TWI788662B - Security authentication method, method for training security authentication model, security authentication device, training device for security authentication model, electronic device, and computer-readable storage medium - Google Patents

Abstract

The embodiment of this specification discloses a security authentication and security authentication model training method, device, and electronic equipment. The method includes: responding to the target user's security authentication request, acquiring the target user's user behavior within a preset time period data; obtain the target user's behavior feature sequence based on the user behavior profile; input the target user's behavior feature sequence into a security authentication model to obtain a security authentication result corresponding to the behavior feature sequence; wherein, the security The authentication model is trained based on multiple sets of behavior feature sequences of the target user in the historical time period.

Description

Security authentication method, method for training security authentication model, security authentication device, training device for security authentication model, electronic device, and computer-readable storage medium

This specification relates to the technical field of computer software, in particular to a method, device and electronic equipment for security authentication and training a security authentication model.

Current terminal devices mainly adopt static security authentication methods, such as fingerprint authentication, face authentication, password authentication, and the like. In this way, static authentication information needs to be stored in the internal storage of the computer and transmitted over the network, so there is a risk of being intercepted by Trojan horse programs or monitoring devices. In addition, this method also requires the user to cooperate with the operation. For example, fingerprint authentication requires the user's fingers to be kept dry and clean, face authentication requires a specific angle, and password authentication requires the user to enter password information. Obviously, these security authentication methods are not convenient enough for users, which affects the user experience to a certain extent.

In view of this, there is an urgent need for a more user-friendly and convenient security authentication method.

The purpose of the embodiment of this description is to provide a security certification and training The method, device and electronic equipment of the security authentication model can provide users with a more friendly and convenient security authentication method.

In order to solve the above-mentioned technical problems, the embodiments of this specification are implemented as follows:

In the first aspect, a security authentication method is proposed, the method includes: in response to a security authentication request for the target user, obtaining user behavior data of the target user within a preset time period; obtaining the user behavior data based on the user behavior data The behavior characteristic sequence of the target user; input the behavior characteristic sequence of the target user into the security authentication model to obtain the security authentication result corresponding to the behavior characteristic sequence; wherein, the security authentication model is based on the historical time of the target user It is obtained by training multiple sets of behavioral feature sequences in the segment.

In the second aspect, a method for training a security authentication model is proposed, including: obtaining multiple sets of user behavior data of the target user within the historical time period; based on the multiple sets of user behavior data of the target user within the historical time period, Acquiring multiple sets of behavioral feature sequences of the target user; training a security authentication model of the target user based on the multiple sets of behavioral feature sequences of the target user.

In the third aspect, a security authentication device is proposed, including: a data acquisition unit, which acquires user behavior data of the target user within a preset time period in response to a security authentication request for the target user; a sequence acquisition unit, based on the User Behavior Data Acquisition Said Goals A user's behavioral feature sequence; a security authentication unit that inputs the behavioral feature sequence into a security authentication model to obtain a security authentication result corresponding to the behavioral feature sequence.

In the fourth aspect, a safety authentication model training device is proposed, including: a data acquisition unit, which acquires multiple groups of user behavior data of a target user in a historical time period; a sequence acquisition unit, based on the target user's historical time period multiple sets of user behavior data in the target user to obtain multiple sets of behavioral feature sequences of the target user; the model training unit is based on the multiple sets of behavioral feature sequences of the target user to train and obtain the security authentication model of the target user.

In a fifth aspect, an electronic device is provided, the electronic device includes: a processor; and a memory arranged to store computer-executable instructions, the executable instructions cause the processor to perform the following operations when executed: responding Based on the security authentication request for the target user, obtain the user behavior data of the target user within a preset time period; obtain the behavior characteristic sequence of the target user based on the user behavior data; input the behavior characteristic sequence into the security authentication model to obtain the security authentication result corresponding to the behavior feature sequence.

In the sixth aspect, a computer-readable storage medium is proposed, the computer-readable storage medium stores one or more programs, and the one or more programs When executed by an electronic device including a plurality of application programs, the electronic device is made to perform the following operations: in response to a security authentication request for the target user, obtain user behavior data of the target user within a preset time period; based on the Obtaining the behavior feature sequence of the target user from the user behavior data; inputting the behavior feature sequence into a security authentication model to obtain a security authentication result corresponding to the behavior feature sequence.

In a seventh aspect, an electronic device is provided, the electronic device includes: a processor; and a memory arranged to store computer-executable instructions, the executable instructions cause the processor to perform the following operations when executed: acquire multiple sets of user behavior data of the target user within the historical time period; based on the multiple sets of user behavior data of the target user within the historical time period, obtaining multiple sets of behavioral feature sequences of the target user; based on the target user Multiple sets of behavioral feature sequences are trained to obtain the security authentication model of the target user.

In an eighth aspect, a computer-readable storage medium is proposed, the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the The electronic device performs the following operations: acquire multiple sets of user behavior data of the target user within the historical time period; acquire multiple sets of behavioral characteristics of the target user based on the multiple sets of user behavior data of the target user within the historical time period sequence; Based on multiple sets of behavior feature sequences of the target user, a security authentication model of the target user is obtained through training.

From the above technical solutions provided by the embodiments of this specification, it can be seen that the solutions of the embodiments of this specification have at least one of the following technical effects: one or more embodiments provided by this specification can respond to the target user’s Security authentication request, obtain the user behavior data of the target user within the preset time period, and then obtain the behavior characteristic sequence of the target user based on the user behavior data, and finally input the behavior characteristic sequence of the target user into the security authentication model to obtain the behavior characteristic sequence The corresponding security authentication results, wherein the security authentication model is trained based on multiple sets of behavior feature sequences of the target user in the historical time period. In this way, when the user performs security authentication, since the dynamic feature sequence within the user's preset time period is obtained, the security authentication can be realized without too much deliberate cooperation from the user, and a more friendly and convenient security authentication method is provided for the user. .

S102~S106: Steps

S502~S506: steps

600: safety authentication device

610: data acquisition unit

620: sequence acquisition unit

630: Security authentication unit

700: Training device for secure authentication model

710: data acquisition unit

720: sequence acquisition unit

730: Model training unit

In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the drawings that need to be used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only For some embodiments described in the description, for those skilled in the art, other drawings can also be obtained based on these drawings without any creative effort.

[Figure 1] is a security authentication provided by an embodiment of this manual Method flow diagram of the method.

[Fig. 2] is an interactive flowchart of the application of the security authentication method provided by an embodiment of this specification in an actual scenario.

[ Fig. 3 ] is a schematic diagram of a feature sequence of an action trajectory collected according to an embodiment of the present specification.

[ Fig. 4 ] is a schematic diagram of the probability of obtaining the user's behavior habits within a preset time period in the security authentication method provided by an embodiment of this specification.

[ Fig. 5 ] is a schematic diagram of the implementation flow of a training method for a security authentication model provided by an embodiment of this specification.

[Fig. 6] is a schematic structural diagram of a security authentication device provided by an embodiment of this specification.

[ Fig. 7 ] is a schematic structural diagram of a training device for a security authentication model provided by an embodiment of this specification.

[ Fig. 8 ] is a schematic structural diagram of an electronic device provided by an embodiment of this specification.

[ Fig. 9 ] is a schematic structural diagram of another electronic device provided by an embodiment of this specification.

In order to make the purpose, technical solutions and advantages of this specification clearer, the technical solutions in this specification will be clearly and completely described below in conjunction with specific embodiments of this specification and corresponding drawings. Apparently, the described embodiments are only some of the embodiments in this document, not all of them. Based on the examples in this document, those of ordinary skill in the art have not made any creative All other embodiments obtained under the premise of creative labor belong to the scope of protection of this document.

The technical solutions provided by each embodiment of this specification will be described in detail below in conjunction with the drawings.

As mentioned above, current terminal devices mainly adopt static security authentication methods, such as fingerprint authentication, face authentication, password authentication, and the like. In this way, on the one hand, because the static authentication information needs to be stored in the internal memory of the computer and transmitted on the network, there is a risk that the authentication information will be intercepted by Trojan horse programs or listening devices; on the other hand, it will also require The user cooperates with the authentication operation. For example, fingerprint authentication requires the user to press the finger on the fingerprint recognition module and keep the finger dry and clean. Face authentication requires the user to hold a device to collect a facial image at a specific angle, which is not convenient for the user and will cause problems. affect the user experience.

In view of the above problems, the embodiment of this specification aims to provide a more friendly and convenient security authentication method for users.

Fig. 1 is a method flowchart of a security authentication method provided by an embodiment of this specification. The method of Figure 1 may include:

S102, in response to the security authentication request for the target user, acquire user behavior data of the target user within a preset time period.

It should be understood that in daily life, there are usually differences in habits between users, such as walking frequency, stride length, running posture, speed, frequency and strength of touching the screen when using a terminal device, and the frequency and strength of using a terminal device. Habits, usage preferences, etc. of the applications installed in the A huge difference. Based on this point, the embodiment of the present description can acquire the user behavior data of the target user within a preset time period, and the user behavior data can represent the dynamic and continuous behavior data of the target user within the preset time period.

Optionally, in order to obtain dynamic and continuous behavior data that can represent the user's behavior within a period of time, the preset time period includes at least one of the following: a specified period of time before initiating a security authentication request; a specified period of time after initiating a security authentication request ; A first specified time period before initiating the security authentication request and a second specified time period after initiating the security authentication request.

Wherein, the specified time period before initiating the security authentication request, for example, may be within a few hours before initiating the security request; the specified time period after initiating the security authentication request, for example, may be within 1 minute or half a minute after initiating the security request; The first specified time period before initiating the security authentication request and the second specified time period after initiating the security authentication request, for example, may include several hours before initiating the security request and within 1 minute or half a minute after initiating the security request, namely Combine the user behavior data of the target user during these two periods of time, perform security authentication on the target user, and determine whether the behavior characteristics of the target user during these two periods of time are abnormal to the behavior characteristics learned in the past.

Optionally, a user usually uses multiple terminal devices at the same time. The terminal devices may include but are not limited to: common user personal devices such as PCs, mobile phones, PADs, smart bracelets, and smart glasses, and such terminal devices generally have The function of collecting user behavior feature sequences. In order to more comprehensively obtain user behavior data of target users within a preset time period, this manual implements For example, the user behavior data of the target user within the preset time period can be obtained from the terminal device that the target user initiates the security authentication request, and the user behavior data of the target user within the preset time period can also be obtained from multiple terminal devices associated with the target user. User behavior data within the segment. Specifically, obtaining the user behavior data of the target user within the preset time period includes: obtaining the user behavior data of the target user within the preset time period from the terminal device that the target user initiates the security authentication request; From multiple terminal devices associated with the target user, user behavior data of the target user within a preset time period is obtained.

As shown in FIG. 2 , it is a schematic diagram of a security authentication method provided by the embodiment of this specification applied in an actual scene. Among them, the multiple terminal devices associated with the target user include mobile phones, PCs, and smart bracelets. The terminal device that the user initiates the security authentication request is the mobile phone, and the device that performs the security authentication operation is the cloud server. In practical applications, the implementation security The device for the authentication operation may also be a terminal device designated by the user.

When the target user uses the mobile phone to unlock the screen, the screen unlocking needs to perform security authentication on the target user. At this time, the mobile phone sends the security authentication request to the cloud server; the cloud server responds to the security authentication request from the target user. The associated mobile phone, PC and smart bracelet obtain the user behavior data of the target user within the preset time period; the cloud server then performs security authentication on the target user based on the user behavior data, and returns the security authentication result to the mobile phone. If the security authentication of the target user is passed, the screen unlocking is successful, and if the security authentication of the target user fails, the screen unlocking fails.

S104. Obtain a behavior feature sequence of the target user based on the user behavior data.

Optionally, when acquiring the behavioral feature data of the target user, the target user can be abstracted into a specified number of key points (or specified joints). These key points can represent the complete torso of the target user after correlation. At each time point, the target user can represent the target user's actions at each time point through the association relationship between these key points. Specifically, the target user's behavior feature sequence includes at least one of the following: the target user's motion trajectory feature sequence; the target user's specified joint feature sequence; the target user's specified body feature sequence.

As shown in FIG. 3 , it is a schematic diagram of the feature sequence of the collected action trajectory provided by the embodiment of this specification. As shown in Figure 3(a), in order to abstract the target user into 17 key points, these key points include the joints of the target user, and there are some associations between these key points, that is, the connection relationship between these key points. Figure 3(b) is a schematic diagram of dividing these key points into the upper body and lower body of the target user. As shown in Figure 3(c), the first picture shows the collected actions of the target user at four consecutive time points within a certain period of time. Action trajectory sequence; the second picture shows the collected lower body movements of the target user at four consecutive time points during the period; the third picture shows the collected upper body movements of the target user at four consecutive time points during the period action.

As shown in Figure 4, it is a schematic diagram of the probability of recording the target user's four different states in the past 0~3.5s provided by the embodiment of this specification. The four states Including walking state, stop state, start state and standing state. The probability diagrams of the four different states can reflect the behavior characteristics of the target user during this period of time. It can be seen that the probability of the target user being in the walking state during this period of time is higher than that of the other three states.

S106. Input the behavioral feature sequence of the target user into the security authentication model to obtain a security authentication result corresponding to the behavioral feature sequence; wherein, the security authentication model is obtained by training based on multiple sets of behavioral feature sequences of the target user in a historical time period.

Optionally, in order to continuously optimize the security authentication model and improve the security authentication accuracy of the security authentication model, after inputting the behavior feature sequence into the security authentication model to obtain the security authentication result corresponding to the behavior feature sequence, the method further includes: The behavioral feature sequence and the corresponding security certification results within the preset time period, iteratively update the security certification model.

One or more embodiments provided in this specification can respond to the security authentication request for the target user when performing security authentication on the user, obtain the user behavior data of the target user within a preset time period, and then obtain the user behavior data based on the user behavior data. The target user’s behavioral feature sequence, and finally input the target user’s behavioral feature sequence into the security authentication model to obtain the security authentication result corresponding to the behavioral feature sequence, where the security authentication model is based on multiple sets of behavioral features of the target user in the historical time period obtained by sequence training. In this way, when the user performs security authentication, since the dynamic feature sequence within the user's preset time period is obtained, the security authentication can be realized without the user's excessive deliberate cooperation, providing users with more friendly and convenient security authentication Way.

Fig. 5 is a schematic diagram of the implementation flow of a method for training a security authentication model provided by an embodiment of this specification, including:

S502. Obtain multiple sets of user behavior data of the target user within a historical time period.

Wherein, the multiple sets of user behavior data are multiple sets of user behavior data in different time periods.

S504. Acquire multiple sets of behavior feature sequences of the target user based on multiple sets of user behavior data of the target user in a historical time period.

Optionally, user behavior data of the target user can be collected jointly based on multiple terminal devices associated with the target user. Action track data. Specifically, based on multiple sets of user behavior data of the target user in the historical time period, obtaining multiple sets of behavioral feature sequences of the target user includes: extracting multiple sets of user behavior data from the multiple sets of user behavior data in the historical time period The specified key points corresponding to multiple time points in the user behavior data, wherein one user corresponds to multiple specified key points at one time point, and a set of user behavior data corresponds to multiple time points; Correlation calculation is performed on the specified key points corresponding to multiple time points in the multiple time points to obtain the correlation between the specified key points corresponding to multiple sets of user behavior data at each time point in multiple time points; based on multiple sets of user behavior data in The association relationship between the specified key points corresponding to each time point in multiple time points, to obtain the behavior characteristics of the target user sign sequence.

Among them, the designated key points may correspond to the 17 key points shown in Fig. 3(a). In order to obtain a dynamic sequence of behavioral characteristics, the above-mentioned set of user behavior data corresponds to multiple time points that should be continuous.

S506. Based on multiple sets of behavioral feature sequences of the target user, train to obtain a security authentication model of the target user.

In one or more embodiments provided in this specification, when training a security authentication model for authenticating target user behavior, multiple sets of user behavior data of the target user in the historical time period can be obtained, and then based on the multiple sets of user behavior data of the target user in the historical time period, Group user behavior data, obtain multiple sets of behavioral feature sequences of target users, and finally train the security authentication model of target users based on multiple sets of behavioral feature sequences of target users. Since the trained security authentication model is trained based on the target user's dynamic behavior feature sequence in the historical time period, when performing security authentication on the target user, the dynamic behavior feature sequence of the target user in a period of time before authentication is obtained , the security authentication of the target user can be realized, so the target user no longer needs too much deliberate cooperation, so as to provide the user with a more friendly and convenient security authentication method.

Fig. 6 is a schematic structural diagram of a security authentication device 600 provided by an embodiment of this specification. Please refer to FIG. 6. In a software implementation, the security authentication device 600 may include: a data acquisition unit 610, which acquires user behavior data of the target user within a preset time period in response to a security authentication request for the target user; The sequence acquisition unit 620, based on the user behavior data, acquires the Behavior feature sequence of the target user; the security authentication unit 630 inputs the behavior feature sequence into a security authentication model to obtain a security authentication result corresponding to the behavior feature sequence.

From the security authentication device shown in Figure 6, it can be known that in one or more embodiments provided by this specification, when performing security authentication on a user, it can respond to the security authentication request for the target user and obtain the target user's time at a preset time. The user behavior data in the segment, and then based on the user behavior data to obtain the behavior feature sequence of the target user, and finally input the behavior feature sequence of the target user into the security authentication model to obtain the security authentication result corresponding to the behavior feature sequence, where the security authentication model is It is trained based on multiple sets of behavior feature sequences of the target user in the historical time period. In this way, when the user performs security authentication, since the dynamic feature sequence within the user's preset time period is obtained, the security authentication can be realized without too much deliberate cooperation from the user, and a more friendly and convenient security authentication method is provided for the user. .

Optionally, in an implementation manner, the preset time period includes at least one of the following: a specified time period before initiating the security authentication request; a specified time period after initiating the security authentication request; initiating the security authentication A first specified time period before the request and a second specified time period after the security authentication request is initiated.

Optionally, in an implementation manner, the data acquisition unit 610 is configured to: acquire the information of the target user within the preset time period from the terminal device from which the target user initiates the security authentication request. user behavior data and/or acquire user behavior data of the target user within the preset time period from multiple terminal devices associated with the target user.

Optionally, in an embodiment, the target user's behavior feature sequence includes at least one of the following: the target user's movement track feature sequence; the target user's designated joint feature sequence; the target user's Specifies the sequence of body features.

Optionally, in one embodiment, after the security authentication unit 630 inputs the behavior feature sequence into a security authentication model to obtain a security authentication result corresponding to the behavior feature sequence, the device further includes: a model update unit 640. Iteratively update the security authentication model based on the behavior feature sequence of the target user within the preset time period and the corresponding security authentication result.

The security authentication device 600 can implement the methods in the method embodiments shown in FIGS. 1 to 4 . For details, reference may be made to the security authentication method in the embodiments shown in FIGS. 1 to 4 , which will not be repeated here.

Fig. 7 is a schematic structural diagram of a safety authentication model training device 700 provided by an embodiment of this specification. Please refer to FIG. 7 , in a software implementation, the training device 700 of the security authentication model may include: a data acquisition unit 710, which acquires multiple sets of user behavior data of the target user in a historical time period; a sequence acquisition unit 720, based on the multiple sets of user behavior data of the target user in the historical time period, and obtain multiple sets of rows of the target user is a feature sequence; the model training unit 730, based on multiple sets of behavior feature sequences of the target user, trains to obtain a security authentication model of the target user.

From the training device of the security authentication model shown in FIG. 7, it can be known that: one or more embodiments provided in this specification can obtain multiple information of the target user in the historical time period when training the security authentication model for authenticating the behavior of the target user. Group user behavior data, and then based on multiple sets of user behavior data of the target user in the historical time period, multiple sets of behavior feature sequences of the target user are obtained, and finally based on multiple sets of behavior feature sequences of the target user, the security authentication model of the target user is obtained through training . Since the trained security authentication model is trained based on the target user's dynamic behavior feature sequence in the historical time period, when performing security authentication on the target user, the dynamic behavior feature sequence of the target user in a period of time before authentication is obtained , the security authentication of the target user can be realized, so the target user no longer needs too much deliberate cooperation, so as to provide the user with a more friendly and convenient security authentication method.

Optionally, in an implementation manner, the sequence acquisition unit 720 is configured to: extract the multiple sets of user behavior data from the multiple sets of user behavior data of the target user within the historical time period, respectively. The specified key points corresponding to multiple time points, wherein one user corresponds to multiple specified key points at one time point, and a set of user behavior data corresponds to multiple time points; Perform associated calculations on specified key points corresponding to multiple time points to obtain the multiple sets of user behavior data The relationship between the specified key points corresponding to each of the multiple time points; based on the multiple sets of user behavior data between the specified key points corresponding to each of the multiple time points The association relationship of the target user is obtained to obtain the behavior feature sequence of the target user.

The security authentication model training device 700 can implement the method in the method embodiment shown in FIG. 5 . For details, reference may be made to the security authentication model training method in the embodiment shown in FIG. 5 , which will not be repeated here.

Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present specification. Please refer to FIG. 8 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Wherein, the storage may include internal storage, such as high-speed random access memory (Random-Access Memory, RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage device etc. Of course, the electronic device may also include hardware required by other services.

The processor, network interface, and storage can be connected to each other by an internal bus, which can be an ISA (Industry Standard Architecture, industry standard architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnection) bus Or EISA (Extended Industry Standard Architecture, extended industry standard architecture) busbar, etc. The bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one double-headed arrow is used in Figure 8, but it does not mean that there is only one bus bar or one type of sink Flow row.

Memory, used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. Storage can include internal storage and non-volatile memory and provides instructions and data to the processor.

The processor reads the corresponding computer program from the non-volatile memory into the internal storage and then runs it, forming a security authentication device on a logical level. The processor executes the program stored in the memory, and is specifically used to perform the following operations: in response to the security authentication request for the target user, obtain user behavior data of the target user within a preset time period; based on the user behavior The data acquires the behavior characteristic sequence of the target user; input the behavior characteristic sequence into the security authentication model to obtain the security authentication result corresponding to the behavior characteristic sequence.

From the electronic device shown in FIG. 8, it can be known that: one or more embodiments provided by this specification can respond to the security authentication request for the target user when performing security authentication on the user, and obtain the target user's time period during the preset time period. Based on the user behavior data in the user behavior data, the target user’s behavior feature sequence is obtained based on the user behavior data, and finally the target user’s behavior feature sequence is input into the security authentication model to obtain the security authentication result corresponding to the behavior feature sequence. The security authentication model is based on It is obtained by training multiple sets of behavior feature sequences of the target user in the historical time period. In this way, when the user performs security authentication, since the dynamic feature sequence within the user's preset time period is obtained, the security authentication can be realized without the need for too much deliberate cooperation from the user. Provide users with a more friendly and convenient security authentication method.

The above method performed by the security authentication device disclosed in the embodiments shown in FIGS. 1 to 4 of this specification may be applied to or implemented by a processor. A processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above-mentioned method can be completed by an integrated logic circuit of the hardware in the processor or instructions in the form of software. The above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processor, DSP), a specific Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, separate gate or transistor logic devices, and separate hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of this specification can be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like. The steps of the methods disclosed in the embodiments of this specification can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, scratchpad. The storage medium is located in the storage, and the processor reads the information in the storage, and completes the steps of the above method in combination with its hardware.

The electronic device can also execute the methods shown in Fig. 1 to Fig. 4, and realize security authentication. The functions of the verification device in the embodiments shown in FIGS. 1 to 3 will not be repeated here in the embodiments of this specification.

Of course, in addition to the software implementation, the electronic equipment in this specification does not exclude other implementations, such as logic devices or the combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit , which can also be a hardware or logic device.

The embodiment of this specification also proposes a computer-readable storage medium, the computer-readable storage medium stores one or more programs, the one or more programs include instructions, and the instructions are executed by a portable electronic device including a plurality of application programs , the portable electronic device can be made to execute the method of the embodiment shown in Figures 1 to 4, and is specifically used to perform the following operations: in response to the security authentication request for the target user, obtain the the user behavior data; obtain the behavior characteristic sequence of the target user based on the user behavior data; input the behavior characteristic sequence into the security authentication model to obtain the security authentication result corresponding to the behavior characteristic sequence.

Fig. 9 is a schematic structural diagram of another electronic device provided by an embodiment of this specification. Please refer to FIG. 9 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a storage. Wherein, the storage may include internal storage, such as high-speed random access memory (Random-Access Memory, RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage device etc. Of course, the electronic equipment may also include other business needs hardware.

The processor, network interface, and storage can be connected to each other by an internal bus, which can be an ISA (Industry Standard Architecture, industry standard architecture) bus, a PCI (Peripheral Component Interconnect, peripheral component interconnection) bus Or EISA (Extended Industry Standard Architecture, extended industry standard architecture) busbar, etc. The bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one double-headed arrow is used in FIG. 9 , but it does not mean that there is only one bus bar or one type of bus bar.

Memory, used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. Storage can include internal storage and non-volatile memory and provides instructions and data to the processor.

The processor reads the corresponding computer program from the non-volatile memory into the internal storage and then runs it, forming a training device for the above-mentioned safety authentication model on a logical level. The processor executes the program stored in the memory, and is specifically used to perform the following operations: obtain multiple sets of user behavior data of the target user within the historical time period; Behavior data, obtaining multiple sets of behavior feature sequences of the target user; based on the multiple sets of behavior feature sequences of the target user, training to obtain a security authentication model of the target user.

By means of the electronic device shown in Figure 9, it can be known that one or more embodiments provided by this specification, in training and authenticating the security authentication of target user behavior When modeling, it is possible to obtain multiple sets of user behavior data of the target user in the historical time period, and then obtain multiple sets of behavioral feature sequences of the target user based on the multiple sets of user behavior data of the target user in the historical time period, and finally based on the target user’s Multiple sets of behavioral feature sequences are trained to obtain the security authentication model of the target user. Since the trained security authentication model is trained based on the target user's dynamic behavior feature sequence in the historical time period, when performing security authentication on the target user, the dynamic behavior feature sequence of the target user in a period of time before authentication is obtained , the security authentication of the target user can be realized, so the target user no longer needs too much deliberate cooperation, so as to provide the user with a more friendly and convenient security authentication method.

The above-mentioned method for training a security authentication model disclosed in the embodiment shown in FIG. 5 of this specification may be applied to or implemented by a processor. A processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above-mentioned method can be completed by an integrated logic circuit of the hardware in the processor or instructions in the form of software. The above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processor, DSP), a specific Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, separate gate or transistor logic devices, and separate hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of this specification can be implemented or executed. A general-purpose processor may be a microprocessor, or the processor may be any standard processor, etc. The steps of the methods disclosed in the embodiments of this specification can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, scratchpad. The storage medium is located in the storage, and the processor reads the information in the storage, and completes the steps of the above method in combination with its hardware.

It should be understood that the electronic device in the embodiment of this specification can realize the functions of the above-mentioned apparatus for training a security authentication model shown in the embodiment shown in FIG. 1 , which will not be repeated herein.

Of course, in addition to the software implementation, the electronic equipment in this specification does not exclude other implementations, such as logic devices or the combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic unit , which can also be a hardware or logic device.

In addition, the embodiment of this specification also proposes a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and the one or more programs include instructions.

Optionally, when the instruction is executed by a portable electronic device including multiple application programs, the portable electronic device can execute the method of the embodiment shown in FIG. multiple sets of user behavior data in the segment; based on the multiple sets of user behavior data of the target user in the historical time period, obtain multiple sets of behavioral feature sequences of the target user; based on multiple sets of behavioral features of the target user sequence, the trained Describe the security authentication model of the target user.

It should be understood that, when the above instructions are executed by a portable electronic device including multiple application programs, the security authentication device described above can realize the functions of the embodiment shown in FIG. 1 . Since the principle is the same, this article will not repeat them.

The foregoing describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the examples and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. Multitasking and parallel processing are also possible or may be advantageous in certain embodiments.

In a word, the above descriptions are only preferred embodiments of this specification, and are not intended to limit the scope of protection of this specification. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this manual shall be included within the scope of protection of this manual.

The systems, devices, modules or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementing device is a computer. Specifically, the computer can be, for example, a personal computer, a notebook computer, a mobile phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device or Combinations of any of these devices.

Computer-readable media includes both permanent and non-permanent, removable and non-removable media and can be implemented by any method or technology for storage of information. information available So computer-readable instructions, data structures, modules of a program, or other data. Examples of storage media for computers include, but are not limited to, phase change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc-read-only (CD-ROM), digital multifunction A compact disc (DVD) or other optical storage, magnetic cassette, tape magnetic disk storage or other magnetic storage device or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory computer readable media, such as modulated data signals and carrier waves.

It should also be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes Other elements not expressly listed, or elements inherent in the process, method, commodity, or apparatus are also included. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

Each embodiment in this specification is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for relevant parts, refer to part of the description of the method embodiment.

Claims (11)

A security authentication method, performed by a security authentication device, comprising: in response to a security authentication request for a target user, acquiring user behavior data of the target user within a preset time period, wherein the user behavior data is obtained from the target user Acquired from multiple associated terminal devices, the multiple terminal devices respectively collect user behavior data at different key points of the target user within the preset time period; obtain the target user's behavior feature sequence based on the user behavior data, Wherein, the behavior feature sequence is used to describe the actions of the target user at multiple time points, and the behavior feature sequence is obtained based on the association relationship between the specified key points corresponding to the multiple time points in the user behavior data. , so as to represent the actions of the target user at the multiple time points; input the target user's behavioral feature sequence into the security authentication model to obtain the security authentication result corresponding to the behavioral feature sequence; wherein, the security authentication model is based on the target It is obtained by training multiple sets of behavior feature sequences of users in the historical time period, wherein the key point is the joint of the target user, the specified key point is the specified joint of the target user, and wherein, by using multiple specified key The association relationship between the points obtains the actions of the target user at each time point. According to the method described in claim 1, the preset time period includes at least one of the following: a specified time period before initiating the security authentication request; a specified period of time after initiating the security authentication request; A first specified time period before initiating the security authentication request and a second specified time period after initiating the security authentication request. According to the method described in Claim 1, the target user's behavior feature sequence includes at least one of the following: the target user's motion track feature sequence; the target user's specified joint feature sequence; the target user's specified body feature sequence. According to the method described in claim 1, after inputting the behavior feature sequence into the security authentication model to obtain the security authentication result corresponding to the behavior feature sequence, the method further includes: based on the behavior of the target user within the preset time period The feature sequence and the corresponding security certification result update the security certification model iteratively. A method for training a security authentication model, comprising: obtaining multiple sets of user behavior data of a target user within a historical time period, wherein the multiple sets of user behavior data are obtained from multiple terminal devices associated with the target user, the Multiple terminal devices separately collect user behavior data of different key points of the target user in the historical time period; based on multiple sets of user behavior data of the target user in the historical time period, obtain multiple sets of behavioral characteristics of the target user Sequence; based on multiple sets of behavioral feature sequences of the target user, the security authentication model of the target user is trained, wherein, based on multiple sets of user behavior data of the target user in the historical time period, multiple sets of behavior of the target user are obtained Feature sequence, including: multiple groups of user behaviors from the target user in the historical time period In the data, specifying key points corresponding to multiple time points in the multiple sets of user behavior data are extracted, wherein one user corresponds to multiple specified key points at one time point, and a set of user behavior data corresponds to multiple time points; Respectively perform associated calculations on the specified key points corresponding to multiple time points in the multiple sets of user behavior data, so as to obtain the relationship between the multiple sets of user behavior data between the specified key points corresponding to each time point in the multiple time points Association relationship: based on the association relationship between the specified key points corresponding to each of the multiple time points in the multiple sets of user behavior data, the behavioral feature sequence of the target user is obtained, and the behavioral feature sequence is used to describe the target The respective actions of the user at the multiple time points, wherein the key point is the joint of the target user, the specified key point is the specified joint of the target user, and wherein, through the association between multiple specified key points The relationship obtains the actions of the target user at each time point. A security authentication device, comprising: a data acquisition unit, in response to a security authentication request for a target user, to acquire user behavior data of a target user within a preset time period, wherein the user behavior data is obtained from multiple Acquired in a terminal device, the plurality of terminal devices respectively collect the user behavior data of different key points of the target user within the preset time period; the sequence acquisition unit obtains the behavior characteristic sequence of the target user based on the user behavior data , wherein the behavior feature sequence is used to describe the actions of the target user at multiple time points, the behavior feature sequence is based on the specified key points corresponding to the multiple time points in the user behavior data The association relationship is obtained to represent the actions of the target user at the multiple time points; the security authentication unit inputs the behavior feature sequence into the security authentication model to obtain the security authentication result corresponding to the behavior feature sequence, wherein the key The points are the joints of the target user, the specified key points are the specified joints of the target user, and the actions of the target user at each time point are obtained through the association relationship between the multiple specified key points. A training device for a security authentication model, comprising: a data acquisition unit, which acquires multiple sets of user behavior data of a target user within a historical time period, and the multiple sets of user behavior data are obtained from multiple terminal devices associated with the target user , the plurality of terminal devices respectively collect user behavior data of different key points of the target user in the historical time period; the sequence acquisition unit acquires the target user based on multiple sets of user behavior data of the target user in the historical time period Multiple sets of behavioral feature sequences of the user; the model training unit, based on the multiple sets of behavioral feature sequences of the target user, trains to obtain the security authentication model of the target user, wherein the sequence acquisition unit: Among the multiple sets of user behavior data in , extract the specified key points corresponding to multiple time points in the multiple sets of user behavior data. Among them, one user corresponds to multiple specified key points at one time point, and a set of user behavior data corresponds to at multiple time points; the indicators corresponding to multiple time points in the multiple sets of user behavior data Perform associated calculations at certain key points to obtain the association relationship between the specified key points corresponding to each of the multiple time points in the multiple sets of user behavior data; based on the multiple sets of user behavior data at the multiple time points The relationship between the specified key points corresponding to each time point in , to obtain the behavior feature sequence of the target user, the behavior feature sequence is used to describe the actions of the target user at the multiple time points, wherein the key point is the joint of the target user, the specified key point is the specified joint of the target user, and wherein, the action of the target user at each time point is obtained through the association relationship between a plurality of the specified key points. An electronic device comprising: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the following operations: in response to a security authentication request to the target user, obtain User behavior data of the target user within a preset time period, wherein the user behavior data is obtained from multiple terminal devices associated with the target user, and the multiple terminal devices respectively collect The user behavior data of different key points in the segment; the behavior feature sequence of the target user is obtained based on the user behavior data, wherein the behavior feature sequence is used to describe the actions of the target user at multiple time points, and the behavior feature sequence It is obtained based on the correlation between specified key points respectively corresponding to multiple time points in the user behavior data, so as to represent the actions of the target user at the multiple time points; input the behavior feature sequence into the security authentication model to obtain the security authentication result corresponding to the behavior feature sequence, wherein the key point is the joint of the target user, the specified key point is the specified joint of the target user, and wherein, by The actions of the target user at each time point are obtained from the association relationship among the specified key points. A computer-readable storage medium that stores one or more programs that, when executed by an electronic device including a plurality of application programs, cause the electronic device to perform the following operations: The security authentication request of the target user, to obtain the user behavior data of the target user within a preset time period, wherein the user behavior data is obtained from multiple terminal devices associated with the target user, and the multiple terminal devices collect The user behavior data of the target user at different key points within the preset time period; the behavior feature sequence of the target user is obtained based on the user behavior data, wherein the behavior feature sequence is used to describe the target user at multiple time points Respective actions, the behavior feature sequence is obtained based on the association relationship between the specified key points corresponding to multiple time points in the user behavior data, so as to represent the actions of the target user at the multiple time points; The behavior feature sequence is input into the security authentication model to obtain the security authentication result corresponding to the behavior feature sequence, wherein the key point is the joint of the target user, the specified key point is the specified joint of the target user, and wherein, by multiple The association relationship between the specified key points is used to obtain the actions of the target user at each time point. An electronic device, comprising: a processor; and a memory arranged to store computer-executable instructions, which when executed cause the processor to perform the following operations: acquire a plurality of groups of users of a target user within a historical time period Behavior data, wherein the multiple sets of user behavior data are obtained from multiple terminal devices associated with the target user, and the multiple terminal devices respectively collect user behavior of the target user at different key points within the historical time period Data; based on multiple sets of user behavior data of the target user in the historical time period, multiple sets of behavioral feature sequences of the target user are obtained; based on multiple sets of behavioral feature sequences of the target user, the security authentication model of the target user is obtained through training , wherein, based on multiple sets of user behavior data of the target user in the historical time period, multiple sets of behavioral feature sequences of the target user are obtained, including: respectively obtaining multiple sets of user behavior data of the target user in the historical time range , extract the specified key points corresponding to multiple time points in the multiple groups of user behavior data, wherein one user corresponds to multiple specified key points at one time point, and a group of user behavior data corresponds to multiple time points; respectively Carry out correlation calculation on the specified key points corresponding to multiple time points in the multiple sets of user behavior data, so as to obtain the correlation between the specified key points corresponding to each time point in the multiple time points of the multiple sets of user behavior data relationship; based on the association relationship between the specified key points corresponding to each of the multiple time points in the multiple sets of user behavior data, the target user's A behavioral feature sequence, the behavioral feature sequence is used to describe the respective actions of the target user at the multiple time points, wherein the key point is the joint of the target user, the specified key point is the specified joint of the target user, and wherein , the actions of the target user at each time point are obtained through the association relationship among the specified key points. A computer-readable storage medium, the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device performs the following operations: acquire target user Multiple sets of user behavior data within a historical time period, wherein the multiple sets of user behavior data are obtained from multiple terminal devices associated with the target user, and the multiple terminal devices respectively collect User behavior data of different key points within the segment; based on multiple sets of user behavior data of the target user in the historical time period, multiple sets of behavioral feature sequences of the target user are obtained; based on multiple sets of behavioral feature sequences of the target user, The security authentication model of the target user is obtained through training, wherein, based on multiple sets of user behavior data of the target user in the historical time period, multiple sets of behavior feature sequences of the target user are obtained, including: Among multiple sets of user behavior data within a time period, the specified key points corresponding to multiple time points in the multiple sets of user behavior data are extracted, wherein one user corresponds to multiple specified key points at one time point, and a set of user behavior data corresponds to multiple specified key points. The data correspond to multiple time points; the indicators corresponding to the multiple time points in the multiple sets of user behavior data respectively Perform associated calculations at certain key points to obtain the association relationship between the specified key points corresponding to each of the multiple time points in the multiple sets of user behavior data; based on the multiple sets of user behavior data at the multiple time points The relationship between the specified key points corresponding to each time point in , to obtain the behavior feature sequence of the target user, the behavior feature sequence is used to describe the actions of the target user at the multiple time points, wherein the key point is the joint of the target user, the specified key point is the specified joint of the target user, and wherein, the action of the target user at each time point is obtained through the association relationship between a plurality of the specified key points.

Images