WO2020024414A1

WO2020024414A1 - User authentication method and device based on slider verification code

Info

Publication number: WO2020024414A1
Application number: PCT/CN2018/107909
Authority: WO
Inventors: 杨冬艳; 王智浩
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-08-03
Filing date: 2018-09-27
Publication date: 2020-02-06
Also published as: CN109271762B; CN109271762A

Abstract

Disclosed is a user authentication method and device based on a slider verification code. The method comprises: obtaining first page operation data starting a target service, and outputting a target slider verification code to a user interface starting the target service according to the first page operation data; obtaining, from the user interface, first slider operation data for user authentication based on the target slider verification code; on the basis of a user behavior recognition model verified by the slider verification code, determining a user behavior category verified by the slider verification code corresponding to the first page operation data and the first slider operation data, the user behavior recognition model being obtained by training sample data verified by the slider verification code; and completing the user authentication of the target service according to the user behavior category and starting the target service, or disconnecting the user authentication of the target service.

Description

User authentication method and device based on slider verification code

This application claims the priority of a Chinese patent application filed on August 3, 2018 with the Chinese Patent Office, application number 201810882217.8, and application name "User Authentication Method and Device Based on Slider Verification Code", the entire contents of which are incorporated by reference. In this application.

Technical field

The present application relates to the field of electronic technology, and in particular, to a user authentication method and device based on a slider verification code.

Background technique

The slider verification code is another security verification code that is different from the image verification code. The slider verification code is also one of the behavioral verification codes. The method of generating the slider verification code is generally to generate a long picture in the user interface of the client. The long picture is composed of multiple small pictures. A slider component is added above the picture frame of the long picture, and the slider component is a slider. Verification code, where the initial position of the slider verification code on the picture frame is random. During the dragging of the slider verification code by the user, the small pictures in the long picture move one by one with the movement of the slider verification code, so that a complete picture is always presented in front of the user. The user drags the slider verification code until the reference picture is displayed in the picture box, and places the slider verification code at the specified position to submit the verification.

However, at present, the verification operation of the slider verification code is only to simply drag the slider verification code and complete the image stitching of the slider verification code to complete the verification of the slider verification code. There is a simple operation in the verification process of the slider verification code. , Easy to use and other characteristics, these characteristics are easy to be imitated by the machine. It is easy to simulate human user behavior through a computer, and the machine user behavior existing in the verification process of the slider verification code is difficult to be identified, which makes the slider verification code low in security and poor in applicability.

Summary of the invention

The embodiments of the present application provide a user authentication method and device based on a slider verification code, which can improve the security of the verification of the slider verification code, can effectively prevent the network attack of the verification of the slider verification code, improve network security, and ensure the slider The verification of the verification code for the requested target service is more secure and applicable.

In a first aspect, an embodiment of the present application provides a user authentication method based on a slider verification code. The method includes:

Obtaining the first page operation data for starting the target service, and outputting the target slider verification code to the user interface for starting the target service according to the first page operation data;

Obtaining, from the user interface, first slider operation data for performing user authentication for starting the target service based on the target slider verification code;

Based on the user behavior recognition model verified by the slider verification code, the user behavior category verified by the slider verification code corresponding to the first page operation data and the first slider operation data is determined. The verified sample data is obtained through training. The above sample data includes at least first user behavior sample data corresponding to the first category of users and second user behavior sample data corresponding to the second category of users, and any user behavior sample data includes page operations. Data and / or slider operation data;

Complete user authentication of the target service and start the target service according to the user behavior category, or disconnect user authentication of the target service according to the user behavior category.

In a second aspect, an embodiment of the present application provides a user authentication device based on a slider verification code. The device includes:

A data acquisition unit, configured to acquire first page operation data of a target business;

An output unit, configured to output a target slider verification code to a user interface that starts the target service according to the first page operation data obtained by the data obtaining unit;

The data obtaining unit is further configured to obtain, from the user interface, first slider operation data for performing user authentication for starting the target service based on the target slider verification code output by the output unit;

The user behavior recognition unit is configured to identify a user verified by the slider verification code corresponding to the first slider operation data obtained by the data acquisition unit based on the user behavior recognition model verified by the slider verification code. Behavior category, the user behavior recognition model is trained from sample data verified by the slider verification code, and the sample data includes at least first user behavior sample data corresponding to the first category of users and second user behavior sample corresponding to the second category of users. Data, any user behavior sample data includes page operation data and / or slider operation data;

The authentication response unit is configured to complete user authentication of the target service and start the target service according to the user behavior category identified by the user behavior identification unit, or disconnect the user authentication of the target service according to the user behavior category.

In a third aspect, an embodiment of the present application provides a terminal device. The terminal device includes a processor and a memory, and the processor and the memory are connected to each other. The memory is configured to store a computer program that supports the terminal device to execute the method provided in the first aspect and / or any possible implementation manner of the first aspect. The computer program includes program instructions, and the processor is configured to call the foregoing. A program instruction executes the first aspect and / or the method provided in any possible implementation manner of the first aspect.

According to a fourth aspect, an embodiment of the present application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, where the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the instructions. The first aspect and / or the method provided by any possible implementation manner of the first aspect.

By adopting the embodiment of the present application, the security of the verification of the slider verification code can be improved, the network attack of the verification of the slider verification code can be effectively prevented, the network security can be improved, and the target service requested by the verification of the verification of the slider verification code can be guaranteed. Safety and applicability.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solution of the embodiment of the present application more clearly, the drawings used in the description of the embodiment will be briefly introduced below.

1 is a schematic flowchart of a user authentication method based on a slider verification code according to an embodiment of the present application;

2 is a schematic flowchart of a method for constructing a user behavior recognition model according to an embodiment of the present application;

FIG. 3 is another schematic flowchart of a user authentication method based on a slider verification code according to an embodiment of the present application; FIG.

4 is a schematic structural diagram of a user authentication device based on a slider verification code according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present application.

detailed description

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

Slider verification code is another security verification code different from image verification code. The security verification of the slider verification code is similar to the sliding unlock of a mobile phone. It is a verification method that can be performed by dragging the slider to a specified position with a mouse or a finger according to a prompt. The slider verification code is also one of the behavioral verification codes. The current method of generating the slider verification code is generally to generate a long picture on the user interface of the client or the web page of the browser, and the long picture is composed of multiple small pictures. Add a slider component above the picture frame of the long picture, where the initial position of the slider on the picture frame is random. Here the slider is used as a verification code, so it is also called a slider verification code, which will not be described in detail below. When the user drags the slider with the mouse or finger, the small pictures in the long picture move one by one, so that a complete picture is always presented to the user. During the verification process of the slider verification code, the user drags the slider verification code until the benchmark picture is displayed in the picture box and submits the verification. The above reference picture is the small picture to which the slider verification code belongs, that is, the picture content of the slider verification code portion is missing from the small picture before the verification of the slider verification code is completed. The slider code verification can be completed. At this time, it can be determined that the verification of the slider verification code is correct. During the process of dragging the slider verification code, the closer the slider verification code is to the correct position, the clearer the picture is, which is more convenient for users to use and judge. At present, the verification operation of the slider verification code is only to simply drag the slider verification code and complete the image stitching of the slider verification code to complete the verification of the slider verification code. The verification process of the slider verification code has a simple operation. Convenience and other characteristics, these characteristics can be easily imitated by the machine. The human user behavior can be easily simulated by a computer, and the machine user behavior existing in the verification process of the slider verification code is difficult to be identified, which makes the slider verification code less secure.

In order to improve the verification security of the slider verification code, the method provided in the embodiment of the present application can build a user behavior recognition model of the slider verification code based on the fuzzy cluster analysis algorithm and the sample data obtained from various data acquisition paths. Here, the user behavior recognition model can be used to identify multiple types of users, such as human users and machine users, or ordinary users and star users (such as VIP users), or other types of users. For the convenience of description, the embodiments of the present application will be described by taking human users and machine users as examples. The corresponding user behavior recognition model may also be a human-machine user behavior recognition model, which is not limited herein. The slider verification code-based user authentication method (for convenience of description, the method provided in the embodiment of the present application may be abbreviated) can recognize the human user behavior and machine user behavior in the slider verification code verification process through a human-machine user behavior recognition model, thereby It can avoid the verification of the slider verification code of the user behavior of the machine, improve the security of the user authentication based on the verification of the slider verification code, and ensure the user data security of the target business.

The method provided in the embodiment of the present application may adopt a verification code display-user behavior data collection-user behavior analysis process, based on the human-machine user behavior recognition model, perform user behavior analysis on the user behavior data collected in real time to identify human user behavior Or the behavior of the machine user, and then the verification of the slider verification code can be completed when the human user behavior is identified, and the verification of the slider verification code can be blocked when the machine user behavior is identified, which can effectively prevent network attack behavior and improve network security To ensure the security of the business requested by the verification of the slider verification code. The method provided in the embodiment of the present application may be applicable to user authentication of any service. For the convenience of description, the target service is taken as an example for description, and details are not described below. The method and device provided in the embodiments of the present application will be described below with reference to FIGS. 1 to 5.

Please refer to FIG. 1, which is a schematic flowchart of a user authentication method based on a slider verification code according to an embodiment of the present application. The method provided in the embodiment of the present application may include data processing stages such as construction of a user behavior recognition model verified by a slider verification code, user authentication based on a user behavior recognition model, and response to user authentication based on a slider verification code. The data processing stages provided by the embodiments of the present application will be described below with reference to steps S1, S2, and S3.

S1. Construction of a user behavior recognition model for slider verification code verification.

In some feasible implementation manners, during the training phase of the user behavior recognition model verified by the slider verification code, the user behavior data used for the training of the user behavior recognition model may be integrated to classify users in two categories (for example, human users or machine users). The classification of the two categories of users) problem is to train the user behavior recognition model for the learning task, so that the user behavior recognition model has the ability to judge human users or machine users on the user behavior data collected in real time. The above user behavior data may include, but is not limited to, page operation data of a user on a browser's business operation page or a client's business operation page, slider operation data of a user's authentication based on a slider verification code, and user operation browsing. Information such as browser or client. Specifically, more types of user behavior data can be determined according to actual application scenarios, and there is no limitation here. However, before identifying human user behavior or machine user behavior, the user behavior recognition model cannot clearly know in advance which user behaviors are human user behaviors, which user behaviors are machine user behaviors, and do not know what are the characteristics of human users and machine users. Clear differences, so this information needs to be trained by unsupervised fuzzy clustering analysis algorithms, combined with distance calculation of user high-dimensional data features to determine the difference between human user behavior and machine user behavior. By analyzing the differences between human user behavior and machine user behavior, the user behavior verified by the slider captcha is divided into two categories of clear human user behavior and machine user behavior. Further, the difference between user behaviors of the two types of users can be comprehensively analyzed in combination with user authentication requirements based on slider verification code verification for specific services, so as to separate machine user behavior from human user behavior.

In some feasible implementation manners, please refer to FIG. 2 together. FIG. 2 is a schematic flowchart of a method for constructing a user behavior recognition model according to an embodiment of the present application. The implementation manner adopted for the construction of the above-mentioned user behavior recognition model may include the implementation manner provided by each step in the following steps S11 to S13.

S11. Sample data collection for user behavior recognition model training.

In some feasible implementation manners, the above sample data for user behavior recognition model training may include sample data for at least two types of users of user behavior recognition model training for slider verification code verification. The above sample data includes at least first user behavior sample data corresponding to the first category of users (for example, human users) and second user behavior sample data corresponding to the second category of users (for example, machine users), and includes the first user Any user behavior sample data including the behavior sample data and the second user behavior sample data includes page operation data and / or slider operation data.

Optionally, the sample data of the at least two types of users may be obtained from a user group database of the target service. The above sample data includes page operation data when at least two types of users included in the user group of the target service start the target service, and / or slider operation data of user authentication.

Optionally, the sample data of the at least two types of users may be obtained from a user group database of other services based on big data analysis. The other services mentioned above are one or more services which are the same type of services as the target service and whose user authentication method is slider verification code verification. The above sample data includes page operation data of at least two types of users included in the user group of other services when each category user starts other services, and / or slider operation data of user authentication. In the embodiment of the present application, the sample data used for user behavior recognition model training can be obtained from multiple data acquisition paths, and the source of the sample data can cover the verification of slider verification codes corresponding to various services, improving the sample data. The validity of the data and the reliability of the sample data are stronger, which can further improve the accuracy of the user behavior judgment of the user behavior recognition model obtained based on the training of the sample data.

In some feasible implementation manners, the data types included in any of the first page operation data and / or sample data in the page operation data include: user operation position on the page, user operation time on the page, and One or more of the user operation trajectories. The user operation position on the above page may be the position where the user's finger or mouse clicks on the page, or the position where the user presses on the page, etc., which can be determined according to the actual application scenario, and is not limited here. Wherein, the user operation instruction generated by the above-mentioned click operation or pressing operation may be a user operation instruction for triggering a service management page for starting a target service (for convenience of description, it may be simply referred to as starting a target service), which is not limited herein. The user operation instruction on the above page may be a duration corresponding to a user's finger or mouse clicking or pressing on the page, for example, the duration from a mouse click or pressing a certain position on the page to releasing the mouse. The user operation trajectory on the above page is the trajectory of a user's finger or mouse clicking or pressing on the page multiple times, or the trajectory of a finger or mouse sliding on the page, etc., which can be specifically based on the user required to start the target service in the actual application scenario The operation form is determined, and there is no limitation here.

In some feasible implementation manners, the types of data included in any of the first slider operation data and / or sample data in the slider operation data include: a user operation position on a slider verification code, a One or more of a user operation duration and a sliding parameter of a slider verification code. The sliding parameters include one or more of a sliding trajectory, a slider speed, a sliding duration, a sliding range, an aspect ratio of sliding, and an acceleration of sliding. Optionally, the user operation position of the slider verification code may include a click position, a pressing position, or a drag position on the slider verification code when the user clicks, presses, or drags the slider verification code. The user operation duration of the above-mentioned slider verification code may include the corresponding duration of operations such as clicking, pressing, or dragging the sliding verification code, and the sliding duration of the slider verification code during the sliding process of dragging the slider verification code, and so on. The total length of time that the block verification code operates. The sliding trajectory of the slider verification code can be determined by the point coordinates collected during the sliding of the slider verification code, including but not limited to the starting point coordinates, end point coordinates, and one or more intermediate point coordinates during the sliding of the slider verification code. . The sliding speed and sliding acceleration of the slider verification code can be determined by data such as the sliding distance and the sliding duration of the slider verification code. The sliding range of the above-mentioned slider verification code and the ratio of the horizontal and vertical coordinates of the sliding can be determined by data such as point coordinates collected during the sliding process of the slider verification code, and can be specifically determined according to the actual application scenario, which is not limited here.

Optionally, the data types and / or data content collected and screened during the training phase of the user behavior recognition model may be collected with the data processing phases such as the test phase and the use phase of the user behavior recognition model provided in the following steps. And the filtered data type and / or data content are kept the same data type and / or data content (the data item type is the same but the values are different), so that the user behavior recognition model can be better used to learn and output the input user behavior data The corresponding user behavior category can increase the discrimination accuracy of the user behavior recognition model, and the applicability is stronger. For the convenience of description, the page operation data and slider operation data involved in the foregoing data processing stages may be described by using user behavior data as an example.

Optionally, in some feasible implementation manners, the sample data may further include identification information (such as an IP address, etc.) of a terminal device used by the user, a display screen resolution of the terminal device used by the user, and a target business account of the user. Information (such as user account ID, etc.) and other user identification information are not limited here. Further, based on the above-mentioned user behavior data, one or more of the above-mentioned user identification information may also be used as the unique identification information for user authentication, and the sliding of the slider verification code in unit time during the user authentication process may be derived therefrom. User operation data such as frequency, user authentication frequency of the user in unit time, and so on. Further, the above-mentioned user operation data can also be used as part of the sample data for user behavior recognition model training, thereby increasing the diversity of data types included in the sample data and enhancing the coverage of the sample data, which can enhance the The scope of application of the user behavior recognition model trained based on sample data is more flexible and more applicable.

S12. Construct a user behavior recognition model based on the sample data.

In some feasible implementation manners, the above sample data for user behavior recognition model training may be used as input of the user behavior recognition model, and the sample data is learned through the user behavior recognition model to obtain identification of any page operation data and / Or the ability of the slider to manipulate the user behavior category corresponding to the data. Optionally, user behavior data (including page operation data and //) of at least two types of users included in the above sample data can be obtained through the above-mentioned user behavior recognition model based on the training unsupervised fuzzy cluster analysis algorithm. Or slider operation data) and / or user operation data for learning, so that the user behavior recognition model has the ability to acquire and identify user behavior data corresponding to any category of users and / or user behavior categories corresponding to user operation data.

In general, the user ’s behavior data corresponding to the human user ’s operation position on the page and on the slider verification code, or dragging the slider verification code to perform sliding data of the slider are relatively random: including but not limited to sliders The degree of dispersion of the horizontal and vertical coordinates of the verification code sliding is also relatively large, and the data such as sliding speed and acceleration are relatively scattered. The identification information of the terminal device used by the user, the display resolution of the terminal device used by the user, and the target business account information When the user identification information becomes more discrete and diversified, the distribution status of the data usually appears as irregular. However, compared to the user behavior data and user operation data corresponding to the human user, the user identification information of the machine user is relatively fixed, the data corresponding to the operation position on the page and the slider is relatively small, and the verification code is dragged on the slider The sliding data corresponding to operations such as sliding are relatively fixed, and the sliding speed and acceleration of the slider verification code are relatively constant, and so on.

In some feasible implementations, based on the above-mentioned user behavior data of human users and machine users, and feature differences in user operation data, machine learning fuzzy cluster analysis algorithms can be used to aggregate human user behaviors and machine user behaviors. Class analysis, and training the user behavior recognition model based on the above sample data, so that a user behavior recognition model capable of identifying the slider verification code verification behavior of a human user and the slider verification code verification behavior of a machine user can be trained. Here, cluster analysis refers to the process of grouping a collection of physical or abstract objects into similar classes composed of similar objects, and dissimilar objects composed of different classes. In other words, the goal of cluster analysis is to collect data on a similar basis To classify. The difference between clustering and classification is that the classes required to be classified by the cluster are unknown, the classes required to be classified by the classification are known and related labels need to be added to mark the categories. Clustering is a process of classifying data into different classes or clusters, so objects in the same cluster have great similarity, but objects in different clusters have great dissimilarity. In the embodiment of the present application, a user behavior recognition model is trained based on a training unsupervised fuzzy clustering analysis algorithm, and training can be performed without adding category tags to the sample data to identify any page operation data and / or slider operation data. The user behavior recognition model corresponding to the capability of the user behavior category is simple to operate and more applicable.

S13. Perform a test of human user behavior and machine user behavior determination based on a user behavior recognition model.

In some feasible implementation manners, on the basis of constructing a user behavior recognition model to recognize human user behavior and machine user behavior, the model parameters of the user behavior recognition model obtained by training are saved, and at the same time, based on the user behavior recognition during the test process, The model can perform real-time determination of user behavior on user behavior test data such as page operation data, slider operation data, and user operation data generated by the user at a single time, and quickly, accurately, and in real time return the determination results of human-machine user behavior. Based on the user behavior judgment results of the human user or machine user output by the above user behavior recognition model and the categories of user behavior in the actual test process, the model parameters of the user behavior recognition model are modified, so that the user behavior recognition model has a more accurate human-machine user The ability to judge behaviors can further improve the accuracy of judging user behavior categories of human users or machine users based on user behavior recognition models.

Through the above steps S11 to S13, training and optimization of the user behavior recognition model can be completed, so that a user behavior recognition model having the ability to recognize human user behavior and machine user behavior can be obtained. The user behavior recognition model obtained through training can determine the user behavior data and / or user operation data collected in real time to determine whether the user corresponding to the user behavior data and / or user operation data collected in real time is a human user or a machine user .

S2. User authentication based on a user behavior recognition model.

In some feasible implementation manners, after the training and optimization of the user behavior recognition model can be completed based on the above steps S11 to S13, the page operation data of the target service started in real time (for convenience) can be collected based on the user behavior recognition model. The description can use the first page operation data as an example to describe, and the slider operation data of the user authentication that starts the target service (for the convenience of description, the first slider operation data can be described as an example) to determine the user behavior category. The user authentication of the target service may be completed and the target service may be started according to the user behavior category determined based on the user behavior recognition model, or the user authentication of the target service may be disconnected according to the user behavior category. Please refer to FIG. 3 together. FIG. 3 is another schematic flowchart of a user authentication method based on a slider verification code according to an embodiment of the present application. The method provided in the embodiment of the present application may be specifically described in combination with steps S21 to S24.

S21: Obtain the first page operation data for starting the target service, and output the target slider verification code to the user interface for starting the target service according to the first page operation data.

In some feasible implementation manners, in the use phase of the user behavior recognition model, when the user needs to complete the operation of starting the target service on the business operation page of the browser corresponding to the target service or the business operation page of the client, the above browsing may be collected. The page operation data (ie, the first page operation data) on the business operation page of the server or the business operation page of the client, and trigger the verification process of starting the slider verification code according to the first page operation data. For the convenience of description, operations for starting a target service may include operations such as starting a service for registering an application account and / or a service for logging in an application account. Among them, the above-mentioned service for registering an application account or the service for logging in an application account may be described as an example of a target service. I will not repeat them below. Optionally, the above-mentioned first page operation data may include one or more of a user operation position on the page, a user operation time on the page, and a user operation track on the page. For details, refer to each of steps S11 to S13 above. The implementation provided by the steps is not repeated here.

For example, when a user needs to log in to an application account of an application or register an application account of an application, he can click the icon of the browser or the icon of the client through a mouse or a finger, etc., so that the business operation page of the browser or the customer can be opened. Business operations page. Enter the existing application account information on the business operation page, or fill in the application account information to be registered, or slide the screen of the terminal device for identity recognition, etc., and then click the verification code on the slider on the business operation page to verify Window, triggering the terminal device to enter the verification process of the slider verification code. Wherein, when a user enters existing application account information on a business operation page, or fills in application account information to be registered, or slides the screen of a terminal device for identity recognition, the terminal device can collect and input the existing application. Page operation data generated by operations such as account information, filling in application account information to be registered, or sliding the screen of a terminal device. You can manipulate the data for the first page. The above-mentioned collected first page operation data includes, but is not limited to, the user operation position on the page triggered by operations such as entering existing application account information, filling in application account information to be registered, or sliding the screen of a terminal device, etc. One or more of a user operation duration on the page and a user operation track on the page may be specifically determined according to an actual application scenario, and there is no limitation here.

In some feasible implementation manners, the terminal collects and obtains the first page operation data, and when the slider verification code verification process is entered according to the first page operation data, the target slider verification code may be output to the user interface that starts the target service. . The target slider verification code may be used for user authentication for starting a target service, and the user interface for starting the target service may include a service operation page of the browser or a service operation page of the client, which is not limited herein. It can be understood that when the user opens the business operation page of the browser or the business operation page of the client and completes the corresponding operation on the above business operation page, the user operation interface displayed on the terminal device at this time may be the business operation page. Therefore, the user interface for starting the target service at this time may also be a user operation interface of the terminal device, including but not limited to the touch screen of the terminal device, which may be specifically determined according to an actual application scenario, and is not limited herein.

In some feasible implementation manners, when the terminal enters the verification process of the slider verification code, the target slider verification code can be output to the user interface that starts the target service, such as the touch screen of the terminal device, and the terminal device can be monitored. User operation instructions on the touch screen. When the user uses the target slider verification code displayed on the touch screen of the terminal device to perform verification by dragging the target slider verification code with the mouse or finger, the slider operation data corresponding to the target slider verification code can be triggered, that is, The first slider operates the data.

S22. Obtain, from the user interface, first slider operation data for performing user authentication for starting the target service based on the target slider verification code.

In some feasible implementation manners, after the terminal device displays the target slider verification code on the user interface for starting the target service, the terminal device can collect the slider operation data (that is, the first Slider operation data), and further, user behavior data including the first page operation data and the first slider operation data may be input into the trained user behavior recognition model. The first slider operation data includes, but is not limited to, one or more of a user operation position on the slider verification code, a user operation duration of the slider verification code, and a sliding parameter of the slider verification code. The sliding parameters include one or more of a sliding trajectory, a slider speed, a sliding duration, a sliding range, an aspect ratio of sliding, and an acceleration of sliding. For the data type and / or data content included in the first slider operation data, refer to the data type included in any slider operation data in the sample data in the implementation methods provided in the steps S11 to S13 above. And / or data content, which will not be repeated here.

Optionally, before determining the first page operation data and / or the first slider operation data collected in real time based on the above-mentioned user behavior recognition model, the user behavior category in the target slider verification code verification process may be determined before the user may be collected. Drag the target slider verification code to perform user authentication, such as the identification information of the terminal device (such as the IP address), the display resolution of the terminal device used by the user, and the user's target business account information (such as the user account ID) Wait for user identification information, which is not limited here. Further, based on the user behavior data including the first page operation data and / or the first slider operation data (for the convenience of description, the first user behavior data may be used as an example for description), the user identification information in the foregoing user identification information may also be used. One or more items are used as the unique identification information for user authentication, and user operation data such as the sliding frequency of the target slider verification code in unit time and the user authentication frequency in unit time during user authentication are derived The convenient description can be described by using the first user operation data as an example). Further, the above-mentioned user operation data can also be used as part of the input data of the user behavior category determination during the verification process of the target slider verification code based on the user behavior recognition model training, thereby improving the verification performance based on the target slider verification code. In the process of starting the user authentication of the target service, the accuracy of the user behavior category determination based on the user behavior recognition model is more applicable.

S23. Based on the user behavior recognition model verified by the slider verification code, a user behavior category verified by the slider verification code corresponding to the first page operation data and the first slider operation data is determined.

In some feasible implementation manners, based on the user behavior recognition model, a user behavior category verified by a target slider verification code corresponding to the input data including the first user behavior data is determined. Optionally, the input data may further include the first user operation data derived based on the first user behavior data, which may be specifically determined according to an actual application scenario, and is not limited herein. The terminal device may use the first user behavior data and / or the first user operation data as input data of a user behavior recognition model, learn the input data based on the user behavior recognition model, and output the first user behavior data and / Or the user behavior corresponding to the first user operation data is a human user behavior or a user behavior category determination result of a machine user behavior, so that whether to respond to the verification of the slider verification code can be determined according to the determination result.

S24. Complete user authentication of the target service according to the user behavior category and start the target service, or disconnect user authentication of the target service according to the user behavior category.

In some feasible implementation manners, when the verification of the target slider verification code is correct and the user behavior category is a human user, the terminal device may determine to complete user authentication of the target service and enter a service processing interface of the target service. For example, the terminal device can output a prompt on the business operation page of the browser or the business operation page of the client to indicate that the verification of the target slider verification code is correct, and enter the business processing interface of the target service for the user to perform the business processing operation of the target service, etc. , Which can be determined according to the actual application scenario, and is not limited here.

In some feasible implementation manners, when the verification of the target slider verification code is correct and the user behavior category is a machine user, the terminal device may close the user authentication interface of the target service to disconnect the user authentication of the target service, and Report the user information of the machine user to the network administrator corresponding to the target service. For example, when the terminal device can output a user authentication prompt that the target slider verification code verification fails on the business operation page of the browser or the business operation page of the client, and exit the user authentication process of the target service. Optionally, for more implementation manners of performing target service response based on the user behavior category determined by the user behavior recognition model, refer to the specific implementation manner provided in step S3 below, which is not limited herein.

S3. Data processing stages such as a response to user authentication based on the slider verification code.

In some feasible implementation manners, if the above-mentioned user behavior recognition model determines that the collected first user behavior data and / or the user behavior corresponding to the first user operation data are human user behaviors, it may be Verify and complete the verification of the slider verification code. At this time, the user may be allowed to enter the subsequent process of the application account registration corresponding to the target service, or allow the user to enter the subsequent process of the application account registration corresponding to the target service. Specifically, it can be determined according to specific operations after user authentication of the target service, and there is no limitation here.

In some feasible implementation manners, the terminal device may output a security prompt question on the business operation page of the browser or the business operation page of the client when the verification of the target slider verification code is correct and the user behavior category is a machine user. The user answers the question according to the security prompt to perform a user authentication process other than user authentication based on the target slider verification code. Further user authentication based on the security prompt question can further avoid the simulated authentication of the machine user and improve the security of the target business. More sexual. Optionally, if the user behavior identification module determines that the collected first user behavior data and / or the user behavior corresponding to the first user operation data is a machine user behavior, and the authentication of the security prompt question is incorrect, the user may be blocked The process of registering and / or logging in to an application account, or reporting user information for user authentication based on the target slider verification code to a network administrator such as a service administrator or network engineer of the target service. For example, the terminal device may send a prompt signal or an alarm or an early warning email to the network administrator to report the above user information to the network administrator and prompt the network administrator to perform manual detection of the user behavior category that starts the target service to improve the target service. Network security.

In the embodiment of the present application, the user data database of the target service or the sample data obtained based on big data analysis is used as sample data for training the user behavior recognition model for slider verification code verification, and a user behavior recognition model is constructed by using a fuzzy cluster analysis algorithm. . User behavior recognition model based on slider verification code verification, which can determine the user behavior category on the page operation data and / or slider operation data collected by the user authentication based on the target slider verification code verification, and then based on the user behavior The user behavior category identified by the recognition model responds to the user authentication of the target service. If the user authentication of the target service is completed based on the user behavior category, the target service can be started; otherwise, the user authentication of the target service is disconnected, the operation is simple, the security of the slider verification code verification can be improved, and the slider verification code verification can be effectively prevented Network attacks to improve network security. Optionally, when the user behavior of the machine user is detected based on the user behavior recognition model, a network administrator such as a service administrator or a network engineer who reports the user information based on the machine user to the target service can further ensure the verification of the slider verification code. The requested target service is more secure and applicable.

Referring to FIG. 4, FIG. 4 is a schematic structural diagram of a user authentication device based on a slider verification code according to an embodiment of the present application. The user authentication device provided in the embodiment of the present application includes:

The data obtaining unit 41 is configured to obtain first page operation data of a target service.

The output unit 42 is configured to output a target slider verification code to a user interface that starts the target service according to the first page operation data obtained by the data obtaining unit 41.

The data obtaining unit 41 is further configured to obtain, from the user interface, first slider operation data for performing user authentication for starting the target service based on the target slider verification code output by the output unit 42.

The user behavior recognition unit 43 is configured to determine the slider verification code verification corresponding to the first page operation data and the first slider operation data obtained by the data obtaining unit 41 based on a user behavior recognition model verified by the slider verification code. User behavior category, the above-mentioned user behavior recognition model is trained from sample data verified by the slider verification code, and the sample data includes at least the first user behavior sample data corresponding to the first category of users and the second user corresponding to the second category of users. Behavior sample data. Any user behavior sample data includes page operation data and / or slider operation data.

The authentication response unit 44 is configured to complete user authentication of the target service and start the target service according to the user behavior category identified by the user behavior identifying unit, or disconnect the user authentication of the target service according to the user behavior category.

In some feasible implementation manners, the foregoing data obtaining unit 41 is further configured to:

Sample data of at least two types of users is obtained, and the sample data is used for training a user behavior recognition model for slider verification code verification. The sample data includes at least the first user behavior sample data and the second user behavior sample data.

The user behavior recognition unit 43 is configured to:

The sample data obtained by the data obtaining unit 41 is used as an input of a user behavior recognition model verified by a slider verification code, and the sample data is learned through the user behavior recognition model to obtain any page operation data and / or slide The ability to block user action categories corresponding to data.

In some feasible implementation manners, the foregoing user behavior recognition unit 43 is configured to:

Based on the above-mentioned user behavior recognition model, based on the training unsupervised fuzzy clustering analysis algorithm, the page operation data and / or slider operation corresponding to each category of users in at least two categories of users included in the sample data obtained by the data acquisition unit 41 described above The data is learned to obtain the ability to identify the page behavior data and / or slider operation data corresponding to any category of user behavior category.

In some feasible implementation manners, the foregoing data obtaining unit 41 is configured to:

Obtaining sample data of at least two types of users from the user group database of the target service;

The sample data includes page operation data when each category of users in at least two types of users included in the user group starts the target service, and / or slider operation data of user authentication.

Based on big data analysis, sample data of at least two types of users are obtained from the user group database of other services. The other services are one or more of the same type of services as the target service and the user authentication method is slider verification code verification. business;

The above sample data includes page operation data when at least two types of users included in the user group of the other services and each category of users start the other services, and / or slider operation data of user authentication.

In some feasible implementation manners, the first category of users includes human users, and the second category of users includes machine users; the authentication response unit 44 is configured to:

When the slider verification code is verified correctly and the user behavior recognition unit recognizes that the user behavior category is a human user, complete user authentication of the target service and enter a service processing interface of the target service;

When the slider verification code is verified correctly and the user behavior recognition unit recognizes that the user behavior category is a machine user, closing the user authentication interface of the target service to disconnect the user authentication of the target service, and The user information is reported to the network administrator corresponding to the target service.

In some feasible implementation manners, the types of data included in the first page operation data and / or any of the page operation data in the sample data include: user operation position on the page, user operation time on the page, and One or more of the user's operation trajectories.

In some feasible implementation manners, the data types included in the first slider operation data and / or any of the slider operation data in the sample data include: a user operation position on a slider verification code, and a slider verification code. One or more of the user operation duration and the sliding parameter of the slider verification code, wherein the sliding parameters include a sliding trajectory, a slider speed, a sliding duration, a sliding range, an aspect ratio of the sliding, and a sliding One or more of the accelerations.

In some feasible implementation manners, the above-mentioned slider verification code-based user authentication device may implement the implementation manners provided by the steps in FIG. 1 to FIG. 3 described above through each of its built-in function modules. Optionally, the user authentication device may be a terminal device described in the foregoing embodiments, and is not limited herein. For example, the data obtaining unit 41 may be configured to obtain data such as page operation data, slider operation data, and sample data in the foregoing steps. For details, refer to the implementation manners provided in the foregoing steps, and details are not described herein again. The output unit 42 may be used to implement the implementation methods such as the output of the slider verification code and the output of the user authentication result based on the slider verification code. For details, refer to the implementation methods provided in the foregoing steps, and details are not described herein again. . The above-mentioned user behavior recognition unit 43 may be configured to perform an implementation manner such as determining a user behavior category based on a user behavior recognition model in the foregoing steps. For details, refer to the implementation manners provided in the foregoing steps, and details are not described herein again. The above-mentioned authentication response unit 44 may be configured to execute a related implementation manner of performing a user authentication response based on a determination result output by a user behavior recognition model in the foregoing embodiments. For details, refer to the implementation manners provided in the foregoing steps, and details are not described herein.

In the embodiment of the present application, the user authentication device may use the user group database of the target service or the sample data obtained based on big data analysis as the sample data trained by the user behavior recognition model for slider verification code verification, and then use fuzzy clustering. Analyze algorithms to build a user behavior recognition model. User behavior recognition model based on slider verification code verification, which can determine the user behavior category on the page operation data and / or slider operation data collected by the user authentication based on the target slider verification code verification, and then based on the user behavior The user behavior category identified by the recognition model responds to the user authentication of the target service. If the user authentication of the target service is completed based on the user behavior category, the target service can be started; otherwise, the user authentication of the target service is disconnected, the operation is simple, the security of the slider verification code verification can be improved, and the slider verification code verification can be effectively prevented. Network attacks to improve network security. Optionally, when the user behavior of the machine user is detected based on the user behavior recognition model, a network administrator such as a service administrator or a network engineer who reports the user information based on the machine user to the target service can further ensure the verification of the slider verification code. The requested target service is more secure and applicable.

Referring to FIG. 5, FIG. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present application. As shown in FIG. 5, the terminal device in this embodiment may include one or more processors 501 and a memory 502. The processor 501 and the memory 502 are connected via a bus 503. The memory 502 is configured to store a computer program. The computer program includes program instructions. The processor 501 is configured to execute the program instructions stored in the memory 502, and perform the following operations:

Based on the user behavior recognition model verified by the slider verification code, the user behavior category verified by the slider verification code corresponding to the first page operation data and the first slider operation data is determined, and the user behavior recognition model is determined by the slider verification code. The verified sample data is obtained through training. The above sample data includes at least first user behavior sample data corresponding to the first category of users and second user behavior sample data corresponding to the second category of users, and any user behavior sample data includes page operations. Data and / or slider operation data;

In some feasible implementation manners, the foregoing processor 501 is further configured to:

Obtaining sample data of at least two types of users, where the sample data is used for user behavior recognition model training for slider verification code verification, and the sample data includes at least the first user behavior sample data and the second user behavior sample data;

The above sample data is used as an input of a user behavior recognition model verified by a slider verification code, and the sample data is learned through the user behavior recognition model to obtain and identify a user corresponding to any page operation data and / or slider operation data. Capabilities of behavior categories.

In some feasible implementation manners, the foregoing processor 501 is configured to:

Through the above-mentioned user behavior recognition model, based on the training unsupervised fuzzy clustering analysis algorithm, the page operation data and / or slider operation data corresponding to each category of users in at least two categories of users included in the sample data are learned to obtain Ability to identify user behavior categories corresponding to page operation data and / or slider operation data corresponding to any category of users.

In some feasible implementation manners, the first category of users includes human users, the second category of users includes machine users, and the processor 501 is configured to:

When the verification of the target slider verification code is correct and the user behavior category is a human user, complete user authentication of the target service and enter a service processing interface of the target service;

When the verification of the target slider verification code is correct and the user behavior category is a machine user, close the user authentication interface of the target service to disconnect the user authentication of the target service, and report the user information of the machine user to the target Network administrator for business.

In some feasible implementation manners, the types of data included in the first page operation data and / or any of the page operation data in the sample data include: user operation position on the page, user operation time on the page, and One or more of the user's operation trajectories;

In some feasible implementation manners, the processor 501 may be a central processing unit (CPU), and the processor may also be another general-purpose processor, a digital signal processor (DSP), or a special-purpose integration. Circuit (application specific integrated circuit, ASIC), ready-made programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 502 may include a read-only memory and a random access memory, and provide instructions and data to the processor 501. A part of the memory 502 may further include a non-volatile random access memory. For example, the memory 502 may also store information of a device type.

In specific implementation, the terminal device can implement the implementation manners provided by the steps in FIG. 1 to FIG. 3 through the built-in functional modules. For details, refer to the implementation manners provided in the foregoing steps, and details are not described herein again.

In the embodiment of the present application, the terminal device may use the user group database of the target service or the sample data obtained based on the big data analysis as the sample data trained by the user behavior recognition model used for the verification of the slider verification code, and perform fuzzy cluster analysis. The algorithm builds a user behavior recognition model. User behavior recognition model based on slider verification code verification, which can determine the user behavior category on the page operation data and / or slider operation data collected by the user authentication based on the target slider verification code verification, and then based on the user behavior The user behavior category identified by the recognition model responds to the user authentication of the target service. If the user authentication of the target service is completed based on the user behavior category, the target service can be started; otherwise, the user authentication of the target service is disconnected, the operation is simple, the security of the slider verification code verification can be improved, and the slider verification code verification can be effectively prevented. Network attacks to improve network security. Optionally, when the user behavior of the machine user is detected based on the user behavior recognition model, a network administrator such as a service administrator or a network engineer who reports the user information based on the machine user to the target service can further ensure the verification of the slider verification code. The requested target service is more secure and applicable.

An embodiment of the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, each step in FIG. 1 to FIG. 3 is implemented. For the user authentication method based on the slider verification code, for details, refer to the implementation manners provided in the foregoing steps, and details are not described herein again.

The computer-readable storage medium may be a user authentication device based on a slider verification code provided in any of the foregoing embodiments or an internal storage unit of the terminal device, such as a hard disk or a memory of an electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, Flash card, etc. Further, the computer-readable storage medium may include both an internal storage unit and an external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been or will be output.

The terms "first", "second", "third", "fourth", etc. in the claims and the description of the present application and the drawings are used to distinguish different objects, rather than describing a specific order. Furthermore, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. Reference to "an embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The term "and / or" used in this specification and the appended claims refers to and includes any combination of one or more of the associated listed items and all possible combinations. The method and related devices provided in the embodiments of the present application are described with reference to the method flowchart and / or the structural schematic diagram provided in the embodiments of the present application, and each process of the method flowchart and / or the structural schematic diagram can be implemented by computer program instructions and / or Or a combination of blocks and processes and / or blocks in the flowcharts and / or block diagrams.

Claims

A user authentication method based on a slider verification code, wherein the method includes:

Acquiring first page operation data for starting a target service, and outputting a target slider verification code to a user interface for starting the target service according to the first page operation data;

Obtaining, from the user interface, first slider operation data for user authentication to start the target service based on the target slider verification code;

Based on the user behavior recognition model verified by the slider verification code, a user behavior category verified by the slider verification code corresponding to the first page operation data and the first slider operation data is determined. The sample data verified by the block verification code is obtained through training. The sample data includes at least first user behavior sample data corresponding to the first category of users and second user behavior sample data corresponding to the second category of users. Both include page operation data and / or slider operation data;

Complete user authentication of the target service according to the user behavior category and start the target service, or disconnect user authentication of the target service according to the user behavior category.
The method according to claim 1, further comprising:

Obtain sample data of at least two types of users, the sample data is used for training of a user behavior recognition model verified by a slider verification code, and the sample data includes at least the first user behavior sample data and the second user behavior sample;

And using the sample data as an input of a user behavior recognition model verified by a slider verification code, and learning the sample data through the user behavior recognition model to obtain identification corresponding to any page operation data and / or slider operation data. The ability of user behavior categories.
The method according to claim 2, wherein the learning the sample data by the user behavior recognition model comprises:

Learning the page operation data and / or slider operation data corresponding to each category of users in at least two categories of users included in the sample data through the user behavior recognition model based on the training unsupervised fuzzy cluster analysis algorithm, To obtain the ability to identify user behavior categories corresponding to any page operation data and / or slider operation data.
The method according to claim 2 or 3, wherein the acquiring sample data of at least two types of users comprises:

Obtaining sample data of at least two types of users from a user group database of the target service;

Wherein, the sample data includes page operation data when at least two types of users included in the user group database when each category user starts the target service, and / or slider operation data for user authentication.
The method according to claim 2 or 3, wherein the acquiring sample data of at least two types of users comprises:

Based on big data analysis, sample data of at least two types of users are obtained from a user group database of other services, the other services being one or more of the same type of services as the target service, and the user authentication method is slider verification code verification Business

Wherein, the sample data includes at least two types of users included in the user group database of the other services, page operation data when each category user starts the other service, and / or slider operation data for user authentication.
The method according to any one of claims 1-5, wherein the first category of users includes human users, and the second category of users includes machine users;

The user authentication for completing the target service according to the user behavior category and starting the target service, or disconnecting the user authentication for the target service according to the user behavior category includes:

When the verification of the target slider verification code is correct and the user behavior category is a human user, complete user authentication of the target service and enter a service management interface of the target service;

When the verification of the target slider verification code is correct and the user behavior category is a machine user, closing the user authentication interface of the target service to disconnect the user authentication of the target service, and the user of the machine user The information is reported to the network administrator corresponding to the target service.
The method according to any one of claims 1-6, wherein a data type included in the first page operation data and / or any page operation data in the sample data includes: One or more of a user operation position, a user operation time on the page, and a user operation track on the page;

The types of data included in the first slider operation data and / or any of the slider operation data in the sample data include: a user operation position on a slider verification code, a user operation duration of the slider verification code, One or more of the sliding parameters of the block verification code, wherein the sliding parameters include one or more of a sliding trajectory, a slider speed, a sliding duration, a sliding range, an aspect ratio of sliding, and an acceleration of sliding Species.
A user authentication device based on a slider verification code, wherein the device includes:

A data acquisition unit, configured to acquire first page operation data of a target business;

An output unit, configured to output a target slider verification code to a user interface that starts the target service according to the first page operation data obtained by the data obtaining unit;

The data obtaining unit is further configured to obtain, from the user interface, first slider operation data for performing user authentication for starting the target service based on the target slider verification code output by the output unit;

A user behavior recognition unit configured to determine a user behavior recognition model based on a slider verification code to determine the first page operation data and the slider verification code corresponding to the first slider operation data obtained by the data acquisition unit. Verified user behavior category, the user behavior recognition model is trained from sample data verified by a slider verification code, the sample data includes at least first user behavior sample data corresponding to the first category of users and second user category corresponding Second user behavior sample data, and any user behavior sample data includes page operation data and / or slider operation data;

An authentication response unit, configured to complete user authentication of the target service and start the target service according to the user behavior category identified by the user behavior identification unit, or disconnect a user of the target service according to the user behavior category Certified.
The apparatus according to claim 8, wherein the data acquisition unit is further configured to:

Obtain sample data of at least two types of users, the sample data is used for training of a user behavior recognition model verified by a slider verification code, and the sample data includes at least the first user behavior sample data and the second user behavior sample;

The user behavior recognition unit is configured to:

Using the sample data obtained by the data acquisition unit as an input of a user behavior recognition model verified by a slider verification code, and learning the sample data through the user behavior recognition model to obtain identification of any page operation data and / or slides The ability to block user action categories corresponding to data.
The device according to claim 9, wherein the user behavior recognition unit is configured to:

Based on the user behavior recognition model, based on the training unsupervised fuzzy cluster analysis algorithm, the page operation data and / or slider corresponding to each category of users in at least two categories of users included in the sample data obtained by the data acquisition unit The operation data is learned to obtain the ability to identify the page operation data and / or the slider operation data corresponding to the user behavior category corresponding to any category of users.
The device according to claim 9 or 10, wherein the data acquisition unit is configured to:

Obtaining sample data of at least two types of users from a user group database of the target service;

Wherein, the sample data includes page operation data when at least two types of users included in the user group database when each category user starts the target service, and / or slider operation data for user authentication.
The device according to claim 9 or 10, wherein the data acquisition unit is configured to:

Based on big data analysis, sample data of at least two types of users are obtained from a user group database of other services, the other services being one or more of the same type of services as the target service, and the user authentication method is slider verification code verification Business

Wherein, the sample data includes at least two types of users included in the user group database of the other services, page operation data when each category user starts the other service, and / or slider operation data for user authentication.
The device according to any one of claims 8-12, wherein the first category of users includes human users, and the second category of users includes machine users;

The authentication response unit is configured to:

When the slider verification code is correct and the user behavior recognition unit recognizes that the user behavior category is a human user, completing user authentication of the target service and entering a service processing interface of the target service;

When the slider verification code is verified correctly and the user behavior recognition unit recognizes that the user behavior category is a machine user, closing the user authentication interface of the target service to disconnect the user authentication of the target service, and The user information of the machine user is reported to a network administrator corresponding to the target service.
A terminal device includes a processor and a memory, and the processor and the memory are connected to each other. The memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to Invoking the program instructions performs the following operations:

Acquiring first page operation data for starting a target service, and outputting a target slider verification code to a user interface for starting the target service according to the first page operation data;

Obtaining, from the user interface, first slider operation data for user authentication to start the target service based on the target slider verification code;

Based on the user behavior recognition model verified by the slider verification code, a user behavior category verified by the slider verification code corresponding to the first page operation data and the first slider operation data is determined. The sample data verified by the block verification code is obtained through training. The sample data includes at least first user behavior sample data corresponding to the first category of users and second user behavior sample data corresponding to the second category of users. Both include page operation data and / or slider operation data;

Complete user authentication of the target service according to the user behavior category and start the target service, or disconnect user authentication of the target service according to the user behavior category.
The terminal device according to claim 14, wherein the processor is further configured to:

Obtain sample data of at least two types of users, the sample data is used for training of a user behavior recognition model verified by a slider verification code, and the sample data includes at least the first user behavior sample data and the second user behavior sample;

And using the sample data as an input of a user behavior recognition model verified by a slider verification code, and learning the sample data through the user behavior recognition model to obtain identification corresponding to any page operation data and / or slider operation data. The ability of user behavior categories.
The terminal device according to claim 15, wherein the processor is configured to:

Learning the page operation data and / or slider operation data corresponding to each category of users in at least two categories of users included in the sample data through the user behavior recognition model based on the training unsupervised fuzzy cluster analysis algorithm, To obtain the ability to identify user behavior categories corresponding to any page operation data and / or slider operation data.
The terminal device according to claim 15 or 16, wherein the processor is configured to:

Obtaining sample data of at least two types of users from a user group database of the target service;

Wherein, the sample data includes page operation data when at least two types of users included in the user group database when each category user starts the target service, and / or slider operation data for user authentication.
The terminal device according to claim 15 or 16, wherein the processor is configured to:

Based on big data analysis, sample data of at least two types of users are obtained from a user group database of other services, the other services being one or more of the same type of services as the target service, and the user authentication method is slider verification code verification Business

Wherein, the sample data includes at least two types of users included in the user group database of the other service, page operation data when each category user starts the other service, and / or slider operation data for user authentication.
The terminal device according to any one of claims 14 to 18, wherein the first category of users includes human users, and the second category of users includes machine users;

The processor is configured to:

When the verification of the target slider verification code is correct and the user behavior category is a human user, complete user authentication of the target service and enter a service management interface of the target service;

When the verification of the target slider verification code is correct and the user behavior category is a machine user, closing the user authentication interface of the target service to disconnect the user authentication of the target service, and the user of the machine user The information is reported to the network administrator corresponding to the target service.
A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes The method according to any one of 1-7 is required.