A method, device and computer equipment for identifying a target account

Abstract

The present application relates to a method for identifying a target account. The method includes: obtaining interaction data to be verified within a preset period; obtaining an account level score of an account to be verified associated with the interaction data to be verified through the interaction data to be verified; screening a target account from the accounts to be verified according to the interaction data to be verified and a preset account level rule; inputting the target account into a second identification model to obtain an account community associated with the target account; obtaining a level rule and a group level score for account grouping according to a first feature and a second feature of the account community; based on the interaction data to be verified of the account community, screening an interaction mode of the account grouping according to the characteristics of the determined account community; obtaining a target account in the account community according to the account level score, the group level score, the level rule of the account grouping, and the interaction mode of the account grouping. The use of this method can reduce the resource consumption problem of directly calculating a large number of target accounts.

Description

Technical Field

[0001] The present application relates to the field of network information security, and in particular to a method, apparatus, and computer equipment for target account identification. Background Art

[0002] As the current Internet environment becomes more complex, some users have used Internet platforms to conduct behaviors that do not comply with regulations. In order to ensure a safe and orderly network environment, the security of the network environment can be maintained by screening target accounts.

[0003] At present, business rules are formulated and machine learning is used to screen out individual accounts. However, the existing technology in machine learning relies on the business experience of staff to generate account labels and screen out individual accounts. Not only can other related target accounts not be found through individual accounts, but direct calculation of a large number of target accounts will cause resource consumption. Summary of the invention

[0004] Based on this, it is necessary to provide a method for target account identification to address the above technical issues. The target account can be screened out through interaction data, and the account community associated with the target account can be obtained, so as to find more target accounts through the account community.

[0005] In a first aspect, the present application provides a method for identifying a target account, the method comprising:

[0006] Obtaining interaction data to be verified within a preset period of time;

[0007] Inputting the to-be-verified interaction data into a first recognition model to obtain an account level score of the to-be-verified account associated with the to-be-verified interaction data;

[0008] Filtering a target account from the accounts to be verified according to the interaction data to be verified and preset account-level rules;

[0009] Input the target account into a second recognition model to obtain an account community associated with the target account, wherein the second recognition model is trained based on a clustering algorithm; screen the first feature of the account community to formulate a level rule for account grouping, input the second feature of the account community into a third recognition model to obtain a group level score, wherein the third recognition model is trained based on a graph convolutional neural network;

[0010] Determine the characteristics of the account community based on the interaction data to be verified of the account community, and filter the interaction patterns of the account groups according to the characteristics of the account community;

[0011] The target accounts in the account community are obtained according to the account level score, the group level score, the level rules of the account grouping, and the interaction mode of the account grouping.

[0012] In one embodiment, the method further comprises:

[0013] The target account and target accounts in the account community are obtained, and a relationship network between the target account and target accounts in the account community is constructed to find other associated target accounts.

[0014] In one embodiment, obtaining the account community associated with the target account includes:

[0015] A transaction relationship network is constructed according to the data to be detected and the account characteristics, and the target account is input into the second recognition model as a seed node of the transaction relationship network to obtain an account community associated with the target account.

[0016] In one embodiment, obtaining the target account in the account community according to the account level score, the group level score, the level rule of the account grouping, and the interaction mode of the account grouping includes:

[0017] The target accounts associated with the interaction data to be verified are screened out according to the account level score, and the target accounts in the account community associated with the target accounts are screened out according to the group level score, the level rules of the account grouping, and the interaction mode of the account grouping.

[0018] In a second aspect, the present application further provides a target account identification device, the device comprising:

[0019] A data acquisition module, used to acquire interaction data to be verified within a preset period of time;

[0020] A first recognition module, configured to input the interaction data to be verified into a first recognition model to obtain an account level score of the account to be verified associated with the interaction data to be verified;

[0021] A first target module, configured to filter a target account from the accounts to be verified according to the interaction data to be verified and a preset account level rule;

[0022] A second identification module is used to input the target account into a second identification model to obtain an account community associated with the target account, wherein the second identification model is trained based on a clustering algorithm; screen the first feature of the account community to formulate a level rule for account grouping, input the second feature of the account community into a third identification model to obtain a gang level score, wherein the third identification model is trained based on a graph convolutional neural network;

[0023] A screening module, configured to determine the characteristics of the account community based on the interaction data to be verified of the account community, and screen the interaction patterns of the account groups according to the characteristics of the account community;

[0024] The second target module is used to obtain the target account in the account community according to the account level score, the group level score, the level rule of the account grouping, and the interaction mode of the account grouping.

[0025] In one embodiment, the device further comprises:

[0026] The target account and target accounts in the account community are obtained, and a relationship network between the target account and target accounts in the account community is constructed to find other associated target accounts.

[0027] In one embodiment, obtaining the account community associated with the target account includes:

[0028] A transaction relationship network is constructed according to the data to be detected and the account characteristics, and the target account is input into the second recognition model as a seed node of the transaction relationship network to obtain an account community associated with the target account.

[0029] In one embodiment, obtaining the target account in the account community according to the account level score, the group level score, the level rule of the account grouping, and the interaction mode of the account grouping includes:

[0030] The target accounts associated with the interaction data to be verified are screened out according to the account level score, and the target accounts in the account community associated with the target accounts are screened out according to the group level score, the level rules of the account grouping, and the interaction mode of the account grouping.

[0031] In a third aspect, the present disclosure further provides a computer device, wherein the computer device 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 target account identification method are implemented.

[0032] In a fourth aspect, the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the target account identification method when executed by a processor.

[0033] In a fifth aspect, the present disclosure further provides a computer program product, which includes a computer program that implements the steps of the target account identification method when executed by a processor.

[0034] The above method for identifying a target account has at least the following beneficial effects:

[0035] The embodiment scheme provided by the present disclosure screens out the target account through the data to be verified within a preset time period, and obtains the account community associated with the target account through the target account. The first feature and the second feature of the account community are screened to obtain the level rules and group level scores of the account grouping. The characteristics of the account community are determined based on the interaction data to be verified in the account community, and the interaction mode of the account grouping is screened. The target account in the account community associated with the target account is screened based on the group level score, the level rules of the account grouping, and the interaction mode of the account grouping, thereby reducing the resource consumption problem of directly calculating a large number of target accounts. It is also possible to build a relationship network of all target accounts, find other target accounts through the relationship network, and realize the display of visual association analysis.

[0036] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0038] Figure 1 A diagram of an application environment of a target account identification method in one embodiment;

[0039] Figure 2 A flowchart of a target account identification method in one embodiment;

[0040] Figure 3 is a structural block diagram of a target account identification device in one embodiment;

[0041] Figure 4 is an internal structure diagram of a computer device in one embodiment;

[0042] Figure 5 The figure is a diagram of the internal structure of a server in one embodiment. DETAILED DESCRIPTION

[0043] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0044] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. On the contrary, they are only examples of devices and methods consistent with some aspects of the present disclosure as detailed in the attached claims. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also includes elements inherent to such process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. For example, if the words first, second, etc. are used to represent the name, they do not represent any specific order.

[0045] The present disclosure provides a target account identification method, which can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0046] In some embodiments of the present disclosure, Figure 2 As shown, a target account identification method is provided, which is applied to Figure 1 The method is described by taking the example of the server in the example of processing the interaction data to be verified. It can be understood that the method can be applied to the server, and can also be applied to the system including the terminal and the server, and is implemented through the interaction between the terminal and the server. In a specific embodiment, the method can include the following steps:

[0047] S202: Acquire interaction data to be verified within a preset period of time.

[0048] When users operate their accounts, they generate interaction data every moment. First, we can obtain the interaction data to be verified for a preset period of time from a large amount of interaction data, which can reduce the time of machine processing. The preset period can be determined based on actual business operations or business needs. The interaction data to be verified can include all data generated by ordinary users or target users in the process of operating their accounts, as well as data of other users who interact with ordinary users or target users.

[0049] S204: Inputting the interaction data to be verified into a first recognition model to obtain an account level score of the account to be verified associated with the interaction data to be verified.

[0050] The first recognition model may include: performing account feature analysis on the account to be verified associated with the interaction data to be verified, using the account to be verified after the account feature analysis as a training sample, and training based on a gradient boosting decision tree machine learning algorithm (LightGBM). The account level score can be used to indicate the possibility that the account to be verified is the target account. If the account level score is high, the possibility that the account to be verified becomes the target account may also be high.

[0051] In some embodiments of the present disclosure, the data to be verified can be cleaned first, and can be determined based on the interaction code, summary code, and the particularity of the two parties to the interaction. The account feature analysis can be performed based on the basic information, interaction frequency, interaction address, etc. of the account to be verified associated with the interaction data to be verified, and the account to be verified after the account feature analysis is used as a training sample to construct a first recognition model. The first recognition model can be used to obtain information such as the probability and ratio of the account to be verified becoming the target account, and the information can be converted into an account-level score, so that the possibility of the account to be verified becoming the target account can be intuitively seen.

[0052] S206: Filtering a target account from the accounts to be verified according to the interaction data to be verified and preset account level rules.

[0053] In the embodiments of the present disclosure, the stability index, information value, and evidence weight analysis operations can be performed on the account characteristics. The ability of the account characteristics to distinguish the target account can be evaluated through the business experience of the operator and the results of the analysis operation, and account characteristics with strong distinguishing ability can be obtained, such as the number of interactions, interaction volatility, etc. Corresponding account-level rules can be formulated for account characteristics with strong distinguishing ability. The target account can be screened out based on the interaction data to be verified and the account-level rules.

[0054] In the embodiments of the present disclosure, the account characteristics of the to-be-verified account associated with the to-be-verified data can be analyzed to obtain account characteristics with strong distinguishing ability, and corresponding account-level rules can be formulated for the account characteristics with strong distinguishing ability. In some embodiments of the present disclosure, when the account characteristic is the number of transactions, the account-level rule can be set to that the to-be-verified account with more than 151 interactions within 3 months is a possible target account. Then the possible target accounts are screened to obtain the target account.

[0055] S208: Input the target account into a second recognition model to obtain an account community associated with the target account, wherein the second recognition model is trained based on a clustering algorithm; screen the first feature of the account community to formulate a level rule for account grouping, input the second feature of the account community into a third recognition model to obtain a group level score, wherein the third recognition model is trained based on a graph convolutional neural network.

[0056] The second recognition model is obtained by training based on a clustering algorithm, and in some embodiments of the present disclosure, it can be a community mining algorithm (LCD), a partitioning method, a hierarchical method, etc. The account characteristics in the account community are analyzed, and the account characteristics in the account community can be divided into a first feature and a second feature according to the ability of the account characteristics in the account community to distinguish the target account. The first feature can be a feature with strong distinguishing ability, and the second feature can be a general feature.

[0057] In an embodiment of the present disclosure, a community mining algorithm can be used to obtain an account community associated with the target account, and feature analysis can be performed on accounts in the account community. A level rule for account grouping can be formulated based on the first feature, and the level rule for account grouping can be used to screen account communities containing target accounts. A graph convolutional neural network model (GraphSage) can be constructed based on the second feature, and the probability of an account in the account community becoming a target account can be obtained. A group level score can be formulated based on the probability value, which can be used to obtain the possibility of an account in the account community becoming a target account.

[0058] S210: Determine the characteristics of the account community based on the interaction data to be verified of the account community, and filter the interaction patterns of the account groups according to the characteristics of the account community.

[0059] The characteristics of the account community may include the number of interactions, the amount of interaction data, etc. The interaction mode of the account grouping may include the interaction of abnormal data, the interaction of excess data, etc.

[0060] In some embodiments of the present disclosure, the characteristics of the account community can be determined based on the interaction data to be verified of the account community. When the number of interactions is higher than the preset number, the high number of interactions can be used as the characteristic of the account community. The interaction mode of the account grouping can be screened based on the characteristics of the account community. If the characteristic of the account community is the high number of interactions, abnormal data or excess data may appear in the interaction data, and the abnormal data or excess data in the interaction data can be screened as the interaction mode of the account grouping.

[0061] S212: Obtain target accounts in the account community according to the account level score, the group level score, the level rule of the account grouping, and the interaction mode of the account grouping.

[0062] In an embodiment of the present disclosure, target accounts associated with the interaction data to be verified can be screened out according to the account level score, and target accounts in the account community associated with the target account can be screened out according to the group level score, the level rules of the account grouping, and the interaction mode of the account grouping.

[0063] In the above target account identification method, the target account can be screened according to the interaction data to be verified within a preset period, and the account community associated with the target account can be obtained through the target account. The group level score, the level rules of account grouping, and the interaction mode of account grouping can be formulated according to the account community associated with the target account to obtain the target account in the account community. This reduces the resource consumption problem of directly calculating a large number of target accounts.

[0064] In some embodiments of the present disclosure, the method further includes:

[0065] The target account and target accounts in the account community are obtained, and a relationship network between the target account and target accounts in the account community is constructed to find other associated target accounts.

[0066] The relationship network between the target account obtained through the interaction data to be verified and the target account in the account community can be constructed through knowledge graph technology. Knowledge graph technology can provide multiple semantic connections, and the accuracy of finding other related target accounts based on knowledge graph technology may be higher.

[0067] In the embodiments of the present disclosure, a relationship network between a target account and target accounts in an account community can be constructed based on knowledge graph technology. Not only can the relationship between target accounts in the relationship network be intuitively seen through the relationship network, but other associated target accounts can also be found through the relationship between target accounts.

[0068] In some embodiments of the present disclosure, obtaining the account community associated with the target account includes:

[0069] A transaction relationship network is constructed according to the data to be detected and the account characteristics, and the target account is input into the second recognition model as a seed node of the transaction relationship network to obtain an account community associated with the target account.

[0070] A community can be composed of a group of nodes, which are highly connected. This group of nodes is different from other nodes in the community. This group of nodes can be regarded as seed nodes for finding other nodes.

[0071] In an embodiment of the present disclosure, the target account may be used as a seed node. When the transaction relationship network is started, other nodes in the network may be quickly discovered through the seed node, and the account community associated with the target account may be obtained.

[0072] In some embodiments of the present disclosure, obtaining the target account in the account community according to the account-level score, the gang-level score, the level rules of the account grouping, and the interaction mode of the account grouping includes: filtering out the target account associated with the interaction data to be verified according to the account-level score, and filtering out the target account in the account community associated with the target account according to the gang-level score, the level rules of the account grouping, and the interaction mode of the account grouping.

[0073] In the process of screening target accounts based on the interaction data to be verified and the preset account-level rules, some accounts do not hit the account-level rules, and accounts that do not hit the account-level rules may become target accounts. In the subsequent process of finding the associated account community through the target account, the account that does not hit the account-level rules may be in the account community associated with other target accounts, or may not be in the account community associated with other target accounts. Accounts that do not hit the account-level rules can be scored with a scorecard to reduce the possibility of missing target accounts.

[0074] In an embodiment of the present disclosure, a scorecard method may involve the integration of point-double-odds and logistic regression to obtain the score of an account that does not hit the account-level rule to become a target account. In the case where the account that does not hit the account-level rule is in the account community associated with other target accounts, a decision summary is performed again based on four aspects: account-level score, gang-level score, level rule of account grouping, and interaction mode of account grouping. The scorecard method can be used to obtain the possibility of the account that does not hit the account-level rule becoming a target account. In the case where the account that does not hit the account-level rule is not in the account community associated with other target accounts, the possibility of the account that does not hit the account-level rule becoming a target account can be obtained based on the account-level score.

[0075] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0076] Based on the same inventive concept, the embodiment of the present disclosure also provides a target account identification device for implementing the target account identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the target account identification device embodiment provided below can refer to the limitations of the target account identification method above, and will not be repeated here.

[0077] The device may include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiments of this specification and a device in combination with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided in the embodiments of the present disclosure is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the device are similar, the implementation of the specific device in the embodiments of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. As used below, the term "unit" or "module" can implement a combination of software and / or hardware for predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0078] In one embodiment, Figure 3 As shown, a target account identification device 300 is provided, and the device may be the aforementioned server, or a module, component, device, unit, etc. integrated in the server.

[0079] The apparatus 300 may include:

[0080] The data acquisition module 302 is used to acquire the interaction data to be verified within a preset period of time;

[0081] A first identification module 304, configured to input the interaction data to be verified into a first identification model to obtain an account level score of the account to be verified associated with the interaction data to be verified;

[0082] A first target module 306, configured to filter a target account from the accounts to be verified according to the interaction data to be verified and a preset account level rule;

[0083] The second identification module 308 is used to input the target account into a second identification model to obtain an account community associated with the target account, wherein the second identification model is trained based on a clustering algorithm; screen the first feature of the account community to formulate a level rule for account grouping, input the second feature of the account community into a third identification model to obtain a gang level score, wherein the third identification model is trained based on a graph convolutional neural network;

[0084] A screening module 310, configured to determine the characteristics of the account community based on the interaction data to be verified of the account community, and screen the interaction patterns of the account groups according to the characteristics of the account community;

[0085] The second target module 312 is used to obtain the target account in the account community according to the account level score, the group level score, the level rule of the account grouping, and the interaction mode of the account grouping.

[0086] In one embodiment, the apparatus further comprises:

[0087] The target account and target accounts in the account community are obtained, and a relationship network between the target account and target accounts in the account community is constructed to find other associated target accounts.

[0088] In one embodiment, obtaining the account community associated with the target account includes:

[0089] A transaction relationship network is constructed according to the data to be detected and the account characteristics, and the target account is input into the second recognition model as a seed node of the transaction relationship network to obtain an account community associated with the target account.

[0090] In one embodiment, obtaining the target account in the account community according to the account level score, the group level score, the level rule of the account grouping, and the interaction mode of the account grouping includes:

[0091] The target accounts associated with the interaction data to be verified are screened out according to the account level score, and the target accounts in the account community associated with the target accounts are screened out according to the group level score, the level rules of the account grouping, and the interaction mode of the account grouping.

[0092] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0093] Each module in the above-mentioned target account identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module above.

[0094] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store interactive data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a target account identification method is implemented.

[0095] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a target account identification method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0096] Those skilled in the art will understand that Figure 4 , Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0097] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method described in any embodiment of the present disclosure is implemented.

[0098] In one embodiment, a computer program product is provided, including a computer program, which implements the method described in any embodiment of the present disclosure when executed by a processor.

[0099] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present disclosure may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided by the present disclosure may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited thereto.

[0100] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0101] The above-described embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the attached claims.

Claims

1. A method for identifying a target account, characterized in that: The method comprises: Obtaining interaction data to be verified within a preset period of time; Inputting the interaction data to be verified into a first recognition model to obtain an account level score of the account to be verified associated with the interaction data to be verified; Filtering a target account from the accounts to be verified according to the interaction data to be verified and a preset account level rule; The target account is input into the second recognition model, a transaction relationship network is constructed according to the data to be detected and the account characteristics, and the target account is input into the second recognition model as a seed node of the transaction relationship network to obtain an account community associated with the target account, and the second recognition model is obtained by training based on a clustering algorithm; the first feature of the account community is screened to formulate a level rule for account grouping, and the second feature of the account community is input into the third recognition model to obtain a gang level score, and the third recognition model is obtained by training based on a graph convolutional neural network; the first feature includes a feature with strong distinguishing ability, and the second feature includes a general feature; Determine the characteristics of the account community based on the interaction data to be verified of the account community, and filter the interaction patterns of the account groups according to the characteristics of the account community; The target accounts in the account community are obtained according to the account level score, the group level score, the level rules of the account grouping, and the interaction mode of the account grouping.

2. The method according to claim 1, characterized in that The method further comprises: The target account and target accounts in the account community are obtained, and a relationship network between the target account and target accounts in the account community is constructed to find other associated target accounts.

3. The method according to claim 1, characterized in that The target accounts in the account community are obtained according to the account level score, the group level score, the level rules of the account grouping, and the interaction mode of the account grouping, including: The target accounts associated with the interaction data to be verified are screened out according to the account level score, and the target accounts in the account community associated with the target accounts are screened out according to the group level score, the level rules of the account grouping, and the interaction mode of the account grouping.

4. A device for identifying a target account, characterized in that: The device comprises: A data acquisition module, used to acquire interaction data to be verified within a preset period of time; A first recognition module, configured to input the interaction data to be verified into a first recognition model to obtain an account level score of the account to be verified associated with the interaction data to be verified; A first target module, configured to filter a target account from the accounts to be verified according to the interaction data to be verified and a preset account level rule; A second identification module is used to input the target account into a second identification model, construct a transaction relationship network according to the data to be detected and the account characteristics, input the target account as a seed node of the transaction relationship network into the second identification model, and obtain an account community associated with the target account, wherein the second identification model is trained based on a clustering algorithm; the first feature of the account community is screened to formulate a level rule for account grouping, and the second feature of the account community is input into a third identification model to obtain a gang level score, wherein the third identification model is trained based on a graph convolutional neural network; the first feature includes a feature with strong distinguishing ability, and the second feature includes a general feature; A screening module, configured to determine the characteristics of the account community based on the interaction data to be verified of the account community, and screen the interaction patterns of the account groups according to the characteristics of the account community; The second target module is used to obtain the target account in the account community according to the account level score, the group level score, the level rule of the account grouping, and the interaction mode of the account grouping.

5. The device according to claim 4, characterized in that The device also includes: The target account and target accounts in the account community are obtained, and a relationship network between the target account and target accounts in the account community is constructed to find other associated target accounts.

6. The device according to claim 4, characterized in that The target accounts in the account community are obtained according to the account level score, the group level score, the level rules of the account grouping, and the interaction mode of the account grouping, including: The target accounts associated with the interaction data to be verified are screened out according to the account level score, and the target accounts in the account community associated with the target accounts are screened out according to the group level score, the level rules of the account grouping, and the interaction mode of the account grouping.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 3 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

9. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images