WO2020134608A1

WO2020134608A1 - Method, apparatus and device for pushing login mode, and method, apparatus and device for displaying login mode

Info

Publication number: WO2020134608A1
Application number: PCT/CN2019/115714
Authority: WO
Inventors: 张仕奇
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2018-12-27
Filing date: 2019-11-05
Publication date: 2020-07-02
Also published as: CN110032860B; TWI733217B; TW202032397A; CN110032860A

Abstract

A method, apparatus and device for pushing a login mode, and a method, apparatus and device for displaying a login mode. The method for pushing a login mode comprises: a serving end receiving a login request sent by a client (S202), wherein the login request at least comprises a login account of a user and environment information; if the login account is a registered account, acquiring behavior habit data of the login account within a period of time in the past (S204); inputting the environment information and the behavior habit data into a login mode prediction model to predict a login mode applicable to the user (S206); and pushing the applicable login mode to the user by means of the client (S208).

Description

Pushing and displaying method, device and equipment of login mode

Technical field

One or more embodiments of this specification relate to the field of computer technology, and in particular, to a method, device, and device for pushing and displaying login methods.

Background technique

With the widespread popularity of Internet technology, users have more and more diversified ways to log in to electronic websites. For example, there can be account password login (referred to as account secret login), SMS verification code login, voiceprint login, and face login login. However, not all the above login methods are available or suitable for all users. For example, for users who frequently enter the wrong password, it is not suitable for account login. As another example, if the user does not set a face-to-face login, face-to-face login is not available.

Therefore, a solution needs to be provided to push the applicable login method to the user when logging in to the electronic website.

Summary of the invention

One or more embodiments of this specification describe a method, device, and device for pushing and displaying a login method, which can improve the user's login success rate.

In the first aspect, a method for pushing a login method is provided, including:

The server receives the login request sent by the client; the login request includes at least the user's login account and environmental information;

If the login account is a registered account, obtain behavioral habits data of the login account in the past period of time;

Input the environmental information and the behavior habit data into a login mode prediction model to predict the login mode applicable to the user;

Pushing the login method to the user through the client.

In the second aspect, a display method of login method is provided, including:

When the client receives the login account input by the user, the environment information of the login account is obtained;

Send a login request to the server, the login request includes at least the login account and the environment information; the login request is used to instruct the server to obtain the login when determining that the login account is a registered account Behavior and habit data of the account in the past period of time; input the environmental information and the behavior and habit data into the login mode prediction model to predict the login mode applicable to the user;

Receiving the login method sent by the server;

Displaying a login page corresponding to the login method; the login page includes at least the login method.

In a third aspect, a push device for logging in is provided, including:

A receiving unit, configured to receive a login request sent by a client; the login request includes at least a user's login account and environmental information;

An obtaining unit, configured to obtain the behavior and habit data of the login account in the past period if the login account is a registered account;

A prediction unit, configured to input the environmental information received by the receiving unit and the behavior habit data acquired by the acquisition unit into a login mode prediction model to predict the login mode applicable to the user;

The pushing unit is configured to push the login method predicted by the prediction unit to the user through the client.

According to a fourth aspect, a login display device is provided, including:

An obtaining unit, configured to obtain environment information of the login account when receiving the login account input by the user;

A sending unit, configured to send a login request to the server, the login request includes at least the login account and the environmental information; the login request is used to instruct the server to determine that the login account is a registered account To obtain behavior and habit data of the login account in the past period of time; input the environmental information and the behavior and habit data into a login mode prediction model to predict the login mode applicable to the user;

A receiving unit, configured to receive the login method sent by the server;

A display unit, configured to display a login page corresponding to the login mode received by the receiving unit; the login page includes at least the login mode.

In a fifth aspect, a push device for logging in is provided, including:

Memory

One or more processors; and

One or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the following steps are implemented:

Receiving a login request sent by a client; the login request includes at least a user's login account and environmental information;

Pushing the login method to the user through the client.

In the sixth aspect, a display device for login mode is provided, including:

Memory

One or more processors; and

When receiving the login account input by the user, acquiring environmental information of the login account;

Receiving the login method sent by the server;

In one or more embodiments of this specification, a method, device, and device for pushing and displaying a login method are provided, and the server receives the login request sent by the client. The login request includes at least the user's login account and environmental information. If the login account is a registered account, the behavior and habit data of the login account in the past period of time are obtained. Enter the environmental information and behavioral habits data into the login mode prediction model to predict the user's applicable login mode. Push the applicable login method to the user through the client. It can be seen from the above that the scheme provided in this specification can push the applicable login method to the user based on the user's behavior and habits data and environmental information, which can improve the user's login success rate and further reduce the user's trial and error cost.

BRIEF DESCRIPTION

In order to more clearly explain the technical solutions of the embodiments of the present specification, the following will briefly introduce the drawings used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present specification. Those of ordinary skill in the art can obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic diagram of an application scenario of a push method of a login method provided by this specification;

2 is a flowchart of a method for pushing a login method provided by an embodiment of the present specification;

Figure 3a is a schematic diagram of the account input page provided by this specification;

Figure 3b is one of the schematic diagrams of the account login page provided in this manual;

Figure 3c is the second schematic diagram of the account login page provided in this manual;

Figure 3d is a schematic diagram of the face-login login page provided by this manual;

Figure 3e is a schematic diagram of the SMS login page provided by this manual;

4 is a flowchart of a method for displaying a login method provided by an embodiment of the present specification;

FIG. 5 is a schematic diagram of a push device for a login method provided by an embodiment of the present specification;

6 is a schematic diagram of a display device for a login method provided by an embodiment of the present specification;

7 is a schematic diagram of a push device in a login mode provided by an embodiment of the present specification;

FIG. 8 is a schematic diagram of a display device of a login method provided by an embodiment of the present specification.

detailed description

The solution provided in this specification will be described below in conjunction with the drawings.

Before describing the solution provided in this specification, the invention of the solution will be introduced as follows:

As described in the background art, there are various ways for users to log in to an electronic website. For these multiple login methods, if they are placed directly on the login page, it will increase the user's selection costs and trial and error costs, because not every user is suitable for each login method. For example, if the password is not used for a long time, the cost of trial and error for account login is high; for another example, many users do not prefer to log in with a face. In order to reduce the user's selection costs and trial and error costs, the applicant of this application considers that he can push the applicable login method to the user. However, how to determine the login method applicable to the user?

First, the applicant considers that the user's applicable login method is related to the user's behavior and habits. For example, for users who frequently log in using SMS verification codes, the user is suitable for logging in using SMS verification codes. As another example, for users who frequently enter the wrong password, it is suitable for face-to-face login or SMS verification code login. Therefore, the login method applicable to the user can be determined based on the user's behavior habit data.

Secondly, the login method applicable to the user is usually related to the scene information of the scene where the user is located. The scene information here includes but is not limited to the latitude and longitude positioning information of the user and the device information of the logged-in device. For example, when it is determined that the login device used by the user does not have a camera installed based on the device information, the user is not suitable for face login. For another example, when it is determined that the user's login location has changed based on the user's latitude and longitude positioning information, the user may be prompted to log in with a face login to ensure security. Therefore, the login method applicable to the user can be determined based on the scene information of the scene where the user is located.

In addition, the login account itself or the current time can also be used as a consideration for determining the login method. For example, if the login account is a non-secret account, the user is not suitable for account secret login. As another example, if the current time is night, the user is not suitable for face-swapping and so on.

After collecting the above information, how to determine the user's applicable login method?

It can be understood that the machine learning model can predict unknown data based on known data. Therefore, a machine learning model can be trained to determine the user's applicable login method. Specifically, it is possible to collect environmental information of multiple sample accounts and behavioral habits data over a period of time in the past. Based on the collected data, the machine learning model is trained. It can be understood that the above sample account has a corresponding sample label, and the sample label may refer to a login method applicable to the sample account.

After training the machine learning model, when a user logs in to the electronic website, the current user's environmental information and behavioral habits data can be input into the trained machine learning model. The machine learning model predicts the user's applicable login method. Afterwards, push the login method to the user to improve the user's login success rate, which can greatly shorten the login time.

The above is the inventive concept of the solution provided in this specification, and this solution can be obtained based on the inventive concept. The plan is elaborated below.

FIG. 1 is a schematic diagram of an application scenario of a push method of a login method provided in this specification. The client in FIG. 1 may refer to a client of an electronic website, which is usually installed on a user's terminal device. The server can refer to the server of the electronic website. In this specification, the interaction process between the client and the server can be as follows: The user starts the client on the terminal device. After the client is started, the boot page is first loaded, and a login button is provided on the boot page. When receiving the user's click instruction on the login button, jump to the account input page. When the user enters the corresponding login account on the account input page and clicks the button indicating that the login account input is completed, the client can send a login request to the server. The login request may include at least a login account and environmental information of the environment in which the user is located. The environment information here includes but is not limited to the latitude and longitude positioning information of the user and the device information of the logged-in device.

After receiving the above login request, the server can determine whether the login account is a registered account. If not, then guide the user to register. If it is, the behavior and habit data related to the login account are obtained. Input the received environmental information and the acquired behavior and habit data into the machine learning model to predict the login method applicable to the user.

The server returns the predicted login method to the client, and then the client displays the login method to the user.

FIG. 2 is a flowchart of a method for pushing a login method provided by an embodiment of the present specification. The execution subject of the method may be the server in FIG. 1. As shown in FIG. 1, the method may specifically include:

In step S202, the server receives the login request sent by the client.

Specifically, when the user starts the installed client on the terminal device, the client first loads the guide page, and a login button is provided on the guide page. When receiving the user's click instruction on the login button, jump to the account input page. When the user enters the corresponding login account on the account input page and clicks the button indicating that the login account input is completed, the client can send a login request to the server. The login request may include at least a login account and environmental information of the environment in which the user is located. The environment information here includes but is not limited to the latitude and longitude positioning information of the user and the device information of the logged-in device.

Taking the client as the Alipay client as an example, the account input page provided in this specification may be as shown in FIG. 3a. In Figure 3a, the input box for the login account and the "Continue" button are shown. It can be understood that, initially, when the user has not entered the login account, the color of the “Continue” button may be gray, that is, unavailable. After the user enters the corresponding login account in the input box, the color of the "Continue" button becomes blue and can be clicked. When the Alipay client receives the user's click instruction on the button, the client can send a login request to the server.

It should be understood that FIG. 3a is only for exemplary purposes. In practical applications, the account input page may further include other controls, for example, an input box for entering a real name may also be included, which is not limited in this specification.

In step S204, if the login account is a registered account, the behavior and habit data of the login account in the past period of time are obtained.

The behavior habit data here may refer to data related to the user's login behavior, for example, it may include login account, login time, login method, and result information of successful login, etc. In addition, the above-mentioned past period of time can be determined according to actual needs, such as: 30 days and so on.

In one example, the server can obtain the behavior and habit data of the login account in the past period from the background database.

It should also be noted that if the login account is a non-registered account, the user can be guided to register first, and then log in, etc.

In step S206, the environmental information and the behavior and habit data are input into the login mode prediction model to predict the login mode applicable to the user.

It should be noted that the login mode prediction model here may be obtained after training the machine learning model based on the environment information of multiple sample accounts and the behavior and habit data in the past period of time. The sample account has a corresponding sample label, where the sample label may refer to the login method applicable to the sample account. Of course, in practical applications, the above-mentioned machine learning model can also be trained in conjunction with the login account itself, so as to improve the accuracy of the prediction model predicted by the login method.

In addition, the above login methods may include, but are not limited to, account password login, face recognition login, SMS verification code login, voiceprint login, and other business system authorized login (such as Taobao authorized login). Among them, account password login and SMS verification code login are conventional login methods, which are available to all users. Face-to-face login, voiceprint login, and other business system authorization logins are settable login methods, which are only available after the user has made the corresponding settings, that is to say, only the electronic website is available after the user's basic information has been collected in advance. Taking the face-swapping login as an example, the verification process may be: collecting the user's face information in real time, and comparing the collected face information with the pre-collected face information to determine whether it is the person. After confirming that it is you, jump to the normal use page.

It should be noted that the login mode prediction model provided in this specification actually predicts based on a series of predetermined rules corresponding to different login modes. Specifically, if the environmental information and/or behavioral habit data of the login account meet the rules corresponding to a certain login method, the login method may be used as the login method applicable to the user.

Taking account password login as an example, the corresponding rule may be: there is a record of successful password verification within 30 days. As another example, the rule corresponding to the login of the SMS verification code may be: there is a record of successful SMS verification within 30 days; and/or, the login account is a non-secret account; and/or, the SMS verification code is often used for login. For another example, the rule corresponding to the face login can be: the login time is daytime; and/or, the wrong password is often entered; and/or, the login device and/or the login location have changed, etc.

It should be understood that the above only illustrates the rules corresponding to different login methods. In practical applications, there may be dozens or even hundreds of rules, so it can be predicted by training a machine learning model.

Optionally, the current time can also be obtained. When the current time is also obtained, the current time, environmental information, and behavioral habits data can be input into the login mode prediction model to predict the login mode applicable to the user.

It should be noted that the login method applicable to the user predicted by the embodiment of the present specification may be any of the following: account password login, face login, SMS verification code login, voiceprint login, and other business system authorization login.

Step S208: Push the predicted login method to the user through the client.

It should be noted that, because some people are not used to logging in with face brushing, in order to realize the accurate push of the login method of this type of crowd, in this embodiment of the specification, when the login method applied by the user is predicted to be face login, step S208 may also be used. Replace with the following steps:

Enter the environmental information and behavioral habits data into the preference estimation model to estimate whether the user prefers to log in with a face. If the user prefers to log in with a face swipe, the login method is pushed to the user.

It should be noted that the preference estimation model here may also be obtained after training the machine learning model based on the environmental information of the above multiple sample accounts and the behavior and habit data in the past period of time. The difference is that when training the preference estimation model, different sample labels can be set for the sample account. For example, the sample tags here can indicate whether the user prefers to log in with a face.

In the embodiment of the present specification, in addition to the applicable login method to the user, other login methods can also be pushed to the user. The determination process of the other login methods can be as follows:

First, the server can obtain a preset set of login methods. The preset login method set may include two types of login methods: a conventional login method and a settable login method. For the conventional login method, the conventional login method is directly selected as the candidate login method. For the settable login method, determine whether the settable login method is set in the login account. In one implementation, a login account that has a settable login method can be marked. Therefore, the above judgment can be made based on whether the login account is a marked account. If so, the settable login method is selected as the candidate login method. The login methods applicable to the user are removed from the candidate login methods to obtain other login methods.

After the client receives the login method applicable to the user and other log-in methods sent by the server, the client needs to perform local feasibility judgment for some other log-in methods. Specifically, it is assumed that other login methods received by the client include: when other business systems authorize login, the client can determine whether the login method is feasible. If feasible, use it as another login method, otherwise, delete the login method. After that, the client can show the user the applicable login method and other login methods. In one implementation, different pages can be jumped for different applicable login methods.

For example, when the applicable login method is account secret login, you can jump to the account secret login page. Taking the client as the Alipay client as an example, the account login page may be as shown in FIG. 3b. In Figure 3b, not only the current login method applicable to the user: account secret login, but also the corresponding buttons for switching other login methods are shown on the right. In addition, the "Back" button is also shown. When the user clicks the "back" button, he can jump from the account login page to the account input page.

It should be understood that the account login page provided in this specification is not limited to that shown in the figure. For example, the "Forgot Password" and "Switch Login Mode" buttons in Figure 3b can be flexibly adjusted. For example, when the other final log-in methods that can be determined are 0, the "Switch Login Method" button may not be displayed, and the "Forgot Password" button may be centered. When the final other login method is one, the text corresponding to the "Switch Login Mode" button can be directly replaced with the other login method. Taking the one login method as the SMS verification code login as an example, it may be as shown in FIG. 3c.

As another example, when the applicable login method is face-to-face login, you can jump to the face-to-face login page. Taking the client as the Alipay client as an example, the face-to-face login page may be as shown in FIG. 3d. In Figure 3d, the account input box is not editable. When the user clicks the "Face to face login" button, the face recognition process can be entered. Since the process of face recognition is a conventional conventional technology, it will not be repeated here. In addition, the description of the "Back" button is the same as described above.

It should be understood that the face login page provided in this specification is not limited to the one shown in the figure. For example, the "switch login mode" button in FIG. 3d can also be flexibly adjusted according to the number of other login modes, and the specific adjustment mode can be the same as described above, and will not be repeated here.

As another example, when the applicable login method is SMS verification code login, you can jump to the SMS login page. Taking the client as the Alipay client as an example, the SMS login page may be as shown in FIG. 3e. In FIG. 3e, when jumping to the SMS verification code login page from another page (for example, the account input page or account secret login page), the client can obtain the mobile phone number bound to the login account from the server. If the mobile phone number is obtained, the mobile phone number can be automatically entered in the mobile phone number input box of the SMS login page; otherwise, the user manually fills in. In addition, according to the mobile phone number filled in automatically or manually, the matching mobile phone attribution can be obtained and displayed. Figure 3e also shows the "Back" button. When the user clicks the "back" button, he can jump from the SMS login page to the other pages mentioned above.

It should be understood that the short message login page provided in this manual is not limited to that shown in the figure. For example, the “password login” button in FIG. 3e can also be flexibly adjusted according to the number of other login methods, and the specific adjustment method can be the same as described above, and will not be repeated here.

In summary, the method for pushing the login method provided in the embodiments of the present specification can push the applicable login method to the user based on the user's environmental information and behavior habits data, which can greatly improve the user's login success rate and shorten the login duration .

4 is a flowchart of a method for displaying a login method provided by an embodiment of the present specification. The execution subject of the method may be the client in FIG. 1. As shown in FIG. 4, the method may specifically include:

Step S402: When the client receives the login account input by the user, it acquires the environment information of the login account.

Specifically, when the user starts the installed client on the terminal device, the client first loads the guide page, and a login button is provided on the guide page. When receiving the user's click instruction on the login button, jump to the account input page. The client can obtain the user's login account through the account input page. After obtaining the login account, the environment information of the login account can be obtained. The environment information here may include, but is not limited to, latitude and longitude positioning information of the user and device information of the logged-in device.

Step S404: Send a login request to the server.

The login request may include at least a login account and environmental information. After receiving the login request, the server can first determine whether the login account is a registered account. If it is a non-registered account, you can first guide the user to register, and then log in. If it is a registered account, the behavior and habit data of the login account in the past period of time are obtained. The behavior habit data here may refer to data related to the user's login behavior, for example, it may include login account, login time, login method, and result information of successful login, etc. In addition, the above-mentioned past period of time can be determined according to actual needs, such as: 30 days and so on.

Input the received environmental information and the acquired behavior and habit data into the login mode prediction model to predict the login mode applicable to the user. Here, the login mode prediction model can be obtained after training the machine learning model based on the environment information of multiple sample accounts and the behavior and habit data in the past period of time. The sample account has a corresponding sample label, where the sample label may refer to the login method applicable to the sample account. Of course, in practical applications, the above-mentioned machine learning model can also be trained in conjunction with the login account itself, so as to improve the accuracy of the prediction model predicted by the login method.

The above login methods may include, but are not limited to, account password login, face recognition login, SMS verification code login, voiceprint login, and other business system authorized login (for example, Taobao authorized login). Among them, account password login and SMS verification code login are conventional login methods, which are available to all users. Face-to-face login, voiceprint login, and other business system authorization logins are settable login methods, which are only available after the user has made the corresponding settings, that is to say, only the electronic website is available after the user's basic information has been collected in advance. Taking the face-swapping login as an example, the verification process may be: collecting the user's face information in real time, and comparing the collected face information with the pre-collected face information to determine whether it is the person. After confirming that it is you, jump to the normal use page.

It should be noted that, because some people are not used to logging in with face brushing, in order to realize the accurate push of the login method of this type of crowd, the embodiment of this specification can also execute the following when predicting that the login method applicable to the user is face brushing. Step: Input environmental information and behavioral habit data into the preference estimation model to estimate whether the user prefers to log in with a face. If the user prefers to log in with a face swipe, the login method is pushed to the user.

Step S406: Receive the applicable login method sent by the server.

In addition, you can also receive other login methods. For some other login methods, the client also needs to make local feasibility judgments. Specifically, it is assumed that other login methods received by the client include: when other business systems authorize login, the client can determine whether the login method is feasible. If feasible, use it as another login method, otherwise, delete the login method.

Step S408, displaying the login page corresponding to the login method.

For example, when the applicable login method is account secret login, you can jump to the account secret login page. Taking the client as the Alipay client as an example, the account login page may be as shown in FIG. 3b. As another example, when the applicable login method is face-to-face login, you can jump to the face-to-face login page. Taking the client as the Alipay client as an example, the face-to-face login page may be as shown in FIG. 3d. As another example, when the applicable login method is SMS verification code login, you can jump to the SMS login page. Taking the client as the Alipay client as an example, its SMS login page can be shown in Figure 3e. The descriptions of FIG. 3b, FIG. 3d and FIG. 3e are the same as above, and will not be repeated here.

In summary, the display method of the login method provided by the embodiment of the present specification can display the applicable login method to the user, which can greatly improve the user's login success rate and shorten the login duration.

Corresponding to the above-mentioned login method push method, an embodiment of the present specification further provides a login method push device. As shown in FIG. 5, the device may include:

The receiving unit 502 is configured to receive a login request sent by a client. The login request may include at least a user's login account and environment information.

The obtaining unit 504 is configured to obtain behavior and habit data of the login account in the past period if the login account is a registered account.

The prediction unit 506 is used to input the environmental information received by the receiving unit 502 and the behavior habit data acquired by the obtaining unit 504 into the login mode prediction model to predict the login mode applicable to the user.

The login mode prediction model may be obtained after training the machine learning model based on the environment information of multiple sample accounts and the behavior and habit data in the past period of time. The sample account has a corresponding sample label, and the sample label may refer to a login method applicable to the sample account.

The pushing unit 508 is used to push the login method predicted by the prediction unit 506 to the user through the client.

The pushing unit 508 may be specifically used for:

Determine whether the login method is face-to-face login.

When the login method is face-swapping, input environmental information and behavioral habit data into the preference estimation model to estimate whether the user prefers face-swapping.

If the user prefers to log in with a face, the login method is pushed to the user.

Optionally, the device may further include: a selection unit 510, a judgment unit 512, and a removal unit 514.

The obtaining unit 504 is also used to obtain a preset set of login methods. The preset set of login methods includes two types of login methods: a conventional login method and a settable login method.

The selecting unit 510 is configured to directly select the conventional login method as the candidate login method for the conventional login method acquired by the obtaining unit 504.

The determining unit 512 is configured to determine whether the settable login method is set in the login account for the settable login method acquired by the acquiring unit 504.

The selecting unit 510 is also used to select the settable login method as a candidate login method.

The removing unit 514 is configured to remove the login method applicable to the user from the candidate login methods selected by the selecting unit 510 to obtain other login methods.

The pushing unit 508 is also used to push other login methods to the user.

Optionally, the obtaining unit 504 is also used to obtain the current time.

The prediction unit 506 may be specifically used to input environmental information, behavioral habit data, and the current time into the login mode prediction model to predict the login mode applicable to the user.

The login methods applicable to the above users may include any one of the following: account password login, face login, SMS verification code login, voiceprint login, and other business system authorization login. Among them, account password login and SMS verification code login are conventional login methods. Face login, voiceprint login and other business system authorization logins are configurable login methods.

The functions of the functional modules of the device in the above embodiments of the present specification can be implemented through the steps of the above method embodiments. Therefore, the specific working process of the device provided by an embodiment of the present specification will not be repeated here.

According to an embodiment of the present specification, in a login method push device, the receiving unit 502 receives a login request sent by a client. The login request may include at least a user's login account and environment information. If the login account is a registered account, the obtaining unit 504 obtains behavioral habits data of the login account in the past period of time. The prediction unit 506 inputs environmental information and behavioral habit data into the login mode prediction model to predict the login mode applicable to the user. The pushing unit 508 pushes the predicted login method to the user through the client. Thus, the user's login success rate can be greatly improved.

The push device for login mode provided by an embodiment of this specification may be a module or unit in the server side in FIG. 1.

Corresponding to the above login method display method, an embodiment of this specification also provides a login method display device. As shown in FIG. 6, the device may include:

The obtaining unit 602 is configured to obtain environment information of the login account when receiving the login account input by the user.

The sending unit 604 is configured to send a login request to the server. The login request may include at least a login account and environmental information. The login request is used to instruct the server to obtain the behavior and habit data of the login account in the past period when determining that the login account is a registered account. Enter the environmental information and behavioral habits data into the login mode prediction model to predict the user's applicable login mode.

The receiving unit 606 is used to receive the login method sent by the server.

The display unit 608 is configured to display a login page corresponding to the login mode received by the receiving unit 606, and the login page includes at least the login mode.

Optionally, the login page may also include other login methods, which are selected by the server from a preset set of login methods. The preset set of login methods includes two types of login methods: regular login methods and settable login methods.

The display device of the login mode provided by an embodiment of this specification can improve the user's login success rate.

The log-in display device provided by an embodiment of this specification may be a module or unit of the client in FIG. 1.

Corresponding to the above login method push method, an embodiment of this specification also provides a login method push device. As shown in FIG. 7, the device may include: a memory 702, one or more processors 704, and one or more Programs. The one or more programs are stored in the memory 702, and are configured to be executed by one or more processors 704. When the programs are executed by the processor 704, the following steps are implemented:

Receive a login request sent by the client, where the login request includes at least the user's login account and environmental information.

If the login account is a registered account, the behavior and habit data of the login account in the past period of time is obtained.

Enter the environmental information and behavioral habits data into the login mode prediction model to predict the user's applicable login mode.

Push the login method to the user through the client.

The push device in the login mode provided by an embodiment of this specification can improve the user's login success rate.

Corresponding to the above login method display method, embodiments of the present specification also provide a login method display device. As shown in FIG. 8, the device may include: a memory 802, one or more processors 804, and one or more Programs. The one or more programs are stored in the memory 802, and are configured to be executed by one or more processors 804, and when the program is executed by the processor 804, the following steps are implemented:

When receiving the login account input by the user, the environment information of the login account is obtained.

Send a login request to the server, the login request includes at least a login account and environmental information. The login request is used to instruct the server to obtain the behavior and habit data of the login account in the past period when determining that the login account is a registered account. Enter the environmental information and behavioral habits data into the login mode prediction model to predict the user's applicable login mode.

Receive the login method sent by the server.

The login page corresponding to the login method is displayed, and the login page includes at least the login method predicted by the server.

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

The steps of the method or algorithm described in conjunction with the disclosure of the present specification may be implemented by hardware, or may be implemented by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, mobile hard disk, CD-ROM or any other form of storage known in the art Medium. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be a component of the processor. The processor and the storage medium may be located in the ASIC. In addition, the ASIC may be located in the server. Of course, the processor and the storage medium may also exist as discrete components in the server.

Those skilled in the art should be aware that in one or more of the above examples, the functions described in the present invention may be implemented by hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes computer storage media and communication media, where communication media includes any medium that facilitates transfer of a computer program from one place to another. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

The foregoing describes specific embodiments of the present specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of this specification in detail. It should be understood that the above descriptions are only specific implementations of this specification and are not intended to limit the scope of this specification. The scope of protection, any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of this specification, shall be included in the scope of protection of this specification.

Claims

A push method for login, including:

The server receives the login request sent by the client; the login request includes at least the user's login account and environmental information;

If the login account is a registered account, obtain behavioral habits data of the login account in the past period of time;

Input the environmental information and the behavior habit data into a login mode prediction model to predict the login mode applicable to the user;

Pushing the login method to the user through the client.
The method of claim 1, the pushing the login method to the user through the client includes:

Judging whether the login method is face-swapping;

When the login method is face-swapping, input the environmental information and the behavioral habit data into a preference prediction model to estimate whether the user prefers the face-swapping login;

If the user prefers the face-to-face login, the login method is pushed to the user.
The method of claim 1, further comprising:

Obtain a preset set of login methods; the preset set of login methods includes two types of login methods: a conventional login method and a settable login method;

For the conventional login method, directly select the conventional login method as a candidate login method;

For the settable login method, determine whether the settable login method is set in the login account; if so, select the settable login method as a candidate login method;

Removing the login method applicable to the user from the candidate login methods to obtain other login methods;

Push the other log-in methods to the user.
The method according to claim 1, wherein the login mode prediction model is obtained after training a machine learning model based on environmental information of multiple sample accounts and behavioral habits data over a period of time in the past; the sample account has Corresponding sample label, the sample label refers to the login method applicable to the sample account.
The method of claim 1, further comprising:

Get the current time;

The inputting the environmental information and the behavior and habit data into the login mode prediction model to predict the login mode applicable to the user includes:

The environment information, the behavior habit data, and the current time are input into a login mode prediction model to predict the login mode applicable to the user.
The method according to any one of claims 1-5, the applicable login method of the user includes any one of the following: account password login, face login, SMS verification code login, voiceprint login, and other business system authorization login ; Among them, the account password login and the SMS verification code login belong to the conventional login method; the face login, the voiceprint login and the other business system authorized login belong to the settable login method.
A display method of login mode, including:

When the client receives the login account input by the user, the environment information of the login account is obtained;

Send a login request to the server, the login request includes at least the login account and the environment information; the login request is used to instruct the server to obtain the login when determining that the login account is a registered account Behavior and habit data of the account in the past period of time; input the environmental information and the behavior and habit data into the login mode prediction model to predict the login mode applicable to the user;

Receiving the login method sent by the server;

Displaying a login page corresponding to the login method; the login page includes at least the login method.
According to the method of claim 7, the login page further includes other login modes, the other login modes are selected by the server from a preset set of login modes; the preset login mode There are two types of login methods in the collection: regular login methods and settable login methods.
A push device for login mode, including:

A receiving unit, configured to receive a login request sent by a client; the login request includes at least a user's login account and environmental information;

An obtaining unit, configured to obtain the behavior and habit data of the login account in the past period if the login account is a registered account;

A prediction unit, configured to input the environmental information received by the receiving unit and the behavior habit data acquired by the acquisition unit into a login mode prediction model to predict the login mode applicable to the user;

The pushing unit is configured to push the login method predicted by the prediction unit to the user through the client.
The apparatus according to claim 9, the pushing unit is specifically configured to:

Judging whether the login method is face-swapping;

When the login method is face-swapping, input the environmental information and the behavioral habit data into a preference prediction model to estimate whether the user prefers the face-swapping login;

If the user prefers the face-to-face login, the login method is pushed to the user.
The device according to claim 9, further comprising: a selection unit, a judgment unit, and a removal unit;

The acquiring unit is also used to acquire a preset set of login methods; the preset set of login methods includes two types of login methods: a conventional login method and a settable login method;

The selecting unit is configured to directly select the conventional login mode as a candidate login mode for the conventional login mode acquired by the acquiring unit;

The determining unit is configured to determine whether the settable login mode is set for the login account for the settable login mode acquired by the acquiring unit;

The selecting unit is also used to select the settable login method as a candidate login method;

The removing unit is configured to remove the login mode applicable to the user from the candidate login modes selected by the selection unit to obtain other login modes;

The pushing unit shown is also used to push the other login methods to the user.
The apparatus according to claim 9, wherein the login mode prediction model is obtained after training a machine learning model based on environmental information of multiple sample accounts and behavioral habits data over a period of time in the past; the sample account has Corresponding sample label, the sample label refers to the login method applicable to the sample account.
The device according to claim 9,

The obtaining unit is also used to obtain the current time;

The prediction unit is specifically configured to: input the environmental information, the behavior habit data, and the current time into a login mode prediction model to predict the login mode applicable to the user.
The device according to any one of claims 9-13, the applicable login method of the user includes any one of the following: account password login, face login, SMS verification code login, voiceprint login, and other business system authorization login ; Among them, the account password login and the SMS verification code login belong to the conventional login method; the face login, the voiceprint login and the other business system authorized login belong to the settable login method.
A display device of login mode, including:

An obtaining unit, configured to obtain environment information of the login account when receiving the login account input by the user;

A sending unit, configured to send a login request to the server, the login request includes at least the login account and the environmental information; the login request is used to instruct the server to determine that the login account is a registered account To obtain behavior and habit data of the login account in the past period of time; input the environmental information and the behavior and habit data into a login mode prediction model to predict the login mode applicable to the user;

A receiving unit, configured to receive the login method sent by the server;

A display unit, configured to display a login page corresponding to the login mode received by the receiving unit; the login page includes at least the login mode.
The apparatus according to claim 15, the login page further includes other login modes, the other login modes are selected by the server from a preset set of login modes; the preset login mode There are two types of login methods in the collection: regular login methods and settable login methods.
A push device for login, including:

Memory

One or more processors; and

One or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the following steps are implemented:

Receiving a login request sent by a client; the login request includes at least a user's login account and environmental information;

If the login account is a registered account, obtain behavioral habits data of the login account in the past period of time;

Input the environmental information and the behavior habit data into a login mode prediction model to predict the login mode applicable to the user;

Pushing the login method to the user through the client.
A login display device, including:

Memory

One or more processors; and

One or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the following steps are implemented:

When receiving the login account input by the user, acquiring environmental information of the login account;

Send a login request to the server, the login request includes at least the login account and the environment information; the login request is used to instruct the server to obtain the login when determining that the login account is a registered account Behavior and habit data of the account in the past period of time; input the environmental information and the behavior and habit data into the login mode prediction model to predict the login mode applicable to the user;

Receiving the login method sent by the server;

Displaying a login page corresponding to the login method; the login page includes at least the login method.