Account security assessment method, device and equipment based on neural network

Abstract

The invention provides an account security assessment method, device and equipment based on a neural network. The method comprises the steps of obtaining multiple pieces of account information of a target account and multiple pieces of article information of articles published by the target account in a preset time period; the neural network training is used for determining an account risk index corresponding to the target account by using a neural network according to multiple pieces of account information of the target account, and determining an article issuing risk index corresponding to the target account according to multiple pieces of article information of articles issued by the target account in a preset time period; determining a network position content security index corresponding to the target account according to the account risk index and the document issuing risk index; and generating an evaluation result based on the network position content security index. In the embodiment of the invention, the account information does not need to be analyzed manually, so that the evaluation efficiency is improved; a specific mathematical model and a statistical method do not need to be selected, and universality is achieved; and data processing is performed through the neural network trained security evaluation model, so that the accuracy of the evaluation result is improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a neural network-based account security assessment method, device and equipment. Background Art

[0002] With the rapid development of the Internet, new communication technologies and online platforms such as Weibo, WeChat public accounts and various self-media apps have emerged. On the one hand, these platforms have greatly facilitated people's lives, changed the production methods of traditional industries, and promoted the rapid development and transformation and upgrading of the national economy.

[0003] At present, traditional methods for security assessment of accounts can be divided into two categories: qualitative assessment and quantitative assessment.

[0004] During the qualitative assessment process, experts will conduct an in-depth analysis of the content source, type, dissemination channel, audience characteristics, and potential malicious behavior patterns inherent in the content. The reliability of the content source, the sensitivity of the type, the breadth of the dissemination channel, the diversity of the audience characteristics, and the complexity of the potential malicious behavior patterns are all indispensable factors in the assessment. By comprehensively considering these factors, experts can more accurately grasp the risk points of content security. However, qualitative assessment also has certain limitations. Since it is highly dependent on the subjective judgment and experience of experts, the evaluation results may be affected by factors such as the expert's personal bias and knowledge level. In addition, qualitative assessment is usually difficult to achieve rapid evaluation of a large amount of content, which may become a bottleneck when faced with massive network content. Qualitative assessment methods are highly dependent on the rich practical experience and deep expertise of network security experts. By conducting in-depth analysis of various parameters that affect content security, including content source, type, dissemination channel, audience characteristics, and potential malicious behavior patterns inherent in the content, this method comprehensively identifies potential security risks in the content. In the assessment process, experts use a variety of technologies such as text analysis, semantic understanding, and sentiment detection, combined with a deep understanding of industry trends, policies, and regulations, to conduct subjective assessments of the security of the content. This process ultimately results in a qualitative description and classification of content security risks.

[0005] Quantitative evaluation can avoid subjective interference from human factors and produce more objective and accurate evaluation results through the scientific application of mathematical models and statistical methods. However, quantitative evaluation also has certain limitations. First, the selection and application of mathematical models and statistical methods require certain professional knowledge and skills, which may be difficult for non-professionals. Secondly, quantitative evaluation can usually only deal with risk factors that have been quantified and measurable, and may not be able to effectively evaluate risk factors that are difficult to quantify and measure. In addition, the results of quantitative evaluation may be affected by data quality and sample size. If the data quality is not high or the sample size is insufficient, it may lead to biased or inaccurate evaluation results.

[0006] Therefore, how to provide an account security assessment with accurate assessment results and high assessment efficiency is a technical problem to be solved by those skilled in the art. Summary of the invention

[0007] The main purpose of this application is to provide a neural network-based account security assessment method, device and equipment, aiming to solve the technical problems of inaccurate assessment results and low assessment efficiency of existing account security assessment methods.

[0008] To achieve the above objectives, the present application provides an account security assessment method based on a neural network, the method comprising:

[0009] Obtain multiple account information of the target account and multiple article information of articles published by the target account in a preset time period;

[0010] The security assessment model completed by neural network training determines the account risk index corresponding to the target account according to multiple account information of the target account, and determines the posting risk index corresponding to the target account according to multiple article information of articles published by the target account in a preset time period;

[0011] Determine the network site content security index corresponding to the target account according to the account risk index and the post risk index;

[0012] Based on the network position content security index, an evaluation result is generated.

[0013] Optionally, the security assessment model completed by neural network training determines the account risk index corresponding to the target account according to multiple account information of the target account, including:

[0014] The security assessment model completed through the neural network training obtains the account risk weight and the first risk index corresponding to each account information;

[0015] For each account information, calculating a first product between the account risk weight corresponding to the account information and a preset value;

[0016] determining a difference between the first product and a first risk index corresponding to the account information as a second risk index corresponding to the account information;

[0017] The second risk index corresponding to each account information is summed to obtain the account risk index corresponding to the target account.

[0018] Optionally, the security assessment model completed by neural network training determines the posting risk index corresponding to the target account according to multiple article information of articles published by the target account in a preset time period, including:

[0019] The security assessment model completed through the neural network training obtains the publication risk weight and the third risk index corresponding to each article information;

[0020] For each article information, calculating the second product between the publication risk weight corresponding to the article information and a preset value;

[0021] Determine the difference between the second product and the third risk index corresponding to the article information as the fourth risk index corresponding to the article information;

[0022] The fourth risk index corresponding to each article information is summed to obtain the posting risk index corresponding to the target account.

[0023] Optionally, determining the network site content security index corresponding to the target account according to the account risk index and the posting risk index includes:

[0024] The network content security index corresponding to the target account is determined by the following formula:

[0025] PPSI=ARI+f(T MAX -t)*NARI,t≤T MAX

[0026] Among them, PPSI is the network position content security index, ARI is the account risk index, NARI is the post risk index, MAX It is the time from the posting time to the account popularity dropping to the daily average, and t is the time from the posting time to the current moment.

[0027] Optionally, generating an evaluation result based on the network site content security index includes:

[0028] When the network site content security index is within the first numerical range, it is confirmed that the target account is in a stable period;

[0029] When the network site content security index is within the second numerical range, it is confirmed that the target account is in an abnormal period;

[0030] When the network site content security index is within the third numerical range, it is confirmed that the target account is in the warning period;

[0031] The maximum value included in the first numerical range is smaller than the minimum value included in the second numerical range, and the maximum value included in the second numerical range is smaller than the minimum value included in the third numerical range.

[0032] Optionally, after generating an evaluation result based on the network site content security index, the method further includes:

[0033] In the case where the assessment result indicates that the target account is in a stable period, if the target account is monitored to publish an article, the security assessment model completed by neural network training is used to re-determine the posting risk index corresponding to the target account according to multiple article information of the article;

[0034] The assessment result is regenerated according to the account risk index corresponding to the target account and the re-determined document posting risk index.

[0035] Optionally, after generating an evaluation result based on the network site content security index, the method further includes:

[0036] When the evaluation result indicates that the target account is in a stable period, updating multiple account information of the target account at intervals of a preset time;

[0037] The security assessment model completed through neural network training re-determines the account risk index corresponding to the target account according to the updated multiple account information;

[0038] The assessment result is regenerated according to the posting risk index corresponding to the target account and the re-determined account risk index.

[0039] Optionally, before obtaining multiple account information of the target account and multiple article information of articles published by the target account in a preset time period, the method further includes:

[0040] Get multiple account information and multiple article information of neural network training accounts;

[0041] Classifying the plurality of account information and the plurality of article information to obtain different types of data sets; the data sets include text data sets, numerical data sets, and category data sets;

[0042] Performing word segmentation and vectorization processing on the text data in the text data set to obtain text vectors;

[0043] Determining a risk level of each numerical data in the numerical data set, and generating a risk label based on the risk level of each numerical data;

[0044] Converting the category data in the category data set into a binary vector by using a one-hot encoding technique;

[0045] Inputting neural network training data into a preset security assessment model to perform iterative neural network training on the security assessment model; the neural network training data includes the text vector, the risk label and the binary vector;

[0046] When the loss function corresponding to the security assessment model is lower than a preset threshold, a security assessment model completed by neural network training is obtained.

[0047] In addition, to achieve the above purpose, the present application also provides an account security assessment device, the account security assessment device comprising:

[0048] A first acquisition module is used to acquire multiple account information of a target account and multiple article information of articles published by the target account in a preset time period;

[0049] A first determination module is used to determine the account risk index corresponding to the target account according to multiple account information of the target account through a security assessment model completed by neural network training, and to determine the posting risk index corresponding to the target account according to multiple article information of articles published by the target account in a preset time period;

[0050] A second determination module is used to determine the network position content security index corresponding to the target account according to the account risk index and the post risk index;

[0051] The first generating module is used to generate an evaluation result based on the network position content security index.

[0052] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0053] The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the account security assessment methods proposed in the embodiments of the present application are implemented.

[0054] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0055] The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the account security assessment method described in any one of the embodiments of the present application are implemented.

[0056] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0057] The present application provides a method, device and equipment for account security assessment based on neural network, the method comprising: obtaining multiple account information of a target account, and multiple article information of articles published by the target account in a preset time period; determining the account risk index corresponding to the target account according to the multiple account information of the target account through the security assessment model completed by neural network training, and determining the posting risk index corresponding to the target account according to the multiple article information of the articles published by the target account in the preset time period; determining the network position content security index corresponding to the target account according to the account risk index and the posting risk index; generating an assessment result based on the network position content security index. In the embodiment of the present application, the security assessment model completed by neural network training is based on determining the account risk index according to the account information, and determining the posting risk index according to the article information, and then determining the network position content security index based on the above account risk index and posting risk index, and generating an assessment result based on the network position content security index. In the account security assessment method provided in the embodiment of the present application, there is no need to manually analyze the account information, thereby improving the assessment efficiency; there is no need to select a specific mathematical model and statistical method, and it has universality; and the security assessment model completed by neural network training performs data processing, which improves the accuracy of the assessment result. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0060] Figure 2 is a flowchart of a neural network-based account security assessment method provided in an embodiment of the present application;

[0061] Figure 3 is an application flow chart of the account security assessment method provided in the embodiment of the present application;

[0062] Figure 4is a schematic diagram of a multi-layer fusion model provided in an embodiment of the present application;

[0063] Figure 5 It is a loss graph based on a single-layer linear regression model on a training set and a test set provided in an embodiment of the present application;

[0064] Figure 6 It is a loss graph on a training set and a test set based on a multi-layer fusion model provided in an embodiment of the present application;

[0065] Figure 7 It is a structural diagram of an embodiment of an account security assessment device provided in an embodiment of the present application;

[0066] Figure 8 It is a basic structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] The neural network-based account security assessment method provided in the embodiment of the present application is applied to the account security assessment device. Unless otherwise defined, all technical and scientific terms used in this article have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned figures are used to distinguish different objects, not to describe a specific order.

[0068] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0069] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0070] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0071] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social online platform software, etc.

[0072] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV), laptop computers, desktop computers, etc.

[0073] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0074] It should be noted that the account security assessment method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the account security assessment device is generally set in the server / terminal device.

[0075] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0076] Please refer to Figure 2 , showing a flowchart of an embodiment of a neural network-based account security assessment method proposed in this application.

[0077] The neural network-based account security assessment method provided in the embodiment of the present application includes the following steps:

[0078] S210, obtaining multiple account information of a target account and multiple article information of articles published by the target account in a preset time period.

[0079] It should be noted that the above account information together constitutes a multi-dimensional and multi-level assessment framework, which can more accurately capture and quantify the risk characteristics of accounts in different aspects, thereby providing strong technical support and decision-making basis for account risk management. Optionally, the account risk index includes primary indicators and secondary indicators, and the above account information includes secondary indicators. Please refer to Table 1:

[0080] Table 1:

[0081]

[0082] It should be noted that the publication risk index is a risk index for specific articles published in a specific account on a certain network. The purpose of constructing the publication risk index is to comprehensively consider the basic information, sensitive elements and article dissemination rate of newly published articles, so as to comprehensively reflect the basic situation of the article, the risk level of sensitive information and its dissemination effect on the network.

[0083] Optionally, when an article is published, its risk index will be dynamically calculated based on the given indicator formula. However, in order to manage risks more reasonably, this project sets a specific time window: if the total risk index of the account does not reach the medium-high risk level within 72 hours after the article is published, it can be considered that no new articles are generated during this period, and the risk index of the article will be temporarily reset to zero. This setting helps to reduce the excessive impact of the accumulated risks of historical articles on the current status of the account, so that risk management can focus more on the latest dynamics of the account. However, it is worth noting that if the publication of an article causes the total risk index of the account to reach the medium-high risk level, even if the 72-hour time window is exceeded, the article will still be continuously monitored. In this case, if the account needs to exit the warning period and return to normal status, it needs to use the sensitive event index for comprehensive evaluation. Sensitive elements are the core content of assessing article risks, which are directly related to the compliance and health of the article content.

[0084] Optionally, the publication risk index includes primary indicators and secondary indicators, and the above article information includes secondary indicators. Please refer to Table 2:

[0085] Table 2:

[0086]

[0087] Among them, the basic information mainly includes three secondary indicators: title name, content form and sentiment field:

[0088] (1) Title: The title is the face of the article and the first factor that attracts readers to click. However, titles that are overly exaggerated, contain sensitive words, or are misleading are likely to cause dissatisfaction among readers and even cause adverse effects. Therefore, when assessing article risks, the title is given a negative weight to warn authors to pay attention to the compliance and accuracy of the title.

[0089] (2) Content form: Content form refers to the specific way in which an article is presented to users, including text, pictures, videos, etc. Different content forms have different appeal and influence on users.

[0090] (3) Emotional field: Emotion is an important dimension of information transmission in articles, which directly affects readers’ reading experience and emotional resonance.

[0091] The above content defines the account information and article information of the account.

[0092] In this step, multiple account information of the target account and multiple article information of the target account published in a preset time period are obtained. Optionally, the preset time period is 72 hours.

[0093] S220, a security assessment model completed through neural network training determines the account risk index corresponding to the target account based on multiple account information of the target account, and determines the article risk index corresponding to the target account based on multiple article information of articles published by the target account in a preset time period.

[0094] It should be noted that the security assessment model can be divided into four levels, as follows:

[0095] (1) Target layer:

[0096] This layer is the highest layer of the entire assessment model, and its core goal is to directly output the risk value of the network position account. This risk value is a quantitative reflection of the comprehensive risk assessment of the network position account. By comprehensively considering multiple dimensions and characteristics of the account, it concisely and clearly reflects the security status of the account. This layer uses machine learning algorithms, such as neural networks or linear regression models, to fuse and calculate the data of the lower layers, and finally obtain the risk value of the account.

[0097] (2) Strategy layer:

[0098] At the strategic level, we comprehensively consider various indicators of network accounts from multiple strategic perspectives. These mainly include various indicators of the account itself, indicators of the content of published articles, records of historical warning libraries, and the correlation between current sensitive events and account behavior. These four dimensions together constitute the evaluation framework of the strategic level, providing direction for subsequent detailed analysis.

[0099] (3) First-level indicator layer:

[0100] Going deep into the first-level indicator layer of the network position content security index, this layer covers multiple key indicators, including login device information, historical situation, account propagation rate, basic attributes, sensitive element analysis, article popularity and text description. Login device information reflects the usage environment and security of the account; historical situation reveals the account's past behavior patterns and possible risk points; account propagation rate shows the dissemination ability and influence of the account content; basic attributes cover the basic information and settings of the account; sensitive element analysis is used to identify possible risk elements in the account content; article popularity reflects the popularity and social influence of the account's published content; text description is a detailed text analysis of the account's published content. These first-level indicators together constitute a comprehensive and in-depth assessment of the account, providing a basis for the refinement of the second-level indicators.

[0101] (4) Secondary indicator layer:

[0102] The account-level risk index determines the security level of each account under different indicators. Furthermore, the risk index of the articles published by the account will further determine the internal security level of each account. In order to effectively assess the risk level of articles, the system covers three primary indicators: basic information, article popularity, and sensitive elements, and is subdivided into multiple secondary indicators to achieve accurate quantification of article risks.

[0103] In this step, the security assessment model completed through neural network training is used to process data of multiple account information to obtain the account risk index corresponding to the target account. The above account risk index is used to characterize the account risk of the target account.

[0104] In this step, the security assessment model completed through neural network training processes data on multiple article information published by the target account in a preset time period to obtain the article risk index corresponding to the target account. The above article risk index is used to characterize the risk of articles published by the target account.

[0105] Among them, the above-mentioned account risk index is also called the ARI (Account Risk Index) index, the above-mentioned article risk index is also called the NARI (New Article Risk Index) index, and the above-mentioned security assessment model is obtained by neural network training.

[0106] S230, determining the network site content security index corresponding to the target account according to the account risk index and the post risk index.

[0107] In this step, after obtaining the account risk index and the post risk index, the network position content security index corresponding to the target account can be determined based on the above account risk index and the post risk index. For the specific implementation method, please refer to the subsequent embodiments.

[0108] Among them, the above-mentioned network position content security index is also called the PPSI (Positions and Platform Safety Index) index.

[0109] S240, generating an evaluation result based on the network site content security index.

[0110] In this step, after obtaining the network site content security index, an evaluation result can be generated based on the numerical range of the network site content security index.

[0111] Optionally, the above evaluation results include three results: the target account is in a stable period, the target account is in an abnormal period, and the target account is in a warning period.

[0112] (1) Stable period: This stage is considered a low-risk period. During this period, the account's activities are stable and compliant, and no special attention or additional risk management measures are required. Under normal circumstances, the account is in this stage by default and enjoys a relatively relaxed management environment.

[0113] (2) Abnormal period: This indicates that the account has entered a medium-risk period. During this period, the account behavior shows certain abnormalities and is suspected to have potential risks. Therefore, it is recommended to conduct further manual research and analysis on such accounts, combined with machine learning technology, to conduct in-depth analysis of the accounts in order to more accurately identify and respond to possible problems.

[0114] (3) Warning period: The account is considered to be at high risk during this stage. During this critical stage, emergency measures must be taken to prevent potential adverse effects.

[0115] The present application provides an account security assessment method, which includes: obtaining multiple account information of a target account, and multiple article information of articles published by the target account in a preset time period; determining the account risk index corresponding to the target account according to the multiple account information of the target account through a security assessment model completed by neural network training, and determining the posting risk index corresponding to the target account according to the multiple article information of the articles published by the target account in a preset time period; determining the network position content security index corresponding to the target account according to the account risk index and the posting risk index; generating an assessment result based on the network position content security index. In the embodiment of the present application, the security assessment model completed by neural network training is based on determining the account risk index according to the account information, and determining the posting risk index according to the article information, and then determining the network position content security index based on the above account risk index and posting risk index, and generating an assessment result based on the network position content security index. In the account security assessment method provided in the embodiment of the present application, there is no need to manually analyze the account information, thereby improving the assessment efficiency; there is no need to select a specific mathematical model and statistical method, and it has universality; and the security assessment model completed by neural network training performs data processing, which improves the accuracy of the assessment result.

[0116] Optionally, the security assessment model completed by neural network training determines the account risk index corresponding to the target account according to multiple account information of the target account, including:

[0117] The security assessment model completed through the neural network training obtains the account risk weight and the first risk index corresponding to each account information;

[0118] For each account information, calculating a first product between the account risk weight corresponding to the account information and a preset value;

[0119] determining a difference between the first product and a first risk index corresponding to the account information as a second risk index corresponding to the account information;

[0120] The second risk index corresponding to each account information is summed to obtain the account risk index corresponding to the target account.

[0121] Optionally, the second risk index corresponding to the account information may be calculated by the following formula:

[0122] x' k =ω k *z-score(x k )

[0123] Among them, x′ k represents the second risk index, x k represents the first risk index, ωk represents the account risk weight, and z represents the preset value.

[0124] Optionally, the account risk index corresponding to the target account can be calculated using the following formula:

[0125]

[0126] Among them, ARI represents the account risk index, x′ k represents the second risk index, and k represents the number of account information.

[0127] In this embodiment, the account risk index corresponding to the target account is determined according to the risk situation of each account information, so that the account risk index can accurately reflect the risk of the target account itself.

[0128] Optionally, the security assessment model completed by neural network training determines the posting risk index corresponding to the target account according to multiple article information of articles published by the target account in a preset time period, including:

[0129] The security assessment model completed through the neural network training obtains the publication risk weight and the third risk index corresponding to each article information;

[0130] For each article information, calculating the second product between the publication risk weight corresponding to the article information and a preset value;

[0131] Determine the difference between the second product and the third risk index corresponding to the article information as the fourth risk index corresponding to the article information;

[0132] The fourth risk index corresponding to each article information is summed to obtain the posting risk index corresponding to the target account.

[0133] Optionally, the fourth risk index corresponding to the article information may be calculated by the following formula:

[0134] y' m =ω' m *z-score(y m )

[0135] Among them, y′ m represents the fourth risk index, y m represents the third risk index, ω m ′ represents the account risk weight, and z represents the preset value.

[0136] Optionally, the post risk index corresponding to the target account can be calculated using the following formula:

[0137]

[0138] Among them, NARI represents the publication risk index, y′ m represents the fourth risk index, and m represents the number of article information.

[0139] In this embodiment, according to the risk situation of the articles published by the target account, the article publishing risk index corresponding to the target account is determined, so that the above-mentioned article publishing risk index can accurately reflect the risk of the articles published by the target account.

[0140] Optionally, determining the network site content security index corresponding to the target account according to the account risk index and the posting risk index includes:

[0141] The network content security index corresponding to the target account is determined by the following formula:

[0142] PPSI=ARI+f(T MAX -t)*NARI,t≤T MAX

[0143] Among them, PPSI is the network position content security index, ARI is the account risk index, NARI is the post risk index, MAX It is the time from the posting time to the account popularity dropping to the daily average, and t is the time from the posting time to the current moment.

[0144] In this embodiment, the above-mentioned account risk index can accurately reflect the risks of the target account itself, and the above-mentioned article risk index can accurately reflect the risks of the articles published by the target account. Therefore, the network position content security index determined based on the account risk index and the article risk index can accurately characterize the risks of the target account.

[0145] Optionally, generating an evaluation result based on the network site content security index includes:

[0146] When the network site content security index is within the first numerical range, it is confirmed that the target account is in a stable period;

[0147] When the network site content security index is within the second numerical range, it is confirmed that the target account is in an abnormal period;

[0148] When the network site content security index is within the third numerical range, it is confirmed that the target account is in the warning period;

[0149] The maximum value included in the first numerical range is smaller than the minimum value included in the second numerical range, and the maximum value included in the second numerical range is smaller than the minimum value included in the third numerical range.

[0150] In this embodiment, a first numerical range, a second numerical range and a third numerical range are pre-set, wherein the maximum value included in the first numerical range is smaller than the minimum value included in the second numerical range, and the maximum value included in the second numerical range is smaller than the minimum value included in the third numerical range.

[0151] When the network content security index is in the first numerical range, it means that the account's activities are stable and compliant, and there is no need for special attention or additional risk management measures. In this case, the target account is determined to be in a stable period.

[0152] When the network content security index is in the second numerical range, it means that the account behavior shows certain abnormalities and there is suspected potential risk, then it is determined that the target account is in an abnormal period.

[0153] When the network content security index is in the third numerical range, it means that the account is considered to be in a high-risk period at this stage, and the target account is determined to be in the warning period.

[0154] Optionally, after generating an evaluation result based on the network site content security index, the method further includes:

[0155] In the case where the assessment result indicates that the target account is in a stable period, if the target account is monitored to publish an article, the security assessment model completed by neural network training is used to re-determine the posting risk index corresponding to the target account according to multiple article information of the article;

[0156] The assessment result is regenerated according to the account risk index corresponding to the target account and the re-determined document posting risk index.

[0157] In this embodiment, when the target account is in a stable period, the target account is monitored in real time. If the target account is monitored to publish an article, the security assessment model completed through neural network training is used to re-determine the posting risk index corresponding to the target account based on multiple article information of the article.

[0158] Furthermore, the assessment result is regenerated according to the account risk index corresponding to the target account and the re-determined posting risk index. For the specific implementation method, please refer to the above embodiment.

[0159] Optionally, after generating an evaluation result based on the network site content security index, the method further includes:

[0160] When the evaluation result indicates that the target account is in a stable period, updating multiple account information of the target account at intervals of a preset time;

[0161] The security assessment model completed through neural network training re-determines the account risk index corresponding to the target account according to the updated multiple account information;

[0162] The assessment result is regenerated according to the posting risk index corresponding to the target account and the re-determined account risk index.

[0163] In this embodiment, when the target account is in a stable period, multiple account information of the target account is updated at intervals of a preset length, and the security assessment model completed by neural network training re-determines the account risk index corresponding to the target account based on the updated multiple account information. Then, the assessment result is regenerated based on the posting risk index corresponding to the target account and the re-determined account risk index. The specific implementation method can refer to the above embodiment.

[0164] For the purpose of explaining the above embodiments, please refer to Figure 3 ,exist Figure 3 In the example shown, during the stable period of the target account, if the target account has not posted anything, the account information of the target account is updated at preset intervals, and the account risk index is recalculated. Based on the account risk index, it is determined whether the target account is at risk. If there is no risk, it is determined that the target account is in a stable period; if there is a risk, it is determined that the target account is in an abnormal period, and the account risk of the target account is evaluated again at preset intervals.

[0165] During the stable period of the target account, if the target account is monitored to post an article, the article risk index of the newly published article of the target account is calculated, and based on the above article risk index and the account risk index of the target account, it is judged whether the target account has risks. If not, it is determined that the target account is in a stable period; if so, it is determined that the target account is in a warning period.

[0166] When the target account is in the early warning period, if a sensitive event occurs, the sensitive event index of the sensitive event is determined, and the status of the target account is determined based on the sensitive event index.

[0167] Among them, the above-mentioned sensitive events are secondary indicators included in the above-mentioned document risk index.

[0168] Optionally, different sensitive events may correspond to different sensitive event indexes.

[0169] Optionally, before obtaining multiple account information of the target account and multiple article information of articles published by the target account in a preset time period, the method further includes:

[0170] Get multiple account information and multiple article information of neural network training accounts;

[0171] Classifying the plurality of account information and the plurality of article information to obtain different types of data sets; the data sets include text data sets, numerical data sets, and category data sets;

[0172] Performing word segmentation and vectorization processing on the text data in the text data set to obtain text vectors;

[0173] Determining a risk level of each numerical data in the numerical data set, and generating a risk label based on the risk level of each numerical data;

[0174] Converting the category data in the category data set into a binary vector by using a one-hot encoding technique;

[0175] Inputting neural network training data into a preset security assessment model to perform iterative neural network training on the security assessment model; the neural network training data includes the text vector, the risk label and the binary vector;

[0176] When the loss function corresponding to the security assessment model is lower than a preset threshold, a security assessment model completed by neural network training is obtained.

[0177] In this embodiment, multiple account information and multiple article information of the neural network training account are obtained, and the multiple account information and multiple article information are classified to obtain different types of data sets. Optionally, the above data sets include text data sets, numerical data sets, and category data sets. Corresponding data preprocessing is performed on the above different types of data, specifically:

[0178] (1) Text data: In the preprocessing stage of text data processing, the data is cleaned by removing irrelevant characters and segmented for subsequent text analysis and model training. Specifically, the jieba tool based on the dynamic programming algorithm is used for Chinese word segmentation, which can effectively segment the title text into meaningful vocabulary units. In order to maintain data consistency, the maximum number of words for each title is set to 10. For titles with less than 10 words, the zero padding method is used to ensure that each title has the same dimension in subsequent processing. After completing the word segmentation, each word is further vectorized using Tencent's Word2Vec database. Word2Vec is an advanced word embedding technology that can map words to vector representations in a high-dimensional space, thereby capturing the semantic relationship between words. Optionally, each word is projected into a 100-dimensional vector. Therefore, each title consisting of 10 words is finally represented as a 1000-dimensional vector. This vector representation not only retains the semantic information of the words, but also facilitates subsequent text analysis and model neural network training.

[0179] (2) Numerical data: Numerical data is a decisive factor in content security. In terms of risk assessment of data labels, it is mainly based on the total number of rejections. Specifically, when the total number of rejections of a certain content is greater than 0, it is assigned a risk label of 1, indicating that the content is risky. On the contrary, when the total number of rejections is 0, the risk label is 0, indicating that the content is highly secure and does not present obvious risks. This risk assessment mechanism helps to quickly and accurately identify potential risk content during content review and management, so that appropriate measures can be taken to ensure the security of platform content. In addition, a certain threshold is set for the total number of suspected cases. When the total number of suspected cases exceeds this specific threshold, the risk warning mechanism is also triggered to further review and deal with the potential risk content.

[0180] (3) Categorical data: In the categorical data processing stage, a one-hot encoding technique is used to convert the categorical data into a numerical form. One-hot encoding is a common method for processing categorical data. It converts each categorical variable into a binary vector. In this vector, the position representing the current category is set to 1, while all other positions are set to 0. This method effectively processes non-numerical categorical data and converts it into a numerical form that the model can understand. After completing the numerical conversion of the data, all the data are further standardized using the Z-Score standardization method. Z-Score standardization is a commonly used data preprocessing technique that converts the data into a standard distribution form with a mean of 0 and a standard deviation of 1 by subtracting the mean and dividing by the standard deviation. This step is crucial to eliminating the differences between data dimensions, improving the convergence speed of the model, and enhancing the generalization ability of the model.

[0181] Furthermore, the neural network training data is input into a preset security assessment model, and the security assessment model is iteratively trained.

[0182] It should be understood that the security assessment model includes a single-layer linear regression model, that is, the security assessment model is constructed based on the single-layer linear regression model.

[0183] First, a single-layer linear regression model in a neural network is used to estimate the weight factors of different influencing factors, which can be expressed as:

[0184] Y=Wx+b,

[0185] Where W represents the weight matrix of the impact of different factors on content security. bis the bias coefficient, x is the model input data, and Y represents the output category probability. In this model, the back propagation algorithm is used as the parameter optimization method. The back propagation algorithm is an efficient gradient descent technique that minimizes the loss function and optimizes the model by calculating the gradient of the loss function for each parameter and updating the parameter value in the opposite direction of the gradient.

[0186] In this model, the input data x covers preprocessed text data, numerical data, and category data, which together constitute the feature set of the model. The output variable Y is determined based on the total number of rejections in the numerical data. Specifically, when the total number of rejections is greater than 0, the risk is marked as 1, indicating that there is a risk; and when the total number of rejections is 0, we mark the risk as 0, indicating that there is no risk. This processing method enables the model to predict the corresponding account risk status based on the input feature data, providing strong support for subsequent platform risk management and decision-making. After optimization through the back propagation algorithm, a weight matrix is ​​obtained, in which each element represents the importance of the corresponding content security influencing parameter. This result not only reveals the degree of influence of different factors on the target variable, but also provides a quantitative basis for the subsequent formulation of content security in different network positions. In addition, the optimization process also involves iterative calculation of the loss function and fine-tuning of the model parameters based on the gradient information to ensure the accuracy and stability of the model prediction.

[0187] It should be understood that the safety assessment model includes a multi-layer linear regression model, that is, the safety assessment model is constructed based on the multi-layer linear regression model.

[0188] The multi-layer linear regression model includes 7 front fully connected layers, which correspond to the article title, subject unit, content type, usage frequency, location (domestic / foreign), whether there is a content review mechanism, and other potential influencing factors in the multidimensional influencing factors. The core function of this model is that it can effectively reduce the multidimensional vector features to one-dimensional space, and then calculate the weights through a unified fully connected layer. The weights derived by the model can be uniquely mapped to each feature in the multidimensional influencing factors, which greatly enhances the interpretability of the model. This feature makes the model more practical in practical applications, such as Figure 4 As shown, it clearly shows how the model effectively maps multi-dimensional features into a one-dimensional weight space, improving the interpretability and practicality of the model.

[0189] In addition, in the design of the fully connected layer of the multi-layer linear regression model, the ReLU activation function is used to enhance the nonlinear expression ability of the model, and the Dropout technology is used to reduce the risk of overfitting and ensure the generalization ability of the model on complex data sets. In addition, in order to further improve the stability and convergence of the model during the neural network training process, a batch normalization layer is added after each fully connected layer, which helps to normalize the input distribution and reduce internal covariate shift.

[0190] Furthermore, when the loss function corresponding to the security assessment model is lower than a preset threshold, a security assessment model completed by neural network training is obtained.

[0191] To demonstrate the accuracy of the security assessment model output, please refer to Figure 5 and Figure 6 180,000 data points were randomly selected from the complete dataset as the neural network training set and validated on an independent test dataset. The validation results of the single-layer linear regression model are shown in Figure 5 As shown in the figure, during the neural network training process, as the sample size increases, the losses on the neural network training set and test set gradually decrease, indicating that the accuracy of the security assessment model has been improved.

[0192] The validation results of the multi-layer linear regression model are as follows: Figure 6 As shown in the figure, the optimization algorithm and regularization technique are used to effectively ensure the generalization ability of the multi-layer linear regression model.

[0193] See also Figure 7 , an account security assessment device 700 provided in an embodiment of the present application, the account security assessment device 700 includes:

[0194] The first acquisition module 710 is used to acquire multiple account information of a target account and multiple article information of articles published by the target account in a preset time period;

[0195] The first determination module 720 is used to determine the account risk index corresponding to the target account according to the multiple account information of the target account through the security assessment model completed by neural network training, and determine the posting risk index corresponding to the target account according to the multiple article information of the articles published by the target account in a preset time period;

[0196] A second determination module 730 is used to determine the network site content security index corresponding to the target account according to the account risk index and the post risk index;

[0197] The first generating module 740 is used to generate an evaluation result based on the network position content security index.

[0198] Optionally, the first determining module 720 is specifically configured to:

[0199] The security assessment model completed through the neural network training obtains the account risk weight and the first risk index corresponding to each account information;

[0200] For each account information, calculating a first product between the account risk weight corresponding to the account information and a preset value;

[0201] determining a difference between the first product and a first risk index corresponding to the account information as a second risk index corresponding to the account information;

[0202] The second risk index corresponding to each account information is summed to obtain the account risk index corresponding to the target account.

[0203] Optionally, the first determining module 720 is further specifically configured to:

[0204] The security assessment model completed through the neural network training obtains the publication risk weight and the third risk index corresponding to each article information;

[0205] For each article information, calculating the second product between the publication risk weight corresponding to the article information and a preset value;

[0206] Determine the difference between the second product and the third risk index corresponding to the article information as the fourth risk index corresponding to the article information;

[0207] The fourth risk index corresponding to each article information is summed to obtain the posting risk index corresponding to the target account.

[0208] Optionally, the second determining module 730 is specifically configured to:

[0209] The network content security index corresponding to the target account is determined by the following formula:

[0210] PPSI=ARI+f(T MAX -t)*NARI,t≤T MAX

[0211] Among them, PPSI is the network position content security index, ARI is the account risk index, NARI is the post risk index, MAX It is the time from the posting time to the account popularity dropping to the daily average, and t is the time from the posting time to the current moment.

[0212] Optionally, the first generating module 740 is specifically configured to:

[0213] When the network site content security index is within the first numerical range, it is confirmed that the target account is in a stable period;

[0214] When the network site content security index is within the second numerical range, it is confirmed that the target account is in an abnormal period;

[0215] When the network site content security index is within the third numerical range, it is confirmed that the target account is in the warning period;

[0216] The maximum value included in the first numerical range is smaller than the minimum value included in the second numerical range, and the maximum value included in the second numerical range is smaller than the minimum value included in the third numerical range.

[0217] Optionally, the account security assessment device 700 further includes:

[0218] A third determination module is used for, when the evaluation result indicates that the target account is in a stable period, if the target account is monitored to publish an article, re-determining the publication risk index corresponding to the target account according to multiple article information of the article through the security assessment model completed by neural network training;

[0219] The second generating module is used to regenerate the evaluation result according to the account risk index corresponding to the target account and the re-determined document risk index.

[0220] Optionally, the account security assessment device 700 further includes:

[0221] An updating module, configured to update the multiple account information of the target account at intervals of a preset time length when the evaluation result indicates that the target account is in a stable period;

[0222] A fourth determination module is used to re-determine the account risk index corresponding to the target account according to the updated multiple account information through the security assessment model completed by neural network training;

[0223] The third generating module is used to regenerate the evaluation result according to the posting risk index corresponding to the target account and the re-determined account risk index.

[0224] Optionally, the account security assessment device 700 further includes:

[0225] A second acquisition module is used to obtain multiple account information and multiple article information of a neural network training account;

[0226] A classification module, used to classify the plurality of account information and the plurality of article information to obtain different types of data sets; the data sets include text data sets, numerical data sets and category data sets;

[0227] A processing module, used for performing word segmentation and vectorization processing on the text data in the text data set to obtain a text vector;

[0228] a fifth determination module, configured to determine a risk level of each numerical data in the numerical data set, and generate a risk label based on the risk level of each numerical data;

[0229] A conversion module, used for converting the category data in the category data set into a binary vector by using a one-hot encoding technique;

[0230] A neural network training module, used for inputting neural network training data into a preset security assessment model to perform iterative neural network training on the security assessment model; the neural network training data includes the text vector, the risk label and the binary vector;

[0231] The sixth determination module is used to obtain a security assessment model completed by neural network training when the loss function corresponding to the security assessment model is lower than a preset threshold.

[0232] To solve the above technical problems, the present application also provides a computer device. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0233] The computer device 8 includes a memory 81, a processor 82, and a network interface 83 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 8 with components 81-83, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0234] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0235] The memory 81 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 81 can be an internal storage unit of the computer device 8, such as a hard disk or memory of the computer device 8. In other embodiments, the memory 81 can also be an external storage device of the computer device 8, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 8. Of course, the memory 81 can also include both the internal storage unit of the computer device 8 and its external storage device. In this embodiment, the memory 81 is generally used to store the operating system and various application software installed on the computer device 8, such as the program code of the account security assessment method, etc. In addition, the memory 81 can also be used to temporarily store various types of data that have been output or are to be output.

[0236] The processor 82 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 82 is generally used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is used to run the program code stored in the memory 81 or process data, such as running the program code of the account security assessment method.

[0237] The network interface 83 may include a wireless network interface or a wired network interface. The network interface 83 is generally used to establish a communication connection between the computer device 8 and other electronic devices.

[0238] The present application also provides another implementation, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores the account security assessment program, and the account security assessment program can be executed by at least one processor so that the at least one processor performs the steps of the account security assessment method as described above.

[0239] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware online platform, and of course, by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0240] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0241] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A neural network-based account security assessment method, characterized in that: include: Obtain multiple account information of the target account and multiple article information of articles published by the target account in a preset time period; The security assessment model completed through neural network training determines the account risk index corresponding to the target account according to multiple account information of the target account, and determines the posting risk index corresponding to the target account according to multiple article information of articles published by the target account in a preset time period; Determine the network site content security index corresponding to the target account according to the account risk index and the post risk index; Based on the network position content security index, an evaluation result is generated.

2. The method according to claim 1, characterized in that The security assessment model completed by the neural network training determines the account risk index corresponding to the target account according to the multiple account information of the target account, including: The security assessment model completed through the neural network training obtains the account risk weight and the first risk index corresponding to each account information; For each account information, calculating a first product between the account risk weight corresponding to the account information and a preset value; determining a difference between the first product and a first risk index corresponding to the account information as a second risk index corresponding to the account information; The second risk index corresponding to each account information is summed to obtain the account risk index corresponding to the target account.

3. The method according to claim 1, characterized in that The security assessment model completed through neural network training determines the posting risk index corresponding to the target account according to multiple article information of the articles published by the target account in a preset time period, including: The security assessment model completed through the neural network training obtains the publication risk weight and the third risk index corresponding to each article information; For each piece of article information, calculating a second product between the publication risk weight corresponding to the article information and a preset value; Determine the difference between the second product and the third risk index corresponding to the article information as the fourth risk index corresponding to the article information; The fourth risk index corresponding to each article information is summed to obtain the posting risk index corresponding to the target account.

4. The method according to claim 1, characterized in that: Determining the network site content security index corresponding to the target account according to the account risk index and the post risk index includes: The network content security index corresponding to the target account is determined by the following formula: PPSI=ARI+f(T MAX -t)*NARI,t≤T MAX Among them, PPSI is the network content security index, ARI is the account risk index, and NARI is the post risk index. TMAX It is the time from the posting time to the account popularity dropping to the daily average, and t is the time from the posting time to the current moment.

5. The method according to claim 1, characterized in that The generating of the evaluation result based on the network position content security index includes: When the network site content security index is within the first numerical range, it is confirmed that the target account is in a stable period; When the network site content security index is within the second numerical range, it is confirmed that the target account is in an abnormal period; When the network site content security index is within the third numerical range, it is confirmed that the target account is in the warning period; The maximum value included in the first numerical range is smaller than the minimum value included in the second numerical range, and the maximum value included in the second numerical range is smaller than the minimum value included in the third numerical range.

6. The method according to claim 1, characterized in that After generating the evaluation result based on the network site content security index, the method further includes: In the case where the assessment result indicates that the target account is in a stable period, if the target account is monitored to publish an article, the security assessment model completed by neural network training is used to re-determine the posting risk index corresponding to the target account according to multiple article information of the article; The assessment result is regenerated according to the account risk index corresponding to the target account and the re-determined document posting risk index.

7. The method according to claim 1, characterized in that After generating the evaluation result based on the network site content security index, the method further includes: When the evaluation result indicates that the target account is in a stable period, updating multiple account information of the target account at intervals of a preset time; The security assessment model completed through neural network training re-determines the account risk index corresponding to the target account according to the updated multiple account information; The assessment result is regenerated according to the posting risk index corresponding to the target account and the re-determined account risk index.

8. The method according to claim 1, characterized in that Before obtaining the multiple account information of the target account and the multiple article information of the articles published by the target account in the preset time period, the method further includes: Get multiple account information and multiple article information of neural network training accounts; Classifying the plurality of account information and the plurality of article information to obtain different types of data sets; the data sets include text data sets, numerical data sets, and category data sets; Performing word segmentation and vectorization processing on the text data in the text data set to obtain text vectors; Determining a risk level of each numerical data in the numerical data set, and generating a risk label based on the risk level of each numerical data; Converting the category data in the category data set into a binary vector by using a one-hot encoding technique; Inputting neural network training data into a preset security assessment model to perform iterative neural network training on the security assessment model; the neural network training data includes the text vector, the risk label and the binary vector; When the loss function corresponding to the security assessment model is lower than a preset threshold, a security assessment model completed by neural network training is obtained.

9. An account security assessment device, characterized in that: include: A first acquisition module is used to acquire multiple account information of a target account and multiple article information of articles published by the target account in a preset time period; A first determination module is used to determine the account risk index corresponding to the target account according to multiple account information of the target account through a security assessment model completed by neural network training, and to determine the posting risk index corresponding to the target account according to multiple article information of articles published by the target account in a preset time period; A second determination module is used to determine the network position content security index corresponding to the target account according to the account risk index and the post risk index; The first generating module is used to generate an evaluation result based on the network position content security index.

10. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the account security assessment method according to any one of claims 1 to 8 are implemented.

Images