Malicious account detection method, device, equipment and medium

By constructing feature association tables and graph networks, and using clustering algorithms to identify malicious accounts, the problem of low accuracy in black industry accounts recognition in the existing technology is solved, and the accuracy of malicious account recognition is improved.

CN114510695BActive Publication Date: 2024-12-06CHINA PING AN LIFE INSURANCE CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202210141552.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-02-16
Publication Date
2024-12-06
Estimated Expiration
2042-02-16

AI Technical Summary

Technical Problem

The existing black industry account identification methods are not very accurate and it is difficult to effectively identify malicious accounts.

Method used

By obtaining the user ID and basic feature parameters of the registered users of the target application software, a feature association table is constructed, the feature similarity between users is calculated, the graph network is constructed based on the similarity and cut, and a clustering algorithm is used to find malicious accounts.

Benefits of technology

It improves the accuracy of malicious account identification, avoids the limitations of finding similar accounts with a single parameter, and enhances the ability to identify malicious accounts.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114510695B_ABST
    Figure CN114510695B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of security monitoring technology, and discloses a malicious account detection method, including: obtaining a user ID and basic feature parameters of a target user in a target user set registered in a target application software, and constructing a feature association table through the user ID and the basic feature parameters; calculating the feature similarity between target users corresponding to each user ID according to the basic feature parameters; constructing a graph network based on the feature similarity between target users, and cutting the graph network through a preset graph structure similarity threshold to obtain multiple connected subgraphs; clustering the connected subgraphs using a preset clustering algorithm, and searching the target application software for user IDs belonging to malicious accounts in the feature association table according to the clustered connected subgraphs. The present invention also proposes a malicious account detection device, equipment and storage medium. The present invention also relates to blockchain technology, and the user ID can be stored in a blockchain node. The present invention can improve the accuracy of malicious account identification.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of security monitoring technology, and in particular to a malicious account detection method, device, electronic device and computer-readable storage medium. Background Art

[0002] With the development of network technology, the Internet has been constantly penetrating into every aspect of people's lives. While bringing various conveniences to people, various risks and threats are also accompanied. Internet black industry is one of them. In marketing activities that provide various benefits to users, Internet black industry often maliciously attacks marketing activities through group control software, various simulators, fake devices and other means to seize various benefits.

[0003] The existing method of identifying black market accounts is mainly based on the concentration of mobile phone numbers, device fingerprints, IP, GPS, etc., combined with expert experience, and summarized into rules and strategies for identification and crackdown. However, this method is not very accurate in identifying black market accounts. Summary of the invention

[0004] The present invention provides a malicious account detection method, device, electronic device and computer-readable storage medium, the main purpose of which is to improve the accuracy of malicious account identification.

[0005] To achieve the above object, the present invention provides a malicious account detection method, comprising:

[0006] Obtaining a user ID and basic feature parameters of a target user in a target user set registered with a target application software, and constructing a feature association table through the user ID and the basic feature parameters;

[0007] Calculating the feature similarity between the target users corresponding to the user identifiers according to the basic feature parameters;

[0008] Building a graph network based on the feature similarity between the target users, and cutting the graph network by a preset graph structure similarity threshold to obtain a plurality of connected subgraphs;

[0009] The connected subgraphs are clustered using a preset clustering algorithm, and the user identifiers belonging to malicious accounts in the target application software are searched in the feature association table according to the clustered connected subgraphs.

[0010] Optionally, the calculating, according to the basic feature parameters, the feature similarity between the target users corresponding to the user identifiers includes:

[0011] Determine the basic characteristic parameters of each of the target users to form a characteristic parameter set of each of the target users;

[0012] Comparing the basic feature parameters in the plurality of feature parameter sets, and calculating the similarity between each of the feature parameter sets using the Jaccard similarity coefficient calculation formula;

[0013] The similarities between the feature parameter sets are used as the feature similarities between the target users corresponding to the user identifiers.

[0014] Optionally, constructing a graph network based on feature similarities between the target users includes:

[0015] Taking each of the target users as a node;

[0016] Determine whether the feature similarity between each of the target users is greater than or equal to a preset threshold;

[0017] When the feature similarity between two first target users is less than a preset threshold, the nodes corresponding to the two first target users are not connected;

[0018] When the feature similarity between two second target users is greater than or equal to a preset threshold, the nodes corresponding to the two second target users are connected to obtain a graph network between the target users.

[0019] Optionally, the graph network is cut using a preset graph structure similarity threshold to obtain a plurality of connected subgraphs, including:

[0020] Convert the graph structure similarity threshold into a length value and add it to the graph network;

[0021] Obtain each node in the graph network, and if the number of nodes connected to any node in the graph network is greater than or equal to a preset number of nodes, use the any node as a target node;

[0022] With the length value as the radius and each target node as the center, the nodes within the radius of each center are connected respectively to obtain multiple connected subgraphs.

[0023] Optionally, the Jaccard similarity coefficient calculation formula is:

[0024]

[0025] Among them, A is a characteristic parameter set, B is another characteristic parameter set, is the similarity between feature parameter set A and feature parameter set B.

[0026] Optionally, constructing a feature association table using the user identifier and the basic feature parameters includes:

[0027] Get the preset data storage table;

[0028] The user identification is used as the primary key of the data storage table, and the basic feature parameters are stored in the data storage table as the corresponding data of the primary key to obtain the feature association table.

[0029] Optionally, before constructing the feature association table using the user identifier and the basic feature parameters, the method further includes:

[0030] Construct a key generator based on the AES algorithm;

[0031] Initialize the key generator, obtain the original key, obtain the byte array of the original key, and generate an AES key according to the byte array;

[0032] The basic characteristic parameters are encrypted using the AES key to obtain encrypted characteristic parameters.

[0033] In order to solve the above problem, the present invention also provides a malicious account detection device, the device comprising:

[0034] An association table construction module is used to obtain a user identifier and basic feature parameters of a target user in a target user set registered with a target application software, and to construct a feature association table using the user identifier and the basic feature parameters;

[0035] A similarity calculation module, used to calculate the feature similarity between target users corresponding to each of the user identifiers according to the basic feature parameters;

[0036] A graph network cutting module, used to construct a graph network based on the feature similarity between the target users, and cut the graph network according to a preset graph structure similarity threshold to obtain multiple connected subgraphs;

[0037] The malicious account search module is used to cluster the connected subgraphs using a preset clustering algorithm, and search the feature association table for user identifiers belonging to malicious accounts in the target application software according to the clustered connected subgraphs.

[0038] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0039] at least one processor; and,

[0040] a memory communicatively connected to the at least one processor; wherein,

[0041] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the malicious account detection method as described above.

[0042] In order to solve the above problems, the present invention also provides a computer-readable storage medium, including a data storage area and a program storage area, the data storage area stores created data, and the program storage area stores a computer program; wherein, when the computer program is executed by a processor, the malicious account detection method as described above is implemented.

[0043] In an embodiment of the present invention, a user identifier and basic feature parameters of a target user in a target user set of a target application software are obtained, and a feature association table is constructed using the user identifier and the basic feature parameters. The feature similarity between the target users corresponding to each user identifier is calculated based on the basic feature parameters to achieve a preliminary analysis of the similarity between each account. A graph network is then constructed based on the feature similarity between the target users, and feature similarities with higher similarities are found after cutting and aggregating the graph network. Thus, the user identifier belonging to a malicious account is found according to the feature association table, and the search process between similar accounts is clarified using the graph structure. All basic feature parameters of the target user are used when constructing the graph network, thereby avoiding the limitation of simply searching for similar accounts through a single parameter and improving the accuracy of identifying malicious accounts. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic diagram of a flow chart of a malicious account detection method provided by an embodiment of the present invention;

[0045] Figure 2 A detailed flowchart of a step in a malicious account detection method is provided for one embodiment of the present invention;

[0046] Figure 3 A schematic diagram of a module of a malicious account detection device provided by an embodiment of the present invention;

[0047] Figure 4 A schematic diagram of the internal structure of an electronic device for implementing a malicious account detection method provided by an embodiment of the present invention.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0050] The embodiment of the present application provides a malicious account detection method. The execution subject of the malicious account detection method includes but is not limited to at least one of the electronic devices such as the server, the terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. Among them, the server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. In other words, the malicious account detection method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0051] Reference Figure 1 FIG. 1 is a flow chart of a malicious account detection method provided by an embodiment of the present invention. In this embodiment, the malicious account detection method includes:

[0052] S1. Obtain a user identifier and basic feature parameters of a target user in a target user set registered with a target application software, and construct a feature association table using the user identifier and the basic feature parameters.

[0053] In the embodiment of the present invention, the target user is a user who registers the application software. The target user provides personal information in the target application software to achieve registration, wherein the personal information includes the user's ID number, the user's mobile phone number, the user's address, etc. Specifically, the personal information can be data converted by the same encryption algorithm. It should be noted that the personal information involved in the present invention is obtained with the full knowledge and consent of the corresponding information subject (i.e., the user registered in the target application software), which complies with the provisions of relevant laws and policies.

[0054] In this embodiment, the target application software is any application software installed on the terminal. For example, the target application software is an application software that provides marketing activities for the target user.

[0055] For example, the target application software is a life insurance manager APP, which will send some benefits to users every month to improve user stickiness. For example, it will issue physical rewards to users who participate in certain insurances, provide lottery opportunities, cultivate user loyalty, and issue vouchers to non-participating users to reduce users' insurance expenses, increase insurance sales and user favorability.

[0056] In the embodiment of the present invention, the user identification may be the user ID. The basic characteristic parameters are parameters collected by the target application software. Specifically, the basic characteristic parameters may be parameters related to basic characteristics such as environment, equipment, user behavior, etc. when the target user logs into the target application software or after logging in, such as: network environment, registration password, behavior data, etc.

[0057] In the embodiment of the present invention, the step of constructing a feature association table using the user identifier and the basic feature parameters includes:

[0058] Get the preset data storage table;

[0059] The user identification is used as the primary key of the data storage table, and the basic feature parameters are stored in the data storage table as the corresponding data of the primary key to obtain the feature association table.

[0060] In the embodiment of the present invention, the feature association table is a table that stores the basic feature parameters and the user identifier in association with each other.

[0061] In the embodiment of the present invention, before constructing the feature association table using the user identifier and the basic feature parameters, the method further includes:

[0062] Construct a key generator based on the AES algorithm;

[0063] Initialize the key generator, obtain the original key, obtain the byte array of the original key, and generate an AES key according to the byte array;

[0064] The basic characteristic parameters are encrypted using the AES key to obtain encrypted characteristic parameters.

[0065] Furthermore, the key generator may be constructed according to the source code of the key generator class KeyGenerator in the AES algorithm, and the key generator may be initialized according to the ecnodeRules rule in the AES algorithm.

[0066] In the embodiment of the present invention, the algorithm for encrypting the basic characteristic parameters to obtain the encrypted characteristic parameters is the AES algorithm, which can also be called the Advanced Encryption Standard (AES) algorithm, which is a symmetric encryption algorithm, that is, an algorithm that uses the same key for encryption and decryption.

[0067] In the embodiment of the present invention, the security and integrity of data can be improved by encrypting the basic characteristic parameters.

[0068] S2. Calculate the feature similarity between the target users corresponding to the user identifiers according to the basic feature parameters.

[0069] In the embodiment of the present invention, the feature similarity between the target users is calculated by using the Jaccard similarity coefficient.

[0070] Furthermore, the calculating, based on the basic characteristic parameters, the characteristic similarity between the target users corresponding to the user identifiers includes:

[0071] S201, determining basic characteristic parameters of each target user to form a characteristic parameter set of each target user;

[0072] S202, comparing the basic feature parameters in the plurality of feature parameter sets, and calculating the similarity between each of the feature parameter sets using the Jaccard similarity coefficient calculation formula;

[0073] S203: Using the similarities between the feature parameter sets as feature similarities between the target users corresponding to the user identifiers.

[0074] The calculation formula of the jaccard similarity coefficient in the embodiment of the present invention is:

[0075]

[0076] Among them, A is a feature parameter set, and B is another feature parameter set is the similarity between feature parameter set A and feature parameter set B.

[0077] For example, if there is a feature parameter set a{a1,b1,c3,d2} and a feature parameter set b{a2,b1,c2,d2}, then {a1,b1,c3,d2,a2,c2}, For {b1,d2}, finally for For example, a1 and a2 can be network environments, such as login IP: 116.**.14*.243, 120.23*.0.3**. B1 and b2 can be registration passwords, such as passwords 123*** and ***123.

[0078] In the embodiment of the present invention, the jaccard similarity coefficient is between 0 and 1. A larger jaccard similarity coefficient indicates a greater similarity between the feature parameter sets, and a smaller jaccard similarity coefficient indicates a smaller similarity between the feature parameter sets.

[0079] Furthermore, the similarity between basic feature parameters can also be calculated by a text similarity algorithm. For example, the basic feature parameters are converted into text data. If the similarity between the text data is greater than or equal to a preset threshold, the text data are considered to be the same, wherein the text data includes digital type data.

[0080] S3. Construct a graph network based on the feature similarity between the target users, and cut the graph network using a preset graph structure similarity threshold to obtain multiple connected subgraphs.

[0081] In the embodiment of the present invention, the graph network is a graph network structure constructed based on the feature similarity between each of the target users.

[0082] Furthermore, constructing a graph network based on the feature similarity between the target users includes:

[0083] Taking each of the target users as a node;

[0084] Determine whether the feature similarity between each of the target users is greater than or equal to a preset threshold;

[0085] When the feature similarity between two first target users is less than a preset threshold, the nodes corresponding to the two first target users are not connected;

[0086] When the feature similarity between two second target users is greater than or equal to a preset threshold, the nodes corresponding to the two second target users are connected to obtain a graph network between the target users.

[0087] For example, if the feature similarity between user 1 and user 2 is greater than a preset threshold, user 1 and user 2 are connected in the graph network structure; if the feature similarity between user 3 and user 4 and user 5 is greater than a preset threshold, user 3 is connected to user 4 and user 5 in the graph network structure respectively, to obtain a graph network between the target users.

[0088] Furthermore, if the feature similarity between the first group of two target users is greater than the feature similarity between the second group of two target users, then in the graph structure, the connection distance between the corresponding nodes of the first group of two target users is less than the connection distance between the corresponding nodes of the second group of target users. For example, user 3 is connected to user 4 and user 5 in the image network structure, and the feature similarity between user 3 and user 4 is greater than the feature similarity between user 3 and user 5. Then in the graph structure, the connection distance between user 3 and user 4 is less than the connection distance between user 3 and user 5.

[0089] In the embodiment of the present invention, the graph structure similarity threshold is preset.

[0090] Furthermore, the graph network is cut by a preset graph structure similarity threshold to obtain a plurality of connected subgraphs, including:

[0091] Convert the graph structure similarity threshold into a length value and add it to the graph network;

[0092] Obtain each node in the graph network, and if the number of nodes connected to any node in the graph network is greater than or equal to a preset number of nodes, use the any node as a target node;

[0093] With the length value as the radius and each target node as the center, the nodes within the radius of each center are connected respectively to obtain multiple connected subgraphs.

[0094] In this embodiment, the connected subgraph is a branch of the graph network. Specifically, among the multiple connected subgraphs obtained, each connected subgraph is a graph centered on the target node, and in the graph, nodes within the radius are connected respectively.

[0095] Moreover, each connected subgraph represents a collection of target user nodes in the graph network whose similarity is greater than the graph structure similarity threshold. For example, if the number of nodes in the graph network constructed based on the feature similarity between users is 1,000, and the number of node data of the connected subgraph constructed after cutting the graph network by a preset similarity threshold is 200, then the similarity between these 200 nodes is greater than the similarity between one of the 200 nodes and the other 800 nodes.

[0096] S4. Clustering the connected subgraphs using a preset clustering algorithm, and searching the feature association table for user identifiers belonging to malicious accounts in the target application software according to the clustered connected subgraphs.

[0097] In an embodiment of the present invention, the clustering algorithm is an image clustering algorithm, which is used to classify each node in the connected subgraph. By searching for accounts corresponding to each node in the classified connected subgraph, multiple groups of similar account numbers can be obtained.

[0098] In the embodiment of the present invention, the malicious account is an account registered in the target application software by criminals based on malicious behaviors (such as obtaining various marketing activity rewards, swiping orders, etc.) from the target application software.

[0099] In the embodiment of the present invention, clustering the connected subgraph using a preset clustering algorithm includes: clustering adjacent nodes in the connected subgraph as a category using the clustering algorithm.

[0100] By clustering adjacent nodes in a connected subgraph, it is convenient to search for each node in the connected subgraph later, thus saving the amount of calculation in the search process.

[0101] Furthermore, searching the feature association table for the user identification of a malicious account in the target application software according to the clustered connected subgraph includes: searching the feature association table for the user identification of the target user in the target application software through the basic feature parameters corresponding to each node in the clustered connected subgraph (for example, the network environment of the login device, the account registration password, and the device parameters of the login device), and using the found account as a fraudulent account, wherein each node in the connected subgraph is a basic feature parameter corresponding to each target user.

[0102] Furthermore, all users corresponding to the nodes in the clustered connected subgraph are malicious accounts.

[0103] In an embodiment of the present invention, a user identifier and basic feature parameters of a target user in a target user set of a target application software are obtained, and a feature association table is constructed using the user identifier and the basic feature parameters. The feature similarity between the target users corresponding to each user identifier is calculated based on the basic feature parameters to achieve a preliminary analysis of the similarity between each account. A graph network is then constructed based on the feature similarity between the target users, and feature similarities with higher similarities are found after cutting and aggregating the graph network. Thus, the user identifier belonging to a malicious account is found according to the feature association table, and the search process between similar accounts is clarified using the graph structure. All basic feature parameters of the target user are used when constructing the graph network, thereby avoiding the limitation of simply searching for similar accounts through a single parameter and improving the accuracy of identifying malicious accounts.

[0104] like Figure 3 , which is a module schematic diagram of the malicious account detection device of the present invention.

[0105] The malicious account detection device 100 of the present invention can be installed in an electronic device. According to the functions implemented, the malicious account detection device can include an association table construction module 101, a similarity calculation module 102, a graph network cutting module 103 and a malicious account search module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0106] In this embodiment, the functions of each module / unit are as follows:

[0107] The association table construction module 101 is used to obtain the user identification and basic feature parameters of the target user in the target user set registered with the target application software, and to construct a feature association table through the user identification and the basic feature parameters;

[0108] A similarity calculation module 102 is used to calculate the feature similarity between target users corresponding to each of the user identifiers according to the basic feature parameters;

[0109] A graph network cutting module 103 is used to construct a graph network based on the feature similarity between the target users, and cut the graph network according to a preset graph structure similarity threshold to obtain multiple connected subgraphs;

[0110] The malicious account search module 104 is used to cluster the connected subgraph using a preset clustering algorithm, and search the feature association table for a user identifier belonging to a malicious account in the target application software according to the clustered connected subgraph.

[0111] In detail, each module in the malicious account detection device 100 in the embodiment of the present invention is used in the same manner as described above. Figure 1 to Figure 2 The malicious account detection method described in the above is a technical means, and can produce the same technical effect, so it will not be repeated here.

[0112] like Figure 4 , which is a schematic diagram of the structure of an electronic device for implementing a malicious account detection method according to the present invention.

[0113] The electronic device may include a processor 10, a memory 11, a communication bus 12, and a communication interface 13, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a malicious account detection program.

[0114] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 10 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory 11 (for example, executing malicious account detection programs, etc.), and calling data stored in the memory 11.

[0115] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory 11 may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory 11 may also include both an internal storage unit of the electronic device and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device, such as the code of a malicious account detection program, etc., but also be used to temporarily store data that has been output or is to be output.

[0116] The communication bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0117] The communication interface 13 is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0118] Figure 4 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 4The structure shown does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0119] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0120] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0121] The malicious account detection program stored in the memory 11 in the electronic device is a combination of multiple computer programs. When running in the processor 10, it can achieve:

[0122] Obtaining a user ID and basic feature parameters of a target user in a target user set registered with a target application software, and constructing a feature association table through the user ID and the basic feature parameters;

[0123] Calculating the feature similarity between the target users corresponding to the user identifiers according to the basic feature parameters;

[0124] Building a graph network based on the feature similarity between the target users, and cutting the graph network by a preset graph structure similarity threshold to obtain a plurality of connected subgraphs;

[0125] The connected subgraphs are clustered using a preset clustering algorithm, and the user identifiers belonging to malicious accounts in the target application software are searched in the feature association table according to the clustered connected subgraphs.

[0126] Specifically, the specific implementation method of the processor 10 for the above computer program can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0127] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0128] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0129] Obtaining a user ID and basic feature parameters of a target user in a target user set registered with a target application software, and constructing a feature association table through the user ID and the basic feature parameters;

[0130] Calculating the feature similarity between the target users corresponding to the user identifiers according to the basic feature parameters;

[0131] Building a graph network based on the feature similarity between the target users, and cutting the graph network by a preset graph structure similarity threshold to obtain a plurality of connected subgraphs;

[0132] The connected subgraphs are clustered using a preset clustering algorithm, and the user identifiers belonging to malicious accounts in the target application software are searched in the feature association table according to the clustered connected subgraphs.

[0133] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0134] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0135] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0136] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0137] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0138] The blockchain referred to in this invention is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0139] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0140] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the system claim can also be implemented by one unit or device through software or hardware. The second and other words are used to indicate names, but not to indicate any particular order.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for detecting malicious accounts, It is characterized in that The method comprises: Obtaining a user ID and basic feature parameters of a target user in a target user set registered with a target application software, and constructing a feature association table through the user ID and the basic feature parameters; Calculating the feature similarity between the target users corresponding to the user identifiers according to the basic feature parameters; Building a graph network based on the feature similarity between the target users, and cutting the graph network by a preset graph structure similarity threshold to obtain a plurality of connected subgraphs; Clustering the connected subgraphs using a preset clustering algorithm, and searching the feature association table for user identifiers belonging to malicious accounts in the target application software according to the clustered connected subgraphs; Wherein, constructing a graph network based on the feature similarity between the target users includes: taking each of the target users as a node; judging whether the feature similarity between each of the target users is greater than or equal to a preset threshold; when the feature similarity between two first target users is less than the preset threshold, the nodes corresponding to the two first target users are not connected; when the feature similarity between two second target users is greater than or equal to the preset threshold, the nodes corresponding to the two second target users are connected to obtain a graph network between the target users; The method cuts the graph network by a preset graph structure similarity threshold to obtain a plurality of connected subgraphs, including: converting the graph structure similarity threshold into a length value and adding it to the graph network; obtaining each node in the graph network, and if the number of nodes connected to any node in the graph network is greater than or equal to the preset number of nodes, taking any node as a target node; taking the length value as a radius and each target node as a center, connecting the nodes within the radius of each center respectively to obtain a plurality of connected subgraphs.

2. The malicious account detection method according to claim 1, It is characterized in that The calculating, according to the basic feature parameters, the feature similarity between the target users corresponding to the user identifiers comprises: Determine the basic characteristic parameters of each of the target users to form a characteristic parameter set of each of the target users; Comparing the basic feature parameters in the plurality of feature parameter sets, and calculating the similarity between each of the feature parameter sets using the Jaccard similarity coefficient calculation formula; The similarities between the feature parameter sets are used as the feature similarities between the target users corresponding to the user identifiers.

3. The malicious account detection method according to claim 2, It is characterized in that The Jaccard similarity coefficient calculation formula is: Among them, A is a feature parameter set, and B is another feature parameter set is the similarity between feature parameter set A and feature parameter set B.

4. The malicious account detection method according to claim 1, It is characterized in that The constructing a feature association table by using the user identifier and the basic feature parameters includes: Get the preset data storage table; The user identification is used as the primary key of the data storage table, and the basic feature parameters are stored in the data storage table as the corresponding data of the primary key to obtain the feature association table.

5. The malicious account detection method according to claim 1, It is characterized in that Before constructing the feature association table using the user identifier and the basic feature parameters, the method further includes: Construct a key generator based on the AES algorithm; Initialize the key generator, obtain the original key, obtain the byte array of the original key, and generate an AES key according to the byte array; The basic characteristic parameters are encrypted using the AES key to obtain encrypted characteristic parameters.

6. A malicious account detection device, used to implement the malicious account detection method according to any one of claims 1 to 5, It is characterized in that The device comprises: An association table construction module is used to obtain a user identifier and basic feature parameters of a target user in a target user set registered with a target application software, and to construct a feature association table using the user identifier and the basic feature parameters; A similarity calculation module, used to calculate the feature similarity between target users corresponding to each of the user identifiers according to the basic feature parameters; A graph network cutting module, used to construct a graph network based on the feature similarity between the target users, and cut the graph network according to a preset graph structure similarity threshold to obtain multiple connected subgraphs; The malicious account search module is used to cluster the connected subgraphs using a preset clustering algorithm, and search the feature association table for user identifiers belonging to malicious accounts in the target application software according to the clustered connected subgraphs.

7. An electronic device, It is characterized in that The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the malicious account detection method according to any one of claims 1 to 5.

8. A computer-readable storage medium, comprising a data storage area and a program storage area, wherein the data storage area stores created data and the program storage area stores a computer program; in, When the computer program is executed by a processor, the malicious account detection method according to any one of claims 1 to 5 is implemented.

Citation Information

Patent Citations

  • Abnormal user identification method and device, storage medium and electronic equipment

    CN111612039A

  • Black gang identification method, device and equipment and storage medium

    CN112380531A

  • Abnormal account identification method, system and device and readable storage medium

    CN113254672A

  • Method, System, and Computer Program Product for Identifying a Malicious User

    US20200366700A1