corresponding to the user using the terminal device and the order payment is owned by the user.

[0062] In the related art, the identity authentication password input by the user through the touch screen can be obtained by the terminal device to authenticate the user. However, when the user inputs the identity authentication password through the touch screen, it is easy for others to see it, which may lead to the leakage of the identity authentication password, and the reliability of the identity authentication is poor. In another technical solution, the user's physiological characteristics such as fingerprints, irises, and faces can be obtained, and the user can be authenticated based on the physiological characteristics of the user. Although the above-mentioned physiological characteristics are not easy to leak and the reliability of identity authentication is good, the cost of obtaining the above-mentioned physiological characteristics is high, which increases the cost of identity authentication. Therefore, how to improve the reliability of identity authentication while ensuring that the cost of identity authentication is low is a problem that needs to be solved urgently.

[0063] Taking the above-mentioned defects into consideration, in the technical solution provided by the present disclosure, by obtaining first authentication operation information and second authentication operation information, the first authentication operation information includes image data of the touch trajectory, and the second authentication operation information includes touch positions, touch time, touch force and touch area of ​​multiple sampling points in the touch trajectory; according to the second authentication operation information, speed distribution information corresponding to the touch position and touch time, acceleration distribution information corresponding to the touch position and touch time, touch area distribution information corresponding to the touch position and touch time, and touch force distribution information corresponding to the touch position and touch time are obtained; a pre-trained target authentication operation detection model is obtained, and the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information are used as inputs, and input into the target authentication operation detection model to obtain an authentication operation detection result; when the authentication operation detection result meets the target authentication operation detection requirement, identity authentication is performed according to the first authentication operation information. Among them, since the speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information obtained according to the second authentication operation information can feedback the behavior characteristics of the user in the process of inputting the touch trajectory, and since the behavior characteristics are usually closely related to the user's personal input habits, and the personal input habits of different users usually have certain differences. Therefore, even if the first authentication operation information corresponding to the authentication operation of any two users is the same (that is, the shape of the touch trajectory is the same), the second authentication operation information corresponding to the authentication operation of the any two users also has certain differences. Therefore, the authentication operation detection results obtained according to the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information corresponding to the authentication operation of different users are different. When the authentication operation detection result meets the target authentication operation detection requirements, it can be confirmed that the authentication operation is made by the user corresponding to the terminal device, and the identity authentication operation can be performed according to the first authentication operation information. Therefore, the technical solution of the present application improves the reliability of identity authentication under the premise of low cost of identity authentication.

[0064] Figure 1 A schematic structural block diagram of an identity authentication system according to an embodiment of the present disclosure is shown, wherein the identity authentication system includes a terminal device 101, an edge server 102, and a network 103, wherein the network 103 is used to provide a medium for a communication link between the terminal device 101 and the edge server 102, and the network 103 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0065] The terminal device 101 is a variety of electronic devices with network access function, including but not limited to mobile communication terminals, desktop computers, tablet computers, laptops, wearable devices, etc.

[0066] The edge server 102 may be a cloud server or a server provided by an identity authentication service provider. It should be noted that in the embodiment of the present application, one edge server 102 may correspond to multiple terminal devices 101. For example, the identity authentication service provider may divide the area under its jurisdiction into multiple blocks, and multiple terminal devices 101 in each area correspond to one edge server 102.

[0067] Figure 2 FIG. 1 is a schematic flow chart of an identity authentication method according to an embodiment of the present disclosure, and the identity authentication method is applied to a terminal device. Figure 2 As shown, the identity authentication method includes the following steps:

[0068] In step S101, first authentication operation information and second authentication operation information are obtained.

[0069] The first authentication operation information includes image data of the touch track, and the second authentication operation information includes touch positions, touch time, touch force, and touch area of ​​multiple sampling points in the touch track.

[0070] In one embodiment of the present disclosure, the first authentication operation information and the second authentication operation information can be obtained through a touch screen, which can be a touch screen on a terminal device or a touch screen in other devices or systems that is wired or wirelessly connected to the terminal device.

[0071] In step S102, speed distribution information corresponding to the touch position and touch time, acceleration distribution information corresponding to the touch position and touch time, touch area distribution information corresponding to the touch position and touch time, and touch force distribution information corresponding to the touch position and touch time are obtained based on the second authentication operation information.

[0072] The speed distribution information is used to indicate the speed of the user's limb movement in contact with the touch screen at different touch times and different touch positions. The speed distribution information can be multiple point values ​​or one or more continuous values.

[0073] The acceleration distribution information is used to indicate the acceleration values ​​at different touch times and different touch positions when the user's limbs are in contact with the touch screen. The acceleration distribution information can be multiple point values ​​or one or more continuous values.

[0074] The touch area distribution information is used to indicate the values ​​of the contact area between the user's limb and the touch screen at different touch times and different touch positions. The touch area distribution information can be multiple point values ​​or one or more continuous values.

[0075] The touch force distribution information is used to indicate the value of the force with which the user's limbs in contact with the touch screen press the touch screen at different touch times and different touch positions. The touch force distribution information can be multiple point values ​​or one or more continuous values.

[0076] In step S103, a pre-trained target authentication operation detection model is obtained, and the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information are used as inputs to the target authentication operation detection model to obtain the authentication operation detection result.

[0077] In one embodiment of the present disclosure, the target authentication operation detection model may be pre-stored in the terminal device, or may be obtained from other devices or systems.

[0078] The target authentication operation detection model can be a neural network (NN) model, a convolutional neural network (CNN) model or a long short-term memory network (LSTM) model, etc.

[0079] In step S104, when the authentication operation detection result meets the target authentication operation detection requirement, identity authentication is performed according to the first authentication operation information.

[0080] In one embodiment of the present disclosure, the authentication operation test result satisfies the target authentication operation test requirement, which can be understood as the value of the authentication operation test result belonging to the authentication operation test value that satisfies the requirement indicated by the target authentication operation test requirement, or the value of the authentication operation test result belonging to the authentication operation test value range that satisfies the requirement indicated by the target authentication operation test requirement.

[0081] In this embodiment, by obtaining first authentication operation information and second authentication operation information, the first authentication operation information includes image data of the touch trajectory, and the second authentication operation information includes the touch position, touch time, touch force and touch area of ​​multiple sampling points in the touch trajectory; according to the second authentication operation information, the speed distribution information corresponding to the touch position and touch time, the acceleration distribution information corresponding to the touch position and touch time, the touch area distribution information corresponding to the touch position and touch time, and the touch force distribution information corresponding to the touch position and touch time are obtained; a pre-trained target authentication operation detection model is obtained, and the first authentication operation information, the speed distribution information, the acceleration distribution information, the touch area distribution information and the touch force distribution information are used as inputs, and input into the target authentication operation detection model to obtain the authentication operation detection result; when the authentication operation detection result meets the target authentication operation detection requirements, identity authentication is performed according to the first authentication operation information. Among them, since the speed distribution information, the acceleration distribution information, the touch area distribution information and the touch force distribution information obtained according to the second authentication operation information can feedback the behavioral characteristics of the user in the process of inputting the touch trajectory, the behavioral characteristics are usually closely related to the user's personal input habits, and the personal input habits of different users usually have certain differences. Therefore, even if the first authentication operation information corresponding to the authentication operation of any two users is the same (that is, the shape of the touch trajectory is the same), the second authentication operation information corresponding to the authentication operation of the any two users also has certain differences. Therefore, the authentication operation detection results obtained according to the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information corresponding to the authentication operation of different users are different. When the authentication operation detection result meets the target authentication operation detection requirements, it can be confirmed that the authentication operation is made by the user corresponding to the terminal device, and the identity authentication operation can be performed according to the first authentication operation information. Therefore, the technical solution of the present application improves the reliability of identity authentication under the premise of low cost of identity authentication.

[0082] In an implementation of the present disclosure, before obtaining the first authentication operation information and the second authentication operation information in step S101, the method further includes:

[0083] receiving the updated weight parameters sent by the edge server, and updating the private authentication operation detection model according to the updated weight parameters;

[0084] Obtaining a real-time identity authentication log, the real-time identity authentication log including first authentication operation information, second authentication operation information, and identity authentication result corresponding to at least one identity authentication operation collected in real time;

[0085] acquiring speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to each identity authentication operation according to second authentication operation information corresponding to each identity authentication operation;

[0086] Taking first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to the authentication operation in the real-time authentication log as input, and taking the authentication result corresponding to the authentication operation in the real-time authentication log as output, training the updated private authentication operation detection model;

[0087] When the trained private authentication operation detection model has not converged, a gradient update vector is obtained according to the trained private authentication operation detection model, and the gradient update vector is sent, and the edge server is used to aggregate the gradient update vector, and update the weight parameter of the shared authentication operation detection model of the edge server according to the aggregated gradient update vector to obtain the updated weight parameter;

[0088] When the trained private authentication operation detection model converges, a target authentication operation detection model is obtained according to the trained private authentication operation detection model.

[0089] In one embodiment of the present disclosure, the real-time identity authentication log may be obtained by reading the real-time identity authentication log pre-stored in the terminal device, or by receiving the real-time identity authentication log sent by other devices or systems.

[0090] In one embodiment of the present disclosure, both the private authentication operation detection model and the shared authentication operation detection model can be a neural network model, a convolutional neural network model, a long short-term memory network model, or the like.

[0091] In one embodiment of the present disclosure, a target authentication operation detection model is obtained based on a trained private authentication operation detection model. This can be understood as storing the trained private authentication operation detection model as a target authentication operation detection model, or can be understood as directly identifying the trained private authentication operation detection model as a target authentication operation detection model.

[0092] In this implementation manner, the updated weight parameter sent by the edge server and received by the terminal device is obtained by the edge server aggregating the gradient update vectors sent by multiple terminal devices, and updating the weight parameter of the shared authentication operation detection model of the edge server according to the aggregated gradient update vectors. Therefore, the updated shared authentication operation detection model can reflect the shared authentication result rules between the real-time authentication logs of multiple terminal devices and the authentication results of the multiple terminal devices learned by the shared authentication operation detection model of the edge server in the previous round of training; by obtaining the speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information corresponding to each authentication operation according to the second authentication operation information corresponding to each authentication operation, taking the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information corresponding to the authentication operation in the real-time authentication log as input, and taking the authentication result corresponding to the authentication operation in the real-time authentication log as output, the updated private authentication operation detection model is trained, so that the updated private authentication operation detection model can learn the shared authentication result rules after learning the shared authentication result rules. On the basis of the authentication result rule, it is also possible to personalize the learning of the data collected when the terminal device itself performs identity authentication, so that the trained private authentication operation detection model can learn the private identity authentication result rule between the real-time identity authentication log of the terminal device itself and the identity authentication result of the terminal device itself; when the trained private authentication operation detection model has not converged, it means that the trained private authentication operation detection model still needs to continue to be trained, and by obtaining the gradient update vector according to the trained private authentication operation detection model and sending the gradient update vector, the edge server can continue to obtain the corresponding update weight parameters based on the gradient update vectors uploaded by multiple terminal devices without leaking the user's personal data of the terminal device, thereby continuing to train the private authentication operation detection model of each terminal device; when the trained private authentication operation detection model converges, the converged private authentication operation detection model can obtain the authentication operation detection result based on the input first authentication operation information, velocity distribution information, acceleration distribution information, touch area distribution information and touch force distribution information, so the converged private authentication operation detection model is used as the target authentication operation detection model.

[0093] In one implementation of the present disclosure, the identity authentication result of an adjacent identity authentication operation adjacent to a successful identity authentication operation whose corresponding identity authentication result in a real-time identity authentication log is successful authentication is also successful authentication, and the identity authentication method of the adjacent identity authentication operation is different from the identity authentication method of the successful identity authentication operation, and the time difference between the identity authentication moment of the adjacent identity authentication operation and the identity authentication moment of the successful identity authentication operation is less than or equal to the identity authentication time difference threshold.

[0094] In this embodiment, since the identity authentication result of the adjacent identity authentication operation adjacent to the successful identity authentication operation whose corresponding identity authentication result is successful authentication is also successful authentication, and the identity authentication method of the adjacent identity authentication operation is different from the identity authentication method of the successful identity authentication operation, and the time difference between the identity authentication moment of the adjacent identity authentication operation and the identity authentication moment of the successful identity authentication operation is less than or equal to the identity authentication time difference threshold, the probability of the successful identity authentication operation whose identity authentication result is successful authentication being misauthenticated is relatively small, thereby improving the reliability of the target authentication operation detection model obtained by training based on the real-time identity authentication log.

[0095] In an implementation of the present disclosure, before receiving the updated weight parameter sent by the edge server and updating the private authentication operation detection model according to the updated weight parameter, the method further includes:

[0096] Receive private data upload instructions;

[0097] In response to a private data upload instruction, send a real-time identity authentication log;

[0098] Receiving initial weight parameters sent by the edge server;

[0099] The initial authentication operation detection model is updated according to the initial weight parameters to obtain a private authentication operation detection model.

[0100] Among them, the initial authentication operation detection model can be a neural network model, a convolutional neural network model or a long short-term memory network model, etc. The initial authentication operation detection model can be understood as an untrained model.

[0101] In this embodiment, by receiving a private data upload instruction and sending a real-time identity authentication log in response to the private data upload instruction, the edge server can obtain speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information based on the second authentication operation information in the real-time identity authentication log, and preliminarily train its own initial authentication operation detection model based on the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, touch force distribution information, and the identity authentication result to obtain a shared authentication operation detection model. At this time, the shared authentication operation detection model can be understood as a model that has preliminarily learned the common identity authentication result rules between the real-time identity authentication logs of multiple terminal devices and the identity authentication results of the multiple terminal devices. Afterwards, the terminal device updates the initial authentication operation detection model according to the initial weight parameters obtained by the shared authentication operation detection model to obtain a private authentication operation detection model. The private authentication operation detection model can be understood as a model that has learned the rules learned by the shared authentication operation detection model, that is, at this time, the private authentication operation detection model can also be understood as a model that has preliminarily learned the rules of shared identity authentication results of multiple terminal devices, thereby facilitating multiple rounds of training of the private authentication operation detection model, without the need for training based on the initial authentication operation detection model, thereby reducing the difficulty of training.

[0102] In one implementation of the present disclosure, before sending the real-time identity authentication log in response to the private data upload instruction, the method further includes:

[0103] Adding noise to the real-time authentication log to obtain a noisy real-time authentication log;

[0104] Send real-time authentication logs, including:

[0105] Send Noise real-time authentication logs.

[0106] The adding of noise to the real-time identity authentication log may be adding random noise to the real-time identity authentication log, or adding Laplace noise to the real-time identity authentication log.

[0107] In this implementation, by adding noise to the real-time identity authentication log to obtain a noisy real-time identity authentication log, and sending the real-time identity authentication log, it is possible to avoid leakage of more sensitive user personal information in the real-time identity authentication log without reducing the regularity of the identity authentication results of the terminal device reflected in the real-time identity authentication log as much as possible, thereby improving the security of user personal information.

[0108] In one implementation of the present disclosure, before receiving the private data upload instruction, the method further includes:

[0109] Send user characteristic information, which includes the gender information, age information, education level information, left-right hand preference information, identity authentication method preference information and application preference information of the user corresponding to the terminal device. The edge server is used to determine multiple target terminal devices based on the user characteristic information and send private data upload instructions to the target terminal devices.

[0110] The user characteristic information may be stored in the terminal device in advance, or may be obtained from other devices or systems.

[0111] In this embodiment, since the input habits of users with different user characteristic information may vary greatly, by sending user characteristic information, the edge server determines multiple target terminal devices based on the user characteristic information, and sends private data upload instructions to the target terminal devices, it can be ensured that the real-time identity authentication log obtained by the edge server is a log of users with relatively consistent input habits when performing identity authentication operations, thereby improving the speed of convergence of the private authentication operation detection model during the training process and reducing the difficulty of training.

[0112] Figure 3 FIG. 1 is a schematic flow chart of an identity authentication method according to an embodiment of the present disclosure, and the identity authentication method is applied to an edge server. Figure 3 As shown, the authentication operation detection method includes the following steps:

[0113] In step S201, a gradient update vector sent by a terminal device is received.

[0114] In step S202, the gradient update vectors are aggregated, and the weight parameters of the shared authentication operation detection model are updated according to the aggregated gradient update vectors to obtain updated weight parameters.

[0115] In step S203, the updated weight parameter is sent, and the terminal device is used to update the private authentication operation detection model according to the updated weight parameter.

[0116] In one embodiment of the present disclosure, the shared authentication operation detection model may be a neural network model, a convolutional neural network model, a long short-term memory network model, or the like.

[0117] In this embodiment, the gradient update vector is obtained by the terminal device using the first authentication operation information corresponding to the authentication operation in the real-time authentication log and the speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information obtained according to the second authentication operation information corresponding to the authentication operation in the real-time authentication log as input, and the authentication result corresponding to the authentication operation in the real-time authentication log as output, to train the updated private authentication operation detection model, and when the trained private authentication operation detection model does not converge, it is obtained according to the trained private authentication operation detection model. The edge server aggregates the gradient update vectors and updates the weight parameters of the shared authentication operation detection model according to the aggregated gradient update vectors. The updated shared authentication operation detection model can reflect the shared authentication result rules between the real-time authentication log of the terminal device and the authentication result of the terminal device learned by the private authentication operation detection models of multiple terminal devices in the previous round of training. By sending the updated weight parameter, the terminal device is used to update the private authentication operation detection model according to the updated weight parameter. The private authentication operation detection model can learn the private identity authentication result rules between the terminal device's own real-time identity authentication log and the terminal device's own identity authentication result, and can also learn the common identity authentication result rules, thereby improving the accuracy of the authentication operation detection results obtained based on the private authentication operation detection model.

[0118] In an implementation of the present disclosure, in step S201, before receiving the gradient update vector sent by the terminal device, the method further includes:

[0119] Determine multiple target terminal devices, and send private data upload instructions to the target terminal devices;

[0120] Receiving a real-time identity authentication log sent by a target terminal device, the real-time identity authentication log including first authentication operation information, second authentication operation information, and identity authentication result corresponding to at least one identity authentication operation collected in real time;

[0121] Obtain a shared identity authentication log according to the real-time identity authentication log, use the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to the identity authentication operation in the shared identity authentication log as input, use the identity authentication result corresponding to the identity authentication operation in the shared identity authentication log as output, and train the initial authentication operation detection model to obtain a shared authentication operation detection model;

[0122] Initial weight parameters are obtained according to the shared authentication operation detection model and the initial weight parameters are sent. The terminal device is used to update the initial authentication operation detection model of the terminal device according to the initial weight parameters to obtain a private authentication operation detection model.

[0123] Among them, the initial authentication operation detection model can be a neural network model, a convolutional neural network model or a long short-term memory network model, etc. The initial authentication operation detection model can be understood as an untrained model.

[0124] In this embodiment, by determining multiple target terminal devices and sending private data upload instructions to the target terminal devices, the target terminal devices can be made to send real-time identity authentication logs in response to the private data upload instructions, and then receive the real-time identity authentication logs sent by the target terminal devices, and obtain the shared identity authentication logs based on the real-time identity authentication logs. The first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to the identity authentication operation in the shared identity authentication log are used as inputs, and the identity authentication results corresponding to the identity authentication operations in the shared identity authentication log are used as outputs. The initial authentication operation detection model is trained to obtain a shared authentication operation detection model. At this time, the shared authentication operation detection model can be understood as a model that has been preliminarily learned about the rules of shared identity authentication results between the real-time identity authentication logs of multiple terminal devices and the identity authentication results of the multiple terminal devices. Afterwards, initial weight parameters are obtained according to the shared authentication operation detection model, and the initial weight parameters are sent, so that the terminal device is used to update the initial authentication operation detection model of the terminal device according to the initial weight parameters to obtain a private authentication operation detection model. At this time, the private authentication operation detection model can be understood as a model that has learned the rules learned by the shared authentication operation detection model, that is, at this time, the private authentication operation detection model can also be understood as a model after preliminary learning of the rules of shared identity authentication results of multiple terminal devices, thereby facilitating multiple rounds of training of the private authentication operation detection model, without the need for training based on the initial authentication operation detection model, thereby reducing the difficulty of training.

[0125] In an implementation of the present disclosure, before determining a plurality of target terminal devices, the method further includes:

[0126] Receiving user characteristic information sent by multiple terminal devices, the user characteristic information including gender information, age information, education level information, left-hand preference information, identity authentication method preference information, and application preference information of users corresponding to the terminal devices;

[0127] Identify multiple target end devices, including:

[0128] A plurality of target terminal devices are determined according to the user characteristic information, and a private data upload instruction is sent to the target terminal devices.

[0129] In this embodiment, since the input habits of users with different user characteristic information may vary greatly, by receiving user characteristic information sent by multiple terminal devices, determining multiple target terminal devices based on the user characteristic information, and sending private data upload instructions to the target terminal devices, it can be ensured that the real-time identity authentication log obtained by the edge server is a log of users with relatively consistent input habits when performing identity authentication operations, thereby improving the speed of convergence of the private authentication operation detection model during the training process and reducing the difficulty of training.

[0130] The following are embodiments of the apparatus of the present disclosure, which can be used to execute embodiments of the method of the present disclosure.

[0131] According to an identity authentication device in one embodiment of the present disclosure, the identity authentication device is arranged in a terminal device, and the identity authentication device can be realized as part or all of the electronic device through software, hardware or a combination of both. Figure 4 A schematic structural block diagram of an identity authentication device according to an embodiment of the present disclosure is shown as follows: Figure 4 As shown, the identity authentication device 400 includes:

[0132] The authentication operation information acquisition module 401 is configured to acquire first authentication operation information and second authentication operation information, wherein the first authentication operation information includes image data of a touch track, and the second authentication operation information includes touch positions, touch time, touch force, and touch area of ​​multiple sampling points in the touch track;

[0133] a distribution information acquisition module 402 configured to acquire, according to the second authentication operation information, velocity distribution information corresponding to the touch position and touch time, acceleration distribution information corresponding to the touch position and touch time, touch area distribution information corresponding to the touch position and touch time, and touch force distribution information corresponding to the touch position and touch time;

[0134] The detection result acquisition module 403 is configured to acquire a pre-trained target authentication operation detection model, take the first authentication operation information, the speed distribution information, the acceleration distribution information, the touch area distribution information and the touch force distribution information as input, and input the target authentication operation detection model to acquire the authentication operation detection result;

[0135] The identity authentication module 404 is configured to perform identity authentication according to the first authentication operation information when the authentication operation detection result meets the target authentication operation detection requirement.

[0136] In this embodiment, by obtaining first authentication operation information and second authentication operation information, the first authentication operation information includes image data of the touch trajectory, and the second authentication operation information includes the touch position, touch time, touch force and touch area of ​​multiple sampling points in the touch trajectory; according to the second authentication operation information, the speed distribution information corresponding to the touch position and touch time, the acceleration distribution information corresponding to the touch position and touch time, the touch area distribution information corresponding to the touch position and touch time, and the touch force distribution information corresponding to the touch position and touch time are obtained; a pre-trained target authentication operation detection model is obtained, and the first authentication operation information, the speed distribution information, the acceleration distribution information, the touch area distribution information and the touch force distribution information are used as inputs, and input into the target authentication operation detection model to obtain the authentication operation detection result; when the authentication operation detection result meets the target authentication operation detection requirements, identity authentication is performed according to the first authentication operation information. Among them, since the speed distribution information, the acceleration distribution information, the touch area distribution information and the touch force distribution information obtained according to the second authentication operation information can feedback the behavioral characteristics of the user in the process of inputting the touch trajectory, the behavioral characteristics are usually closely related to the user's personal input habits, and the personal input habits of different users usually have certain differences. Therefore, even if the first authentication operation information corresponding to the authentication operation of any two users is the same (that is, the shape of the touch trajectory is the same), the second authentication operation information corresponding to the authentication operation of the any two users also has certain differences. Therefore, the authentication operation detection results obtained according to the first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information corresponding to the authentication operation of different users are different. When the authentication operation detection result meets the target authentication operation detection requirements, it can be confirmed that the authentication operation is made by the user corresponding to the terminal device, and the identity authentication operation can be performed according to the first authentication operation information. Therefore, the technical solution of the present application improves the reliability of identity authentication under the premise of low cost of identity authentication.

[0137] According to an identity authentication device in one embodiment of the present disclosure, the identity authentication device is arranged in an edge server, and the identity authentication device can be realized as part or all of the electronic device through software, hardware or a combination of both. Figure 5 A schematic structural block diagram of an identity authentication device according to an embodiment of the present disclosure is shown as follows: Figure 5 As shown, the identity authentication device 500 includes:

[0138] A vector receiving module 501 is configured to receive a gradient update vector sent by a terminal device;

[0139] A vector aggregation module 502 is configured to aggregate the gradient update vectors and update the weight parameters of the shared authentication operation detection model according to the aggregated gradient update vectors to obtain updated weight parameters;

[0140] The weight sending module 503 is configured to send updated weight parameters, and the terminal device is used to update the private authentication operation detection model according to the updated weight parameters.

[0141] In this embodiment, the gradient update vector is obtained by the terminal device using the first authentication operation information corresponding to the authentication operation in the real-time authentication log and the speed distribution information, acceleration distribution information, touch area distribution information and touch force distribution information obtained according to the second authentication operation information corresponding to the authentication operation in the real-time authentication log as input, and the authentication result corresponding to the authentication operation in the real-time authentication log as output, to train the updated private authentication operation detection model, and when the trained private authentication operation detection model does not converge, it is obtained according to the trained private authentication operation detection model. The edge server aggregates the gradient update vectors and updates the weight parameters of the shared authentication operation detection model according to the aggregated gradient update vectors. The updated shared authentication operation detection model can reflect the shared authentication result rules between the real-time authentication log of the terminal device and the authentication result of the terminal device learned by the private authentication operation detection models of multiple terminal devices in the previous round of training. By sending the updated weight parameter, the terminal device is used to update the private authentication operation detection model according to the updated weight parameter. The private authentication operation detection model can learn the private identity authentication result rules between the terminal device's own real-time identity authentication log and the terminal device's own identity authentication result, and can also learn the common identity authentication result rules, thereby improving the accuracy of the authentication operation detection results obtained based on the private authentication operation detection model.

[0142] The present disclosure also discloses an electronic device, Figure 6 A schematic structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. Figure 6 As shown, the electronic device 600 includes a memory 601 and a processor 602; wherein,

[0143] The memory 601 is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor 602 to implement any method in the embodiments of the present disclosure.

[0144] Figure 7 It is a structural diagram of an electronic device suitable for implementing the identity authentication method according to an embodiment of the present disclosure.

[0145] like Figure 7 As shown, the electronic device 700 includes a processing unit 701, which can be implemented as a processing unit such as a CPU, a GPU, an FPGA, and an NPU. The processing unit 701 can perform various processes in the embodiments of any of the above methods of the present disclosure according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0146] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0147] In particular, according to an embodiment of the present disclosure, any method in the above referenced embodiment of the present disclosure may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes a program code for executing any method in the embodiment of the present disclosure. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 709, and / or installed from a removable medium 711.

[0148] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the road map or block diagram can represent a part of a module, program segment or code, and the part of the module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a different order from the order marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0149] The units or modules involved in the embodiments described in the present disclosure may be implemented by software or hardware. The units or modules described may also be arranged in a processor, and the names of these units or modules do not constitute limitations on the units or modules themselves in some cases.

[0150] As another aspect, the present disclosure further provides a computer-readable storage medium, which may be a computer-readable storage medium included in the device described in the above embodiment; or a computer-readable storage medium that exists independently and is not assembled into the device. The computer-readable storage medium stores one or more programs, and the programs are used by one or more processors to execute the method described in the present disclosure.

[0151] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present disclosure is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

Claims

1. An identity authentication method, the method being applied to a terminal device, comprising: Receiving the updated weight parameter sent by the edge server, and updating the private authentication operation detection model according to the updated weight parameter; Acquire a real-time identity authentication log, wherein the real-time identity authentication log includes first authentication operation information, second authentication operation information, and identity authentication result corresponding to at least one identity authentication operation collected in real time; acquiring speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to each identity authentication operation according to second authentication operation information corresponding to each identity authentication operation; Taking first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to the authentication operation in the real-time authentication log as input, and taking the authentication result corresponding to the authentication operation in the real-time authentication log as output, training the updated private authentication operation detection model; When the trained private authentication operation detection model has not converged, a gradient update vector is obtained according to the trained private authentication operation detection model, and the gradient update vector is sent, and the edge server is used to aggregate the gradient update vector, and update the weight parameter of the shared authentication operation detection model of the edge server according to the aggregated gradient update vector to obtain the updated weight parameter; When the trained private authentication operation detection model converges, obtaining a target authentication operation detection model according to the trained private authentication operation detection model; Acquire first authentication operation information and second authentication operation information, wherein the first authentication operation information includes image data of a touch trajectory, and the second authentication operation information includes touch positions, touch time, touch force, and touch area of ​​multiple sampling points in the touch trajectory; acquiring, according to the second authentication operation information, speed distribution information corresponding to the touch position and the touch time, acceleration distribution information corresponding to the touch position and the touch time, touch area distribution information corresponding to the touch position and the touch time, and touch force distribution information corresponding to the touch position and the touch time; Taking the first authentication operation information, the speed distribution information, the acceleration distribution information, the touch area distribution information, and the touch force distribution information as input, and inputting them into the target authentication operation detection model to obtain an authentication operation detection result; When the authentication operation detection result meets the target authentication operation detection requirement, identity authentication is performed according to the first authentication operation information.

2. According to the identity authentication method of claim 1, the identity authentication result of the adjacent identity authentication operation adjacent to the successful identity authentication operation whose corresponding identity authentication result in the real-time identity authentication log is successful authentication is also successful authentication, and the identity authentication method of the adjacent identity authentication operation is different from the identity authentication method of the successful identity authentication operation, and the time difference between the identity authentication moment of the adjacent identity authentication operation and the identity authentication moment of the successful identity authentication operation is less than or equal to the identity authentication time difference threshold.

3. According to the identity authentication method of claim 1, before receiving the updated weight parameter sent by the edge server and updating the private authentication operation detection model according to the updated weight parameter, the method further comprises: Receive private data upload instructions; In response to the private data upload instruction, sending the real-time identity authentication log; Receiving initial weight parameters sent by the edge server; The initial authentication operation detection model is updated according to the initial weight parameters to obtain the private authentication operation detection model.

4. The identity authentication method according to claim 3, before sending the real-time identity authentication log in response to the private data upload instruction, the method further comprises: Adding noise to the real-time identity authentication log to obtain a noisy real-time identity authentication log; The sending of the real-time identity authentication log includes: Send the noise real-time authentication log.

5. The identity authentication method according to claim 3, before receiving the private data upload instruction, the method further comprises: Sending user characteristic information, wherein the user characteristic information includes gender information, age information, education level information, left-right hand preference information, identity authentication method preference information, and application preference information of the user corresponding to the terminal device, wherein the edge server is used to determine multiple target terminal devices based on the user characteristic information, and send the private data upload instruction to the target terminal devices.

6. An identity authentication method, the identity authentication method being applied to an edge server, comprising: Receiving a gradient update vector sent by a terminal device as described in any one of claims 1 to 5; Aggregating the gradient update vectors, and updating the weight parameters of the shared authentication operation detection model according to the aggregated gradient update vectors to obtain updated weight parameters; The updated weight parameter is sent, and the terminal device is used to update the private authentication operation detection model according to the updated weight parameter.

7. The identity authentication method according to claim 6, before receiving the gradient update vector sent by the terminal device, the method further comprises: Determine a plurality of target terminal devices, and send a private data upload instruction to the target terminal devices; Receiving a real-time identity authentication log sent by the target terminal device, wherein the real-time identity authentication log includes first authentication operation information, second authentication operation information, and identity authentication result corresponding to at least one identity authentication operation collected in real time; Obtaining a shared identity authentication log according to the real-time identity authentication log, taking first authentication operation information, speed distribution information, acceleration distribution information, touch area distribution information, and touch force distribution information corresponding to the identity authentication operation in the shared identity authentication log as input, taking the identity authentication result corresponding to the identity authentication operation in the shared identity authentication log as output, and training an initial authentication operation detection model to obtain the shared authentication operation detection model; Initial weight parameters are obtained according to the shared authentication operation detection model and the initial weight parameters are sent. The terminal device is used to update the initial authentication operation detection model of the terminal device according to the initial weight parameters to obtain a private authentication operation detection model.

8. The identity authentication method according to claim 7, before determining a plurality of target terminal devices, the method further comprises: Receiving user characteristic information sent by multiple terminal devices, the user characteristic information including gender information, age information, education level information, left-hand preference information, identity authentication method preference information, and application preference information of users corresponding to the terminal devices; The determining of multiple target terminal devices includes: A plurality of target terminal devices are determined according to the user characteristic information, and the private data upload instruction is sent to the target terminal devices.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the method according to any one of claims 1 to 7.

Images