A software login method and system based on big data

Abstract

A software login method and system based on big data provided by the present invention relate to the technical field of software login. The method includes obtaining a mobile phone screen recording video, multiple logged-in software, and unlogged software; determining the security credibility and usage frequency of each logged-in software using an information processing model based on the mobile phone screen recording video and the information of the multiple logged-in software; determining the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software; and verifying and logging in the unlogged software based on the login method of the unlogged software. This method can accurately provide a suitable login method for users.

Description

Technical Field

[0001] The present invention relates to the technical field of software login, and particularly to a software login method and system based on big data. Background Art

[0002] With the rapid expansion of the smartphone application ecosystem, users need to frequently switch and log in to multiple software in daily use, which not only increases the operation burden on users, but also poses higher requirements for the security and convenience of software login. Traditional login methods, such as verifying through usernames and passwords, are difficult to meet the requirements of the current complex and changeable application environment. Especially when faced with unlogged software, it is particularly important to dynamically adjust the login strategy according to user behavior habits and security requirements. Existing solutions often rely on a single verification method and lack the effective use of user historical behavior data, resulting in an inefficient and insecure login process. Therefore, how to quickly and accurately determine the login method of software is an urgent problem to be solved currently. Summary of the Invention

[0003] The main technical problem to be solved by the present invention is to quickly and accurately determine the login method of software.

[0004] According to a first aspect, the present invention provides a software login method based on big data, including: obtaining a mobile phone screen recording video, multiple logged-in software, and unlogged software; using an information processing model to determine the security credibility and usage frequency of each logged-in software based on the mobile phone screen recording video and information of the multiple logged-in software; determining the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software; and performing verification login on the unlogged software based on the login method of the unlogged software.

[0005] In a possible implementation manner, the determining the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software includes: generating an estimated security requirement level, an estimated usage frequency, and a similarity between the unlogged software and each logged-in software of the unlogged software by using a generative adversarial network based on unlogged software information, the security credibility and usage frequency of each logged-in software; constructing a graph structure, where the graph structure includes multiple nodes and multiple edges between the nodes, the multiple nodes include an unlogged software node and multiple logged-in software nodes, the unlogged software node is the central node, each unlogged software is respectively connected to the unlogged software node to establish an edge, the node features of the unlogged software node are the estimated security requirement level and estimated usage frequency of the unlogged software, the node features of each logged-in software node include the security credibility and usage frequency of the logged-in software, and the edges between the nodes are the similarities between the unlogged software and the logged-in software; and determining the login method of the unlogged software by processing the graph structure based on a graph autoencoder.

[0006] In a possible implementation, the login methods for the unlogged software include collaborative verification login of face recognition and SMS verification code, SMS verification code verification, password verification login, and direct login without verification.

[0007] In a possible implementation, the information processing model is a long short-term neural network model. The input of the information processing model is the mobile phone screen recording video and the information of multiple logged-in software, and the output of the information processing model is the security credibility and usage frequency of each logged-in software.

[0008] According to a second aspect, the present invention provides a software login system based on big data, including:

[0009] An acquisition module, configured to acquire a mobile phone screen recording video, multiple logged-in software, and unlogged software;

[0010] An information processing module, configured to use an information processing model to determine the security credibility and usage frequency of each logged-in software based on the mobile phone screen recording video and the information of multiple logged-in software;

[0011] A login method confirmation module, configured to determine the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software;

[0012] A login verification module, configured to perform verification login on the unlogged software based on the login method of the unlogged software.

[0013] In a possible implementation, the login method confirmation module is further configured to: based on the unlogged software information, the security credibility and usage frequency of each logged-in software, use a generative adversarial network to generate the estimated security requirement level, estimated usage frequency of the unlogged software, and the similarity between the unlogged software and each logged-in software; construct a graph structure, where the graph structure includes multiple nodes and multiple edges between the nodes. The multiple nodes include an unlogged software node and multiple logged-in software nodes, where the unlogged software node is the central node. Each unlogged software establishes an edge with the unlogged software node respectively. The node features of the unlogged software node are the estimated security requirement level and estimated usage frequency of the unlogged software. The node features of each logged-in software node include the security credibility and usage frequency of the logged-in software. The edges between the nodes are the similarity between the unlogged software and the logged-in software; and determine the login method of the unlogged software based on processing the graph structure by a graph autoencoder.

[0014] In a possible implementation, the login methods for the unlogged software include collaborative verification login of face recognition and SMS verification code, SMS verification code verification, password verification login, and direct login without verification.

[0015] In a possible implementation, the information processing model is a long short-term neural network model. The input of the information processing model is the mobile phone screen recording video and the information of multiple logged-in software, and the output of the information processing model is the security credibility and usage frequency of each logged-in software.

[0016] According to a third aspect, an embodiment of the present invention provides an electronic device, including: a processor; a memory; and a computer program; wherein, the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above. The method includes: obtaining a mobile phone screen recording video, multiple logged-in software, and unlogged software; determining the security credibility and usage frequency of each logged-in software using an information processing model based on the mobile phone screen recording video and the information of multiple logged-in software; determining the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software; and verifying the login of the unlogged software based on the login method of the unlogged software.

[0017] According to a fourth aspect, the present embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the software login method based on big data as provided above. The method includes: obtaining a mobile phone screen recording video, multiple logged-in software, and unlogged software; determining the security credibility and usage frequency of each logged-in software using an information processing model based on the mobile phone screen recording video and the information of multiple logged-in software; determining the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software; and verifying the login of the unlogged software based on the login method of the unlogged software.

[0018] A software login method and system based on big data provided by the present invention. The method includes obtaining a mobile phone screen recording video, multiple logged-in software, and unlogged software; determining the security credibility and usage frequency of each logged-in software using an information processing model based on the mobile phone screen recording video and the information of multiple logged-in software; determining the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software; and verifying the login of the unlogged software based on the login method of the unlogged software. This method can quickly and accurately determine the login method of the software. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of an application scenario of a software login method based on big data provided by an embodiment of the present invention;

[0020] Figure 2Schematic flowchart of a software login method based on big data provided by an embodiment of the present invention;

[0021] Figure 3 Schematic flowchart of a method for determining a login method for an unlogged software provided by an embodiment of the present invention;

[0022] Figure 4 Schematic diagram of a software login system based on big data provided by an embodiment of the present invention;

[0023] Figure 5 Schematic diagram of an electronic device provided by an embodiment of the present invention;

[0024] Figure 6 Schematic structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0025] The present invention will be further described in detail below in conjunction with the accompanying drawings through specific implementation manners. Similar elements in different implementation manners are labeled with related similar element numbers. In the following implementation manners, many details are described to enable a better understanding of the present invention. However, those skilled in the art can easily recognize that some of the features can be omitted in different situations, or can be replaced by other elements, materials, or methods. In some cases, some operations related to the present invention are not shown or described in the specification to avoid the core part of the present invention being overwhelmed by excessive description. For those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0026] Figure 1 Schematic diagram of an application scenario of a software login method based on big data provided by an embodiment of the present invention. Figure 1 The application scenario of the software login method based on big data may include a server 11, a network 12, a terminal 13, and a storage device 14.

[0027] In some embodiments, the server 11 may be a single server or a server group. The server 11 may access information and / or data stored in the terminal 13 or the storage device 14 through the network 12. In some embodiments, the server 11 may be used to execute Figure 2 the software login method based on big data shown in

[0028] The network 12 can facilitate the exchange of information and / or data. In some embodiments, the network 12 may be any form of wired or wireless network, or any combination thereof.

[0029] The terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, the terminal 13 may include one or more combinations of a mobile device, a tablet computer, a laptop computer, etc.

[0030] The storage device 14 may store data and / or instructions. For example, the storage device 14 may store data instructions of a software login method based on big data.

[0031] In an embodiment of the present invention, there is provided a Figure 2 software login method based on big data as shown in

[0032] Step S1: Obtain a mobile phone screen recording video, multiple logged-in software, and unlogged software.

[0033] The mobile phone screen recording video is a series of consecutive time-point images that record the entire process of operations on the mobile phone screen through a specific software or function. The mobile phone screen recording video includes, but is not limited to, actions such as clicking and swiping and their corresponding interface changes. The mobile phone screen recording video can be used to capture browsing behaviors in an application.

[0034] The information of multiple logged-in software records the relevant data of each logged-in software, such as name, version number, most recent login time, usage frequency, authentication method, etc.

[0035] The unlogged software is software that the user needs to log in to but has not logged in yet.

[0036] Step S2: Use an information processing model based on the mobile phone screen recording video and the information of multiple logged-in software to determine the security credibility and usage frequency of each logged-in software.

[0037] The information processing model is a long short-term neural network model. The input of the information processing model is the mobile phone screen recording video and the information of multiple logged-in software, and the output of the information processing model is the security credibility and usage frequency of each logged-in software.

[0038] The information processing model is obtained by training an existing long short-term neural network model. In some embodiments, the existing long short-term neural network model can be trained by the gradient descent method based on training samples to obtain the information processing model. The sample input of the training samples is the information usage of the mobile phone screen recording video and multiple logged-in software, and the sample output of the training samples is the security credibility and usage frequency of each logged-in software.

[0039] The long short-term neural network model includes a long short-term neural network (LSTM, Long Short-Term Memory). Through the long short-term neural network model, the mobile phone screen recording video of continuous time periods can be processed, the relationships in the time series of the mobile phone screen recording video can be better captured, and features that comprehensively consider the association relationships of the mobile phone screen recording video at each time point can be output, making the output features more accurate and comprehensive.

[0040] The long short-term neural network model can effectively capture the long-term dependence relationships in these sequences, understand the user's interaction patterns, and determine the security credibility and usage frequency of each logged-in software based on the mobile phone screen recording video and the information of multiple logged-in software.

[0041] The mobile phone screen recording video is used to analyze user behavior. The information processing model statistically obtains data such as the number of times each logged-in software is opened and the duration of each use by analyzing the mobile phone screen recording video, thereby directly quantifying the usage frequency of multiple logged-in software. The information processing model can determine the specific interaction steps between the user and the logged-in software through the mobile phone screen recording video, such as operations like entering passwords and performing authentication, and judge whether the logged-in software has good security measures. The information processing model can also further understand the functions and operation types involved in the logged-in software by extracting features such as icons and interface elements from the mobile phone screen recording video, thereby judging the purpose and potential risks of the logged-in software.

[0042] The security credibility of each logged-in software is a measure of the degree of security and reliability of each software during its use. For example, if the logged-in software uses multi-factor authentication and has no abnormal login records, the information processing model determines that the security credibility of the logged-in software is relatively high. Another example is that if the logged-in software only logs in through a password, the information processing model can determine that the security credibility of the logged-in software is relatively low.

[0043] The usage frequency of the logged-in software is the record information of the number of times or the duration of use of the logged-in software by the user within a certain period of time. The information processing model can process the usage frequency of the logged-in software based on the mobile phone screen recording video and the information of multiple logged-in software.

[0044] In some embodiments, the information processing model may include a segmentation layer, a logged-in software information determination layer, and a security credibility determination layer. The input of the segmentation layer is the mobile phone screen recording video and the information of multiple logged-in software. The output of the segmentation layer is the mobile phone screen recording video of each logged-in software and the usage frequency of each logged-in software. The input of the logged-in software information determination layer is the mobile phone screen recording video of each logged-in software. The output of the logged-in software information determination layer is the click degree, swipe degree, sharing degree, and jump degree of each logged-in software. The input of the security credibility determination layer is the click degree, swipe degree, sharing degree, and jump degree of each logged-in software. The output of the security credibility determination layer is the security credibility of each logged-in software.

[0045] Step S3: Determine the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software;

[0046] In some embodiments, Figure 3 FIG. is a schematic flowchart of a method for determining the login method of unlogged software provided by an embodiment of the present invention. The method for determining the login method of unlogged software includes steps S21 to S23:

[0047] Step S21: Based on the unlogged software information, the security credibility and usage frequency of each logged-in software, use a generative adversarial network to generate the estimated security requirement degree, estimated usage frequency of the unlogged software, and the similarity between the unlogged software and each logged-in software;

[0048] The input of the generative adversarial network is the unlogged software information, the security credibility and usage frequency of each logged-in software. The output of the generative adversarial network is the estimated security requirement degree, estimated usage frequency of the unlogged software, and the similarity between the unlogged software and each logged-in software.

[0049] A generative adversarial network (GAN) includes a generator and a discriminator. The generator and the discriminator play against each other and are continuously optimized to achieve the purpose of generating realistic data. Through the training process, the generative adversarial network can learn the feature representation of the data. The generator is responsible for generating the estimated security requirement degree, estimated usage frequency of the unlogged software, and the similarity between the unlogged software and each logged-in software, while the discriminator is used to determine the probability that the data generated by the generator is real data. The generator attempts to generate more realistic data to confuse the discriminator, while the discriminator tries to improve its discrimination ability. The two continuously improve their performance through adversarial training, and finally make the data generated by the generator more in line with the actual situation.

[0050] Based on its powerful data distribution learning ability, the generative adversarial network can learn the distribution law from data such as the security credibility and usage frequency of logged-in software through the adversarial training of the generator and the discriminator, and generate estimated data highly similar to the real data distribution, so as to calculate the similarity between the unlogged software and each logged-in software. The generative adversarial network can also generate the estimated security requirement level and estimated usage frequency of the unlogged software based on the information of the unlogged software and the characteristics of the logged-in software.

[0051] The estimated security requirement level is the security level required for the unlogged software predicted by the generative adversarial network. The higher the estimated security requirement level of the unlogged software, the higher the security verification level required for the unlogged software, and vice versa.

[0052] The estimated usage frequency is the predicted usage frequency of the unlogged software in a future period. For example, the estimated usage frequency can be expressed as the number of times of use per day or per week.

[0053] The similarity between the unlogged software and each logged-in software measures the similarity between the unlogged software and other logged-in software. For example, the more similar the unlogged software and the logged-in software are in function, the higher the similarity generated by the generative adversarial network.

[0054] The information of the unlogged software, the security credibility and usage frequency of each logged-in software provide a key data basis and feature basis for the generative adversarial network, enabling the generative adversarial network to generate high-quality estimated results. The information of the unlogged software includes the basic attributes of the unlogged software such as function category and user group, and the usage frequency reflects the usage habits of users. By learning the distribution law of the information of the unlogged software, the security credibility and usage frequency of each logged-in software, the generative adversarial network can capture the correlation between the logged-in software and the unlogged software, calculate the estimated security requirement level, estimated usage frequency of the unlogged software, and the similarity between the unlogged software and each logged-in software, providing a basis for the selection of the login method.

[0055] Step S22: Construct a graph structure. The graph structure includes multiple nodes and multiple edges between the nodes. The multiple nodes include an unlogged software node and multiple logged-in software nodes. The unlogged software node is the central node. Each unlogged software is respectively connected to the unlogged software node to establish an edge. The node features of the unlogged software node are the estimated security requirement level and estimated usage frequency of the unlogged software. The node features of each logged-in software node include the security credibility and usage frequency of the logged-in software. The edges between the nodes are the similarities between the unlogged software and the logged-in software.

[0056] The graph structure is a data structure representing the relationships between objects. The graph structure consists of nodes (vertices) and edges. In this context, the graph structure is used to represent the relationships between unlogged software and other logged-in software. Each node represents either unlogged software or logged-in software. An edge represents the similarity between unlogged software and logged-in software.

[0057] Step S23, process the graph structure based on the graph autoencoder to determine the login method of the unlogged software.

[0058] The input of the graph autoencoder is the graph structure, and the output of the graph autoencoder is the login method of the unlogged software.

[0059] The login methods of the unlogged software include collaborative verification login of face recognition and SMS verification code, SMS verification code verification, password verification login, and direct login without verification. The graph autoencoder is a neural network model specifically designed to process graph-structured data. The graph autoencoder reconstructs the graph structure by learning the representations of nodes and edges, thereby extracting useful feature information. The graph autoencoder captures the features and relationships by converting the nodes in the graph into low-dimensional embeddings, including the similarity between unlogged software and logged-in software. The graph autoencoder can reconstruct the graph structure and analyze the similarity between nodes, thereby recommending a suitable login method for the unlogged software.

[0060] Each node contains rich feature information, such as security credibility, usage frequency, etc. These features help to evaluate the security requirements of the application. An edge represents the similarity between unlogged software and logged-in software. A high similarity means that the two have common points in terms of function, purpose, permission requests, etc. The graph structure constructs a complex relationship network through nodes and edges. This relationship network enables the graph autoencoder to better understand and evaluate the security requirements of unlogged software and recommend a suitable login method. Based on the features of nodes and edges in the graph structure, the graph autoencoder can provide accurate login method recommendations for unlogged software.

[0061] Step S4, verify the login of the unlogged software based on the login method of the unlogged software.

[0062] When the login method of the unlogged software is determined, obtain the mobile phone number currently used by the user, and then verify the login of the unlogged software based on the login method of the unlogged software using the mobile phone number currently used by the user.

[0063] Based on the same inventive concept, Figure 4 FIG. is a schematic diagram of a software login system based on big data provided by an embodiment of the present invention. The software login system based on big data includes:

[0064] An acquisition module 41, configured to acquire a mobile phone screen recording video, multiple logged-in software, and unlogged-in software;

[0065] An information processing module 42, configured to use an information processing model to determine the security credibility and usage frequency of each logged-in software based on the mobile phone screen recording video and the information of multiple logged-in software;

[0066] A login method confirmation module 43, configured to determine the login method of unlogged-in software based on the security credibility and usage frequency of each logged-in software;

[0067] A login verification module 44, configured to verify the login of the unlogged-in software based on the login method of the unlogged-in software.

[0068] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, as Figure 5 shown, including:

[0069] Including: a processor 51; a memory 52; and a computer program; wherein, the computer program is stored in the memory 52 and is configured to be executed by the processor 51 to implement the big data-based software login method provided above. The method includes: acquiring a mobile phone screen recording video, multiple logged-in software, and unlogged-in software; using an information processing model to determine the security credibility and usage frequency of each logged-in software based on the mobile phone screen recording video and the information of multiple logged-in software; determining the login method of unlogged-in software based on the security credibility and usage frequency of each logged-in software; and verifying the login of the unlogged-in software based on the login method of the unlogged-in software.

[0070] Based on the same inventive concept, this embodiment provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor 51, it implements the big data-based software login method provided above. The method includes: acquiring a mobile phone screen recording video, multiple logged-in software, and unlogged-in software; using an information processing model to determine the security credibility and usage frequency of each logged-in software based on the mobile phone screen recording video and the information of multiple logged-in software; determining the login method of unlogged-in software based on the security credibility and usage frequency of each logged-in software; and verifying the login of the unlogged-in software based on the login method of the unlogged-in software.

[0071] The software login method based on big data provided by the embodiments of the present application can be applied to electronic devices such as terminal devices (such as mobile phones), tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smart watches, smart glasses, or smart helmets, etc.), augmented reality (AR) / virtual reality (VR) devices, smart home devices, in-vehicle computers, etc. The embodiments of the present application do not impose any restrictions on this.

[0072] Taking the mobile phone 100 as an example of the above-mentioned electronic device, Figure 6 shows a schematic structural diagram of the mobile phone 100.

[0073] As Figure 6 shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone interface 170D, a sensor module 180, a key 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0074] The processing module 110 can be used to: obtain the mobile phone screen recording video, multiple logged-in software, and unlogged software; use an information processing model based on the mobile phone screen recording video and the information of multiple logged-in software to determine the security credibility and usage frequency of each logged-in software; determine the login method of the unlogged software based on the security credibility and usage frequency of each logged-in software; and perform verification login on the unlogged software based on the login method of the unlogged software.

[0075] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are proposed in this specification, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0076] In the meantime, this specification uses specific terms to describe the embodiments of this specification. For example, "an embodiment", "one embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0077] In addition, unless clearly stated in the claims, the order of the processing elements and sequences described in this specification, the use of numerical letters, or the use of other names are not used to limit the order of the processes and methods in this specification. Although some currently useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details are only for illustrative purposes. The appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on existing servers or mobile devices.

[0078] Similarly, it should be noted that, in order to simplify the expression of the disclosure in this specification and thus help the understanding of one or more embodiments of the invention, in the foregoing description of the embodiments of this specification, sometimes multiple features are merged into one embodiment, drawing, or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than those mentioned in the claims. In fact, the features of the embodiments are fewer than all the features of the individual embodiments disclosed above.

[0079] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification can be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments clearly introduced and described in this specification.

Claims

1. A software login method based on big data, characterized in that: include: Get mobile phone screen recording videos, multiple logged-in apps, and logged-out apps; Based on the mobile phone screen recording video and the information of the multiple logged-in software, an information processing model is used to determine the security credibility and usage frequency of each logged-in software, wherein the information processing model is a long-term and short-term neural network model, the input of the information processing model is the mobile phone screen recording video and the information of the multiple logged-in software, and the output of the information processing model is the security credibility and usage frequency of each logged-in software; Determining the login method of the non-logged-in software based on the security credibility and usage frequency of each logged-in software, wherein determining the login method of the non-logged-in software based on the security credibility and usage frequency of each logged-in software includes: Based on the unregistered software information, the security credibility and usage frequency of each registered software, a generative adversarial network is used to generate an estimated security requirement degree, an estimated usage frequency and a similarity between the unregistered software and each registered software; Constructing a graph structure, wherein the graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, wherein the plurality of nodes include an unregistered software node and a plurality of registered software nodes, wherein the unregistered software node is a central node, and each of the registered software nodes respectively establishes edges with the unregistered software node, wherein the node features of the unregistered software node are an estimated safety requirement degree and an estimated usage frequency of the unregistered software, and the node features of each of the registered software nodes include a safety credibility and a usage frequency of the registered software, and the edges between the nodes are similarities between the unregistered software and the registered software; Processing the graph structure based on the graph autoencoder to determine a login method for the non-logged-in software; The non-logged-in software is authenticated and logged in based on the login method of the non-logged-in software.

2. The software login method based on big data according to claim 1, characterized in that: The login methods for the non-logged-in software include face recognition and SMS verification code collaborative verification login, SMS verification code verification, password verification login, and direct login without verification.

3. A software login system based on big data, characterized in that: include: The acquisition module is used to obtain the mobile phone screen recording video, multiple logged-in software, and non-logged-in software; An information processing module, used to determine the security credibility and usage frequency of each logged-in software based on the mobile phone screen recording video and the information of multiple logged-in software using an information processing model, wherein the information processing model is a long-short term neural network model, the input of the information processing model is the mobile phone screen recording video and the information of multiple logged-in software, and the output of the information processing model is the security credibility and usage frequency of each logged-in software; A login mode confirmation module is used to determine the login mode of the non-logged-in software based on the security credibility and usage frequency of each logged-in software, and the login mode confirmation module is also used to: Based on the unregistered software information, the security credibility and usage frequency of each registered software, a generative adversarial network is used to generate an estimated security requirement degree, an estimated usage frequency and a similarity between the unregistered software and each registered software; Constructing a graph structure, wherein the graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, wherein the plurality of nodes include an unregistered software node and a plurality of registered software nodes, wherein the unregistered software node is a central node, and each of the registered software nodes respectively establishes edges with the unregistered software node, wherein the node features of the unregistered software node are an estimated safety requirement degree and an estimated usage frequency of the unregistered software, and the node features of each of the registered software nodes include a safety credibility and a usage frequency of the registered software, and the edges between the nodes are similarities between the unregistered software and the registered software; Processing the graph structure based on the graph autoencoder to determine a login method for the non-logged-in software; The login verification module is used to verify the login of the non-logged in software based on the login method of the non-logged in software.

4. The software login system based on big data as claimed in claim 3, characterized in that: The login methods for the non-logged-in software include face recognition and SMS verification code collaborative verification login, SMS verification code verification, password verification login, and direct login without verification.

5. An electronic device, characterized in that: include: processor; Memory; And a computer program; wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the big data-based software login method as described in any one of claims 1 to 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the software login method based on big data as described in any one of claims 1 to 2 is implemented.

Images