Payment terminal identification method and device, equipment and storage medium

Abstract

The invention provides a payment terminal identification method and device, equipment and a storage medium. The method comprises the steps that a community of a payment terminal is acquired, the community belongs to a payment terminal association network corresponding to the payment terminal, the payment terminal association network is generated according to payment transaction data of the payment terminal, and the community comprises a first community and a second community, the transaction time intervals of the payment transaction data corresponding to the first community and the second community are different; and according to the similarity between the first community and the second community, determining whether the first community and / or the second community comprise / comprises an abnormal payment terminal, and if the first community and / or the second community comprise / comprises the abnormal payment terminal, outputting the abnormal payment terminal. The method is used for achieving the effect of improving the accuracy and efficiency of identifying the abnormal payment terminal.

Description

Technical Field

[0001] The present application relates to data processing technology, and in particular to a payment terminal identification method, device, equipment and storage medium. Background Art

[0002] In a normal business operation model, merchants often have fixed business locations, which are relatively stable and rarely change. This stability is based on the characteristics of traditional business operations, such as store leasing, fixed layout of business facilities, and geographical positioning of target customer groups. Therefore, the location of merchants' payment terminals is usually fixed.

[0003] With the development of the payment industry, third-party acquiring institutions play an important role in the commercial payment system, but some institutions have problems with illegal operations. For example, they use payment terminals to conduct improper behaviors such as cash withdrawal and code duplication to obtain improper benefits. These illegal operations break the normal pattern of merchant transaction behavior and make merchant transaction behavior abnormal. This abnormality not only affects the merchant's own operating risk and reputation, but may also have a serious negative impact on the security of the entire payment system, financial order, and consumer rights protection. However, the current method of identifying abnormal payment terminals has the problem of low accuracy.

[0004] Therefore, how to improve the accuracy of identifying abnormal payment terminals is a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a payment terminal identification method, apparatus, device and storage medium to solve the problem of low accuracy in identifying abnormal payment terminals.

[0006] In a first aspect, the present application provides a payment terminal identification method, comprising:

[0007] Acquire a community of the payment terminal, the community belonging to a payment terminal associated network corresponding to the payment terminal, the payment terminal associated network generated according to payment transaction data of the payment terminal, the community including a first community and a second community, the transaction time intervals of the payment transaction data corresponding to the first community and the second community being different;

[0008] determining, according to the similarity between the first community and the second community, whether the first community and / or the second community includes an abnormal payment terminal;

[0009] If the abnormal payment terminal is included, the abnormal payment terminal is output.

[0010] Optionally, the determining, according to the similarity between the first community and the second community, whether the first community and / or the second community includes an abnormal payment terminal includes:

[0011] Acquire the same first payment terminal in the first community and the second community;

[0012] determining, according to the first payment terminal, a similarity between the first community and the second community;

[0013] If the similarity is less than or equal to a first preset similarity threshold, it is determined that the first community and / or the second community includes the abnormal payment terminal.

[0014] Optionally, determining the similarity between the first community and the second community according to the first payment terminal includes:

[0015] Acquire a second payment terminal, where the second payment terminal includes all payment terminals in the first community and all payment terminals in the second community;

[0016] The similarity between the first community and the second community is obtained according to the first payment terminal and the second payment terminal.

[0017] Optionally, the determining, according to the similarity between the first community and the second community, whether the first community and / or the second community includes an abnormal payment terminal includes:

[0018] generating a first embedding vector for the first community according to the graph embedding representation of the first community;

[0019] generating a second embedding vector for the second community according to the graph embedding representation of the second community;

[0020] If the similarity between the first embedding vector and the second embedding vector is less than or equal to a second preset similarity threshold, it is determined that the first community and / or the second community includes the abnormal payment terminal.

[0021] Optionally, the payment terminal association network includes location information of the payment terminal, and after determining whether the first community and / or the second community includes an abnormal payment terminal according to the similarity between the first community and the second community, the method further includes:

[0022] determining, according to the location information of the payment terminal, a dispersion degree of the payment terminals in the first community and / or the second community;

[0023] If the payment terminal dispersion is greater than or equal to a preset dispersion threshold, it is determined that the first community and / or the second community includes the abnormal payment terminal.

[0024] Optionally, determining the dispersion of payment terminals in the first community and / or the second community according to the location information of the payment terminal includes:

[0025] Acquire location information of payment terminals in the first community and / or the second community;

[0026] Determining payment terminals included in each of the areas according to the areas to which the location information belongs;

[0027] Arrange the payment terminals according to the number of the payment terminals included in each of the areas to generate payment terminal location distribution data;

[0028] The dispersion of payment terminals in the first community and / or the second community is determined according to the number of payment terminals in a first area, the first area being an area with the largest number of payment terminals.

[0029] Optionally, if the discreteness of the payment terminal is less than a preset discreteness threshold, the method further includes:

[0030] Acquire, from the payment terminal location distribution data, a third payment terminal whose distance from the first area is greater than or equal to a preset distance threshold;

[0031] The third payment terminal is determined as the abnormal payment terminal.

[0032] Optionally, acquiring from the payment terminal location distribution data a third payment terminal whose location distance from the first area is greater than or equal to a preset distance threshold includes:

[0033] Acquire, from the payment terminal location distribution data, a second area whose distance from the first area is greater than or equal to the preset distance threshold, the second area being an area in the payment terminal location distribution data other than the first area;

[0034] If the second area exists, the payment terminal whose location is within the second area is determined to be the third payment terminal.

[0035] Optionally, the payment terminal association network includes location information of the payment terminal, and the method further includes:

[0036] Acquire the community of the payment terminal;

[0037] determining, according to the location information of the payment terminal, a dispersion degree of the payment terminals in the first community and / or the second community;

[0038] If the payment terminal dispersion is greater than or equal to a preset dispersion threshold, determining that the first community and / or the second community includes the abnormal payment terminal;

[0039] The abnormal payment terminal is output.

[0040] Optionally, the weight of any edge in the payment terminal association network is related to a transaction time interval between two nodes corresponding to the edge.

[0041] Optionally, the weight of any edge in the payment terminal association network is related to the minimum transaction time interval between two nodes corresponding to the edge and a preset duration, and the preset duration is used to determine whether there is an association between two nodes in the payment terminal association network based on the payment transaction data.

[0042] In a second aspect, the present application provides a payment terminal identification device, comprising:

[0043] an acquisition module, configured to acquire a community of a payment terminal, wherein the community belongs to a payment terminal associated network corresponding to the payment terminal, the payment terminal associated network being generated according to payment transaction data of the payment terminal, the community comprising a first community and a second community, and the transaction time intervals of the payment transaction data corresponding to the first community and the second community being different;

[0044] a processing module, configured to determine whether the first community and / or the second community includes an abnormal payment terminal according to the similarity between the first community and the second community;

[0045] An output module is used to output the abnormal payment terminal if the abnormal payment terminal is included.

[0046] In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0047] The memory stores computer-executable instructions;

[0048] The processor executes the computer-executable instructions stored in the memory to implement the method as described in the first aspect.

[0049] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0050] In a fifth aspect, the present application provides a computer program product, which, when executed by a processor, is used to implement the method as described in the first aspect.

[0051] The payment terminal identification method, device, equipment and storage medium provided in the present application obtain the first community and the second community of the payment terminal from the payment terminal association network, and determine whether there is a large difference between the first community and the second community in different transaction time intervals based on the similarity between the first community and the second community. Since the payment terminal in the present application is a payment terminal whose transaction location is not easy to change, if the similarity between the first community and the second community is low, it indicates that the location of the payment terminal in the two communities has changed, so it can be considered that there is an abnormal payment terminal among the payment terminals included in the two communities, thereby improving the efficiency and accuracy of identifying abnormal payment terminals. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0053] Figure 1 A schematic diagram of a payment terminal identification method provided in an embodiment of the present application;

[0054] Figure 2 A flowchart of another payment terminal identification method provided in an embodiment of the present application;

[0055] Figure 3 A community schematic diagram provided for an embodiment of the present application;

[0056] Figure 4 A flowchart of another payment terminal identification method provided in an embodiment of the present application;

[0057] Figure 5 A flowchart of another payment terminal identification method provided in an embodiment of the present application;

[0058] Figure 6 A flowchart of another payment terminal identification method provided in an embodiment of the present application;

[0059] Figure 7 A schematic diagram of the structure of a payment terminal identification device provided in an embodiment of the present application;

[0060] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0061] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0062] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application.

[0063] “It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portals for users to choose to authorize or refuse.

[0064] First, the current methods for identifying abnormal payment terminals are introduced:

[0065] Method 1: Generate a merchant association network based on the transaction information of merchants (implied as payment terminals). Merchants include merchants to be determined and given seed abnormal merchants. Merchants in the merchant association network whose similarity exceeds the preset similarity threshold have connection edges. In the merchant association network, with the seed abnormal merchant as the center, the label coloring algorithm is used to color the labels of the merchants to be determined along the connection edges between merchants, and the merchants to be determined and the seed abnormal merchants that have been successfully colored are determined as abnormal sample merchants. The abnormal merchant detection model is trained using the merchant multi-dimensional transaction data of the abnormal sample merchants. According to the merchant multi-dimensional transaction data of the merchant to be detected and the abnormal merchant detection model, it is determined whether the merchant to be detected is an abnormal merchant.

[0066] However, this identification method relies on a pre-acquired reference data set (ie, seed abnormal merchants). If the seed abnormal merchants cannot be obtained, it is difficult to identify abnormal payment terminals.

[0067] Method 2: Obtain the recorded data of multiple users in different time periods, determine the object sequence corresponding to each user according to the recorded time and object attribute information in the recorded data of each user, and then establish the object association network corresponding to different time periods based on the object sequence corresponding to each user. Then, based on the object association network corresponding to different time periods, determine the similarity of the state of the target object in the object association network in different time periods, and finally determine whether the target object is an abnormal object based on the similarity.

[0068] However, this scheme performs anomaly detection by comparing the local feature similarities of payment terminals in the associated network, ignoring the overall characteristics of the community where the payment terminal is located and not considering the location factor of the payment terminal, resulting in a low accuracy rate in identifying abnormal payment terminals.

[0069] In view of this, the present application provides a payment terminal identification method, which obtains the first community and the second community of the payment terminal from the payment terminal association network, and determines whether there is a large difference between the first community and the second community in different transaction time intervals according to the similarity between the first community and the second community. Since the payment terminal in the present application is a payment terminal whose transaction location is not easy to change, if the similarity between the first community and the second community is low, it indicates that the location of the payment terminal in the two communities has changed, so it can be considered that there are abnormal payment terminals in the payment terminals included in the two communities, thereby improving the efficiency and accuracy of identifying abnormal payment terminals.

[0070] The execution subject of the payment terminal identification method provided in the present application may be a terminal device with data processing function, or a processing chip of the terminal device, or software or program code for implementing the payment terminal identification method. When the execution subject is a terminal device with data processing function, the terminal device may be, for example, a computing device such as a computer or a mobile phone with computing function, and the computing device may be deployed with software or program code for running the payment terminal identification method, and the software or program code is used to identify whether there are abnormal payment terminals in the community.

[0071] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0072] Figure 1 A flow chart of a payment terminal identification method provided in this application. Figure 1 As shown, the method includes:

[0073] S101. Obtain a community of a payment terminal.

[0074] The community belongs to a payment terminal associated network corresponding to the payment terminal. The payment terminal associated network is generated based on the payment transaction data of the payment terminal. The community includes a first community and a second community, and the transaction time intervals of the payment transaction data corresponding to the first community and the second community are different. The payment terminal is a payment terminal with a fixed transaction location or a transaction location that is not easily changed, such as an automatic teller machine, a shopping mall payment terminal, or a supermarket payment terminal.

[0075] The payment transaction data may include, for example, the identification of the payment terminal, the identification of the transaction entity corresponding to the payment terminal (eg, a shopping mall, a supermarket, an ATM, etc.), the transaction date, the transaction time, etc.

[0076] Through payment transaction data, the payment terminal association network can be constructed through transaction records after obtaining the transaction records of multiple transaction entities. Exemplarily, assuming that for the same transaction terminal (such as a mobile phone, smart watch, etc.) or the same trader identifier in the transaction record (such as a bank card number, transaction account number, etc.), there are transaction records of transactions conducted successively at two payment terminals in a short period of time, then it can be considered that the distance between the two payment terminals is close. At this time, the two payment terminals can be regarded as two nodes in the payment terminal association network, and the connection between the two nodes can be regarded as the edge of the two nodes in the payment terminal association network. The node can be represented, for example, by the identifier of the payment terminal, the identifier of the transaction entity corresponding to the payment terminal, etc.

[0077] For example, it can be assumed that the transaction record includes the transaction records of the same bank card in payment terminal A and payment terminal B continuously within a time period of t, then payment terminal A and payment terminal B can be regarded as two nodes in the payment terminal association network, and payment terminal A and payment terminal B are connected as an edge between the two. The time period t can be set according to actual needs, for example, it can be 10 minutes.

[0078] Through the above method, a payment terminal association network can be generated according to payment transaction data.

[0079] Optionally, the weight of any edge in the payment terminal association network is related to the transaction time interval between two nodes corresponding to the edge. For example, the smaller the transaction time interval, the greater the weight of the edge. Alternatively, the weight of the edge may be calculated based on the transaction time interval.

[0080] Taking the edge weight calculated based on the transaction time interval as an example, specifically, the weight of any edge in the payment terminal association network is related to the minimum transaction time interval between two nodes corresponding to the edge and the preset duration. The preset duration is used to determine whether there is an association between two nodes in the payment terminal association network based on the payment transaction data.

[0081] For example, the transaction records include n bank cards that are continuously traded at payment terminal A and payment terminal B within a period of t (i.e., the preset period mentioned above). Assume that the n bank cards are continuously traded at payment terminal A and payment terminal B, and the transaction time intervals corresponding to each bank card are t1, t2, ..., tn. At this time, the minimum transaction time interval t can be taken from t1, t2, ..., tn. min, then the weight of the edge between the node corresponding to payment terminal A and the node corresponding to payment terminal B can be expressed as the following formula (1):

[0082]

[0083] The community of the payment terminal can be obtained by processing the payment terminal associated network through a community partitioning algorithm such as Louvain or Unicom. The payment terminal associated network can be divided into at least one community. How to divide the payment terminal associated network into the payment terminal community through the community partitioning algorithm can refer to the existing technology and will not be described in detail here.

[0084] The first community and the second community are communities corresponding to the same payment terminal in different transaction time intervals. For example, the transaction time of the payment transaction data can be divided to obtain the payment terminal associated network corresponding to the different transaction time intervals, and the payment terminal associated network can be divided into communities to obtain the first community and the second community. Alternatively, after generating the payment terminal associated network, the transaction data can be divided by the transaction time to obtain the first community and the second community belonging to different transaction time intervals.

[0085] The different transaction time intervals may be adjacent different transaction time intervals, for example, the first community is the community where the A payment terminal with transaction time in August is located, and the second community is the community where the A payment terminal with transaction time in July is located. Alternatively, the different transaction time intervals may also be non-adjacent different transaction time intervals, for example, the first community is the community where the A payment terminal with transaction time in August is located, and the second community is the community where the A payment terminal with transaction time in May is located.

[0086] In a possible implementation, the community of the payment terminal may be information obtained from other data processing devices to complete community division. The other data processing devices may construct a payment terminal association network and divide the community according to the method described above.

[0087] Another possible implementation method is to first obtain the payment transaction data of the payment terminal, then generate a payment terminal associated network by processing the payment transaction data, and divide the above-mentioned community from the payment terminal associated network.

[0088] S102: Determine whether the first community and / or the second community includes an abnormal payment terminal according to the similarity between the first community and the second community.

[0089] Optionally, the similarity between the first community and the second community may be determined according to the similarity of payment terminals included in the two communities, for example.

[0090] Optionally, the similarity between the first community and the second community may also be determined according to the similarity between the topological structure of the first community and the topological structure of the second community.

[0091] If the similarity between the first community and the second community is high, it can be considered that the payment terminals in the first community and the second community are relatively stable in different transaction time intervals, that is, it can be further considered that the payment terminals in the two communities and the distances between the payment terminals (further implying the locations of the payment terminals) are stable, and there are no abnormal transaction behaviors (for example, there are no payment terminals with large location changes in the community). Therefore, it can be considered that there are no abnormal payment terminals in the first community and the second community.

[0092] If the similarity between the first community and the second community is low, it can be considered that the payment terminals in the first community and the second community are unstable in different transaction time intervals, that is, it can be further considered that the payment terminals in the two communities and the distances between the payment terminals (further implying the locations of the payment terminals) are unstable, and there may be abnormal transaction behaviors (for example, there may be payment terminals with large location changes in the community). Therefore, it can be considered that there are abnormal payment terminals in the first community and the second community.

[0093] S103: If an abnormal payment terminal is included, output the abnormal payment terminal.

[0094] If it is determined that the first community and / or the second community include abnormal payment terminals, the payment terminals included in the first community and / or the second community can be considered as abnormal payment terminals, and the payment terminals included in the first community and the second community can be output so that the staff can further check the payment terminals included in the first community and / or the second community to determine and handle the abnormal payment terminals.

[0095] Alternatively, if it is determined that the first community and / or the second community include abnormal payment terminals, payment terminals that may be abnormal can be further determined from the payment terminals included in the first community and / or the second community, and used as abnormal payment terminals. For example, payment terminals that cause a decrease in similarity in the first community and the second community can be used as abnormal payment terminals, and the determined abnormal payment terminals can be output. Alternatively, payment terminals with abnormal location information can be determined from the first community and / or the second community as abnormal payment terminals based on the location information of the payment terminals.

[0096] The method provided in the embodiment of the present application obtains the first community and the second community of the payment terminal from the payment terminal association network, and determines whether there is a large difference between the first community and the second community in different transaction time intervals based on the similarity between the first community and the second community. Since the payment terminal in the present application is a payment terminal whose transaction location is not easy to change, if the similarity between the first community and the second community is low, it indicates that the location of the payment terminal in the two communities has changed, so it can be considered that there is an abnormal payment terminal among the payment terminals included in the two communities, thereby improving the efficiency and accuracy of identifying abnormal payment terminals.

[0097] Next, taking the similarity of payment terminals included in two communities as an example, how to determine whether the first community and / or the second community includes an abnormal payment terminal according to the similarity between the first community and the second community in the aforementioned step S102 is described in detail. Figure 2 A flow chart of another payment terminal identification method provided in an embodiment of the present application. Figure 2 As shown, the aforementioned step S102 may further include:

[0098] S201. Acquire the same first payment terminal in the first community and the second community.

[0099] According to the payment terminals included in the first community and the payment terminals included in the second community, a first payment terminal that belongs to both the first community and the second community is determined. For example, the nodes in the payment terminal association network are represented by the identifiers of the payment terminals. Then, the identifiers of the payment terminals in the first community and the identifiers of the payment terminals in the second community can be used to determine the payment terminals with the same identifiers as the first payment terminals.

[0100] The method for determining the first payment terminal may be, for example, traversing the identifiers of the payment terminals in the first community and the identifiers of the payment terminals in the second community, and then performing identifier comparison to determine the first payment terminal.

[0101] S202: Determine the similarity between the first community and the second community according to the first payment terminal.

[0102] In a possible implementation, the similarity can be determined by the proportion of the first payment terminal in the payment terminals included in the first community and the second community. For example, the proportion of the first payment terminal can be determined based on the number of the first payment terminal and the number of all payment terminals included in the first community and the second community to determine the similarity between the first community and the second community. Alternatively, the proportion of the first payment terminal can be determined based on the number of the first payment terminal and the number of all payment terminals included in the first community and the second community except the first payment terminal to determine the similarity between the first community and the second community.

[0103] Taking the example of determining the proportion of the first payment terminals according to the number of the first payment terminals and the number of all payment terminals included in the first community and the second community to determine the similarity between the first community and the second community, step S202 may be implemented by the following sub-steps:

[0104] S2021. Obtain a second payment terminal.

[0105] The second payment terminal includes all payment terminals in the first community and all payment terminals in the second community. The second payment terminal can be, for example, a payment terminal with different identifications determined by using identifications of payment terminals in the first community and identifications of payment terminals in the second community as the second payment terminal.

[0106] S2022: Obtain similarity between the first community and the second community according to the first payment terminal and the second payment terminal.

[0107] According to the first payment terminal and the second payment terminal, the proportion of the number of the first payment terminal in the number of the second payment terminal is determined, and the proportion is used as the similarity between the first community and the second community. For example, if the number of the first payment terminal is 800 and the number of the second payment terminal is 1000, then the proportion of the number of the first payment terminal in the number of the second payment terminal is 80%, and the similarity between the first community and the second community is also 80%.

[0108] Another possible implementation method is to directly determine the similarity between the first community and the second community based on the number of first payment terminals and the mapping relationship between the number of first payment terminals and the similarity. The mapping relationship can be preset according to actual needs, and this application does not limit this. For example, if the number of first payment terminals is 800, and by querying the mapping relationship, it is determined that the similarity corresponding to the 800 first payment terminals in the mapping relationship is 80%, then it can be determined that the similarity between the first community and the second community is 80%.

[0109] S203: If the similarity is less than or equal to a first preset similarity threshold, determine that the first community and / or the second community includes an abnormal payment terminal.

[0110] The first preset similarity threshold may be determined according to actual needs, and the present application does not impose any limitation thereto. For example, the first preset similarity threshold may be set to 90%.

[0111] If the similarity between the first community and the second community determined by the method of the aforementioned step S102 is less than or equal to the first preset similarity threshold, it indicates that the similarity between the first community and the second community is low, and the payment terminals in the first community and the second community are unstable in different transaction time intervals, that is, it can be further characterized that the payment terminals in the two communities and the distances between the payment terminals (further implying the locations of the payment terminals) are unstable, and there may be abnormal transaction behaviors (for example, there may be payment terminals with large location changes in the community). Therefore, it is considered that there are abnormal payment terminals in the first community and / or the second community.

[0112] For example, assume that the community to which the payment terminal M belongs in August is A (i.e., the first community), and the number of merchants in community A is Q, and the community to which the payment terminal M belongs in July is B (i.e., the second community), and the number of merchants in community B is P. Then, the similarity J between the first community and the second community to which the payment terminal M belongs at different times is as shown in the following formula (2):

[0113]

[0114] Where A∩B represents the intersection of payment terminals in communities A and B, i.e., the first payment terminal. A∪B represents the union of merchants in communities A and B, i.e., the second payment terminal. For example, Figure 3 A community diagram provided in an embodiment of the present application. Figure 3 As shown, the payment terminal M may be, for example, a node numbered 1, and other nodes are other payment terminals associated with the payment terminal M. In different transaction time intervals, the structure of the community to which the payment terminal M belongs is different.

[0115] By using the above formula (2), the similarity between the first community and the second community can be calculated, and it can be determined whether there is an abnormal payment terminal in the first community and / or the second community based on the similarity.

[0116] The method provided in the embodiment of the present application determines the similarity between the first community and the second community based on the first payment terminal by obtaining the same first payment terminal in the first community and the second community. If the similarity between the first community and the second community is less than or equal to the first preset similarity threshold, it is determined that the first community and / or the second community include an abnormal payment terminal. The method of the present application can determine whether the first community and / or the second community includes an abnormal payment terminal by measuring the degree of change of the payment terminals included in the community in different transaction time intervals without obtaining the location of the payment terminal, thereby increasing the efficiency of identifying abnormal payment terminals, reducing the difficulty of data collection, and improving the accuracy of identifying abnormal payment terminals.

[0117] Next, taking the similarity between the topological structure of the first community and the topological structure of the second community as an example, how to determine whether the first community and / or the second community includes an abnormal payment terminal according to the similarity between the first community and the second community in the aforementioned step S102 is described in detail. Figure 4 A flow chart of another payment terminal identification method provided in an embodiment of the present application. Figure 4 As shown, the aforementioned step S102 may further include:

[0118] S401. Generate a first embedding vector of the first community according to the graph embedding representation of the first community.

[0119] The first community can be processed by algorithms such as SimGNN and Graph Kernel to generate an embedded representation of the topological graph structure corresponding to the first community. The embedded representation is represented in the form of an embedded vector. For example, assuming that the first community is community C, and the community C includes x payment terminals, the vector of the community C can be represented as an x-dimensional vector as shown in the following formula (3):

[0120] V(C)=[a1,a 2, …,a x ] (3)

[0121] Among them, a x is the vector corresponding to the xth payment terminal in the first community, and V(C) is the first embedding vector of the C community.

[0122] How to process the first community through algorithms such as SimGNN and Graph Kernel to obtain a graph embedding representation of the first community can be referred to the prior art, and this application will not elaborate on this.

[0123] S402: Generate a second embedding vector for the second community according to the graph embedding representation of the second community.

[0124] According to the method of the aforementioned step S401, the second community can be processed in the same way to generate a graph embedding representation corresponding to the second community, and to generate a second embedding vector for the second community, which will not be described again here. The difference between this step and the aforementioned step S301 is that the processing object is switched from the first community to the second community.

[0125] For example, assuming that the first community is community D, and community D includes y payment terminals, the vector of community D can be expressed as a y-dimensional vector as shown in the following formula (4):

[0126] V(D)=[b1,b 2, …,b y ] (4)

[0127] Among them, b y is the vector corresponding to the yth payment terminal in the second community, and V(D) is the second embedding vector of the D community.

[0128] S403: If the similarity between the first embedding vector and the second embedding vector is less than or equal to a second preset similarity threshold, determine that the first community and / or the second community includes an abnormal payment terminal.

[0129] The similarity between the topological structures of the first community and the second community is characterized by calculating the similarity between the first embedding vector and the second embedding vector. The method for calculating the similarity between the first embedding vector and the second embedding vector can be calculated, for example, by algorithms such as cosine similarity or Pearson correlation coefficient, and the present application does not limit the specific similarity algorithm.

[0130] For example, continuing with the examples in the aforementioned step S401 and the aforementioned step S402, the similarity S(C, D) between V(C) and V(D) may be calculated.

[0131] If the value of the similarity between the first embedding vector and the second embedding vector (for example, S(C, D)) is larger, the similarity between the topological structures of the first community and the second community is higher, further indicating that the stability of the payment terminals included in the first community and the second community is higher, and the probability of abnormal payment terminals is lower. Conversely, if the value of the similarity between the first embedding vector and the second embedding vector (for example, S(C, D)) is smaller, the similarity between the topological structures of the first community and the second community is lower, further indicating that the stability of the payment terminals included in the first community and the second community is lower, and the probability of abnormal payment terminals is higher.

[0132] By setting a second preset similarity threshold, the similarity between the first embedding vector and the second embedding vector is compared with the second preset similarity threshold. If the similarity between the first embedding vector and the second embedding vector is less than or equal to the second preset similarity threshold, it indicates that the topological structure similarity between the first community and the second community is low, further indicating that the stability of the payment terminals included in the first community and the second community is low, and the probability of abnormal payment terminals appearing is high.

[0133] The method provided in the embodiment of the present application processes the first community and the second community as graph embedding representations, obtains the embedding vectors of the first community and the second community, calculates the vector similarity based on the corresponding embedding vectors of the two, so as to obtain the similarity between the first community and the second community in the topological structure, and determines the stability of the community structure based on the comparison between the similarity and the second preset similarity threshold. Since the first community and the second community are communities corresponding to the same payment terminal in different transaction time intervals, if the community structure is unstable, it indicates that the payment terminal has abnormal behavior in the two transaction time intervals. The method of the present application determines whether the first community and / or the second community include abnormal payment terminals by analyzing the stability of the community topological structures of the first community and the second community corresponding to the payment terminal in different transaction time intervals, thereby increasing the efficiency of identifying abnormal payment terminals, reducing the difficulty of data collection, and improving the accuracy of identifying abnormal payment terminals.

[0134] Furthermore, after determining whether the first community and / or the second community includes an abnormal payment terminal based on the similarity between the first community and the second community, if the payment terminal association network also includes the location information of the payment terminal, it is possible to further determine whether the first community and / or the second community includes an abnormal payment terminal in combination with the location information, so as to further improve the recognition accuracy of the abnormal payment terminal. The location information of the payment terminal may be, for example, the registered transaction location of the payment terminal, the transaction location of the payment terminal, etc.

[0135] Figure 5 A flowchart of another payment terminal identification method provided in an embodiment of the present application. Figure 5 As shown, after determining whether the first community and / or the second community includes an abnormal payment terminal, the method may further include:

[0136] S501. Determine the dispersion of payment terminals in the first community and / or the second community according to location information of the payment terminals.

[0137] A possible implementation method is to determine the dispersion of payment terminals in the first community and / or the second community by the number of geographical grids where the payment terminals are located. The geographical grid may be preset according to actual needs. For example, it is assumed that the payment terminal association network is divided into a plurality of square geographical grids. The first community contains 100 payment terminals, and the location information of these payment terminals is obtained. With each payment terminal as the center, a circle is drawn with a fixed radius (e.g., 1 km), and the number of different geographical grid areas covered by each circle is counted. For example, the circle of 50 payment terminals covers 1 grid area, the circle of 30 payment terminals covers 2 grid areas, and the circle of 20 payment terminals covers 3 grid areas. Then, the number of geographical grids is used as the weight to calculate the average number of areas covered by each payment terminal, that is, (50×1+30×2+20×3)=1.7, and the average value can be used as a measure of the dispersion of the payment terminal.

[0138] Another possible implementation is to determine the dispersion of payment terminals in the first community and / or the second community according to the arrangement of the number of payment terminals included in each area. Specifically, this implementation can be implemented through the following sub-steps:

[0139] S5011. Obtain location information of a payment terminal in the first community and / or the second community.

[0140] The location information of the payment terminal belonging to the first community and / or the second community can be obtained from the database storing the payment terminal information. The location information can be, for example, the aforementioned payment terminal transaction location, payment terminal registration transaction location, etc.

[0141] Optionally, the location information may be converted into information including geographical area divisions. For example, the location information may be converted into information in the geographical area division format of X province X city X area, so as to facilitate subsequent division of the area described in the location information.

[0142] S5012. Determine the payment terminals included in each area according to the area to which the location information belongs.

[0143] For example, the area may be divided first, and then all payment terminals in each area may be determined. Alternatively, other payment terminals that also belong to the area may be determined based on the location information of each payment terminal.

[0144] By traversing the location information corresponding to all payment terminals, the sets of all areas where these payment terminals are located are determined, and all payment terminals included in each area set are determined.

[0145] S5013. Arrange the payment terminals according to the number of the payment terminals included in each area, and generate payment terminal location distribution data.

[0146] According to the number of payment terminals included in each area, each area is arranged in ascending order or descending order to generate payment terminal location distribution data.

[0147] For example, a payment terminal location distribution data provided by an embodiment of the present application may be shown in the following Table 1:

[0148] Table 1

[0149] Province city district Number of merchants Ranking Proportion Province 1 City 2 Zone 4 43 1 43％ Province 2 City 4 Zone 3 27 2 27％ Province 3 City 6 Zone 2 16 3 16％ Province 4 City 1 Zone 4 11 4 11％ Province 4 City 8 Zone 1 3 5 3％

[0150] S5014. Determine the dispersion of payment terminals in the first community and / or the second community according to the number of payment terminals in the first area.

[0151] Among them, the first area is the area with the largest number of payment terminals. Continuing with the above Table 1 as an example, the first area is the geographical area corresponding to Province 1 City 2 District 4.

[0152] In a possible implementation, the dispersion of payment terminals in the first community and / or the second community may be determined based on the proportion of the number of payment terminals in the first area to the number of payment terminals in all areas. That is, the dispersion of payment terminals in the community in the example of Table 1 is 43%.

[0153] In another possible implementation, the dispersion of payment terminals in the first community and / or the second community may be determined based on the ratio of the number of payment terminals in the first area to the sum of the number of payment terminals in other areas. That is, the dispersion of payment terminals in the community in the example of Table 1 is 43 / 57=75.4%.

[0154] If the payment terminal discreteness is greater than or equal to the preset discreteness threshold, it indicates that the payment terminals in the first community and / or the second community are scattered in multiple areas, and there are abnormal transaction behaviors, and step S502 is executed; if the payment terminal discreteness is less than the preset discreteness threshold, it indicates that most of the payment terminals in the first community and / or the second community are located in the same area, and there may be no abnormal transaction behaviors, and step S503 is executed.

[0155] The preset discreteness threshold may be determined according to actual needs. For example, the preset discreteness threshold is determined according to the recognition laxity of abnormal payment terminals and / or the calculation method of the discreteness of payment terminals.

[0156] For example, when the payment terminal dispersion in the first community and / or the second community can be based on the proportion of the number of payment terminals in the first area to the number of payment terminals in all areas, the preset dispersion threshold can be set to 50%, for example. When the payment terminal dispersion in the first community and / or the second community can be based on the proportion of the number of payment terminals in the first area to the sum of the number of payment terminals in other areas, the preset dispersion threshold can be set to 100%, for example. Alternatively, those skilled in the art can further adjust the preset dispersion threshold according to the required identification leniency of abnormal payment terminals, and this application does not limit this.

[0157] S502: Determine whether the first community and / or the second community includes an abnormal payment terminal.

[0158] S503: Acquire, from the payment terminal location distribution data, a third payment terminal whose distance from the first area is greater than or equal to a preset distance threshold.

[0159] When the payment terminal discreteness is less than the preset discreteness threshold, it indicates that most of the payment terminals in the first community and / or the second community are located in the same area (i.e., the locations are concentrated). At this time, the locations of most payment terminals are normal, and there is no abnormal transaction behavior. However, if the distances between the multiple areas included in the payment terminal location distribution data are far, and the association between payment terminals belonging to the same community depends on the aforementioned t duration, under the limitation of t duration, there will usually not be two payment terminals with a long distance between their locations. Therefore, when the payment terminal discreteness is less than the preset discreteness threshold, further identifying abnormal payment terminals by the location of the payment terminal can further improve the recognition accuracy of abnormal payment terminals.

[0160] In a possible implementation, it is possible to determine whether the distance between the location information and the first area is greater than or equal to a preset distance threshold based on the location information of the payment terminals in other areas outside the first area. If greater than, it is considered that these payment terminals are third payment terminals, which are far away from the first area, have abnormal transaction behavior, and are abnormal payment terminals.

[0161] Another possible implementation is to obtain a second area whose distance from the first area is greater than or equal to a preset distance threshold from the payment terminal location distribution data, where the second area is the area other than the first area in the payment terminal location distribution data. If the second area exists, the payment terminal whose location belongs to the second area is determined to be the third payment terminal. In this implementation, the third payment terminal is determined based on the distance between the areas. If the distance between the second area and the first area is greater than or equal to the preset distance threshold, it indicates that the payment terminal in the second area has abnormal transaction behavior and is an abnormal payment terminal.

[0162] S504: Determine the third payment terminal as an abnormal payment terminal.

[0163] The method provided in the embodiment of the present application determines the dispersion of payment terminals in the first community and / or the second community through the location information of the payment terminal. If the dispersion of the payment terminal is greater than or equal to the preset dispersion threshold, it indicates that the payment terminals in the first community and the second community are scattered in multiple areas and there are abnormal transaction behaviors. If the dispersion of the payment terminal is less than the preset dispersion threshold, it is further determined based on the location information of the payment terminal whether there is a third payment terminal whose distance from the first area is greater than or equal to the preset distance threshold. If there is, the third payment terminal is determined as an abnormal payment terminal, thereby improving the accuracy of identifying abnormal payment terminals.

[0164] In addition, if the payment terminal association network also includes the location information of the payment terminal, the method of the present application can also directly identify abnormal payment terminals based on the location information, that is, there is no need to perform community similarity comparison, and the dispersion of payment terminals in a community can be determined directly based on the location information of the payment terminals in the community to identify whether there are abnormal payment terminals in the community.

[0165] Figure 6 A flowchart of another payment terminal identification method provided in an embodiment of the present application. Figure 6 As shown, the method may also include:

[0166] S601. Obtain the community of the payment terminal.

[0167] The method for obtaining the community of the payment terminal can refer to the aforementioned step S101, which will not be described in detail here. The difference between the method for obtaining the community of the payment terminal in this step and the method in the aforementioned step S101 is that the community includes the location information of the payment terminal.

[0168] S602: Determine the dispersion of payment terminals in the first community and / or the second community according to the location information of the payment terminals.

[0169] This step may refer to the aforementioned step S501 and will not be described in detail here.

[0170] S603: If the payment terminal dispersion is greater than or equal to a preset dispersion threshold, determine that the first community and / or the second community includes an abnormal payment terminal.

[0171] If the discreteness of the payment terminals is greater than or equal to the preset discreteness threshold, it indicates that the payment terminals in the first community and / or the second community are scattered in multiple areas and there are abnormal transaction behaviors, and the payment terminals included in the first community and / or the second community are determined as abnormal payment terminals.

[0172] If the discreteness of the payment terminal is less than the preset discreteness threshold, it indicates that most of the payment terminals in the first community and / or the second community are located in the same area, and there may be no abnormal transaction behavior. Optionally, the payment terminals in the first community and / or the second community that are not abnormal transaction terminals can be directly output. Or, optionally, it can be further determined according to the method in the aforementioned step S503 whether there are payment terminals in other areas in the first community and / or the second community whose distance from the first area is greater than or equal to the preset distance threshold. If so, the transaction terminals in other areas whose distance from the first area is greater than or equal to the preset distance threshold are determined as abnormal payment terminals; if not, the payment terminals in the first community and / or the second community that are not abnormal transaction terminals can be directly output.

[0173] S604: Output abnormal payment terminal.

[0174] The method provided in the embodiment of the present application obtains the community of the payment terminal and the location information of the payment terminal when the location information of the payment terminal can be obtained, and determines the discreteness of the payment terminals in the first community and / or the second community based on the location information of the payment terminal. If the discreteness of the payment terminals is greater than or equal to a preset discreteness threshold, it is determined that the first community and / or the second community includes abnormal payment terminals, and the abnormal payment terminals are output, thereby improving the efficiency of identifying abnormal payment terminals based on location information.

[0175] Figure 7 This is a schematic diagram of the structure of a payment terminal identification device provided in an embodiment of the present application. Figure 7 As shown, the payment terminal identification device may include: an acquisition module 11, a processing module 12, and an output module 13.

[0176] An acquisition module 11 is used to acquire a community of a payment terminal, the community belongs to a payment terminal associated network corresponding to the payment terminal, the payment terminal associated network is generated according to payment transaction data of the payment terminal, the community includes a first community and a second community, and the transaction time intervals of the payment transaction data corresponding to the first community and the second community are different;

[0177] A processing module 12, configured to determine whether the first community and / or the second community includes an abnormal payment terminal according to the similarity between the first community and the second community;

[0178] The output module 13 is used to output the abnormal payment terminal when the abnormal payment terminal is included.

[0179] Optionally, the processing module 12 is specifically used to obtain the same first payment terminal in the first community and the second community; determine the similarity between the first community and the second community based on the first payment terminal; if the similarity is less than or equal to a first preset similarity threshold, determine that the first community and / or the second community includes the abnormal payment terminal.

[0180] Optionally, the processing module 12 is specifically configured to: obtain a second payment terminal; and obtain the similarity between the first community and the second community according to the first payment terminal and the second payment terminal, wherein the second payment terminal includes all payment terminals in the first community and all payment terminals in the second community.

[0181] Optionally, the processing module 12 is specifically used to: generate a first embedding vector of the first community based on the graph embedding representation of the first community; generate a second embedding vector of the second community based on the graph embedding representation of the second community; if the similarity between the first embedding vector and the second embedding vector is less than or equal to a second preset similarity threshold, determine that the first community and / or the second community includes the abnormal payment terminal.

[0182] In a possible implementation, when the location information of the payment terminal is included in the payment terminal association network, the processing module 12, after determining whether the first community and / or the second community includes an abnormal payment terminal based on the similarity between the first community and the second community, is further used to: determine the dispersion of payment terminals in the first community and / or the second community based on the location information of the payment terminal; if the dispersion of the payment terminals is greater than or equal to a preset dispersion threshold, determine that the first community and / or the second community includes the abnormal payment terminal.

[0183] Optionally, the processing module 12 is specifically used to: obtain location information of payment terminals in the first community and / or the second community; determine the payment terminals included in each area according to the area to which the location information belongs; arrange the payment terminals according to the number of payment terminals included in each area to generate payment terminal location distribution data; determine the dispersion of payment terminals in the first community and / or the second community according to the number of payment terminals in the first area, the first area being the area with the largest number of payment terminals.

[0184] Optionally, when the discreteness of the payment terminal is less than a preset discreteness threshold, the processing module 12 is further used to: obtain from the payment terminal location distribution data a third payment terminal whose location is greater than or equal to a preset distance threshold from the first area; and determine the third payment terminal as the abnormal payment terminal.

[0185] In this implementation, optionally, the processing module 12 is specifically configured to: obtain from the payment terminal location distribution data a second area whose distance from the first area is greater than or equal to the preset distance threshold; if the second area exists, determine that the payment terminal located within the second area is the third payment terminal. The second area is an area in the payment terminal location distribution data other than the first area.

[0186] In another possible implementation, when the location information of the payment terminal is included in the payment terminal association network, the acquisition module 11 is further used to obtain the community of the payment terminal; the processing module 12 is further used to determine the dispersion of the payment terminals in the first community and / or the second community based on the location information of the payment terminal; if the dispersion of the payment terminals is greater than or equal to a preset dispersion threshold, it is determined that the first community and / or the second community includes the abnormal payment terminal; the output module 13 is further used to output the abnormal payment terminal.

[0187] Optionally, the weight of any edge in the payment terminal association network is related to the transaction time interval between two nodes corresponding to the edge.

[0188] Optionally, the weight of any edge in the payment terminal association network is related to the minimum transaction time interval between two nodes corresponding to the edge and a preset duration, and the preset duration is used to determine whether there is an association between two nodes in the payment terminal association network based on the payment transaction data.

[0189] The payment terminal identification device provided in the embodiment of the present application can execute the payment terminal identification method in the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated here.

[0190] Figure 8 The following is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device is used to execute the payment terminal identification method mentioned above, for example, it can be the terminal device with data processing function mentioned above. Figure 8 As shown, the electronic device 800 may include: at least one processor 801 , a memory 802 , and a communication interface 803 .

[0191] The memory 802 is used to store programs. Specifically, the programs may include program codes, and the program codes include computer operation instructions.

[0192] The memory 802 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0193] The processor 801 is used to execute the computer-executable instructions stored in the memory 802 to implement the method described in the above method embodiment. The processor 801 may be a CPU, or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0194] The processor 801 can communicate and interact with external devices through the communication interface 803. The external device can be, for example, the device where the aforementioned database is located. In a specific implementation, if the communication interface 803, the memory 802, and the processor 801 are implemented independently, the communication interface 803, the memory 802, and the processor 801 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc., but it does not mean that there is only one bus or one type of bus.

[0195] Optionally, in a specific implementation, if the communication interface 803, the memory 802 and the processor 801 are integrated on a chip, the communication interface 803, the memory 802 and the processor 801 can communicate through an internal interface.

[0196] The present application also provides a computer-readable storage medium, which may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes. Specifically, the computer-readable storage medium stores program instructions, and the program instructions are used for the methods in the above embodiments.

[0197] The present application also provides a program product, which includes an execution instruction, which is stored in a readable storage medium. At least one processor of a computing device can read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the computing device implements the payment terminal identification method.

[0198] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A payment terminal identification method, characterized in that: The method comprises: Acquire a community of the payment terminal, the community belonging to a payment terminal associated network corresponding to the payment terminal, the payment terminal associated network generated according to payment transaction data of the payment terminal, the community including a first community and a second community, the transaction time intervals of the payment transaction data corresponding to the first community and the second community being different; determining, according to the similarity between the first community and the second community, whether the first community and / or the second community includes an abnormal payment terminal; If the abnormal payment terminal is included, the abnormal payment terminal is output.

2. The method according to claim 1, characterized in that The determining, based on the similarity between the first community and the second community, whether the first community and / or the second community includes an abnormal payment terminal includes: Acquire the same first payment terminal in the first community and the second community; determining, according to the first payment terminal, a similarity between the first community and the second community; If the similarity is less than or equal to a first preset similarity threshold, it is determined that the first community and / or the second community includes the abnormal payment terminal.

3. The method according to claim 2, characterized in that The determining, according to the first payment terminal, the similarity between the first community and the second community includes: Acquire a second payment terminal, where the second payment terminal includes all payment terminals in the first community and all payment terminals in the second community; The similarity between the first community and the second community is obtained according to the first payment terminal and the second payment terminal.

4. The method according to claim 1, characterized in that: The determining, based on the similarity between the first community and the second community, whether the first community and / or the second community includes an abnormal payment terminal includes: generating a first embedding vector for the first community according to the graph embedding representation of the first community; generating a second embedding vector for the second community according to the graph embedding representation of the second community; If the similarity between the first embedding vector and the second embedding vector is less than or equal to a second preset similarity threshold, it is determined that the first community and / or the second community includes the abnormal payment terminal.

5. The method according to any one of claims 1 to 4, characterized in that: The payment terminal association network includes location information of the payment terminal. After determining whether the first community and / or the second community includes an abnormal payment terminal based on the similarity between the first community and the second community, the method further includes: determining, according to the location information of the payment terminal, a dispersion degree of the payment terminals in the first community and / or the second community; If the payment terminal dispersion is greater than or equal to a preset dispersion threshold, it is determined that the first community and / or the second community includes the abnormal payment terminal.

6. The method according to claim 5, characterized in that The determining, according to the location information of the payment terminal, the dispersion of the payment terminals in the first community and / or the second community includes: Acquire location information of payment terminals in the first community and / or the second community; Determining payment terminals included in each area according to the area to which the location information belongs; Arrange the payment terminals according to the number of the payment terminals included in each of the areas to generate payment terminal location distribution data; The dispersion of payment terminals in the first community and / or the second community is determined according to the number of payment terminals in a first area, the first area being an area with the largest number of payment terminals.

7. The method according to claim 6, characterized in that If the discreteness of the payment terminal is less than a preset discreteness threshold, the method further includes: Acquire, from the payment terminal location distribution data, a third payment terminal whose distance from the first area is greater than or equal to a preset distance threshold; The third payment terminal is determined as the abnormal payment terminal.

8. The method according to claim 7, characterized in that The acquiring, from the payment terminal location distribution data, a third payment terminal whose location is greater than or equal to a preset distance threshold from the first area comprises: Acquire, from the payment terminal location distribution data, a second area whose distance from the first area is greater than or equal to the preset distance threshold, the second area being an area in the payment terminal location distribution data other than the first area; If the second area exists, the payment terminal whose location is within the second area is determined to be the third payment terminal.

9. The method according to claim 1, characterized in that: The payment terminal association network includes location information of the payment terminal, and the method further includes: Acquire the community of the payment terminal; determining, according to the location information of the payment terminal, a dispersion degree of the payment terminals in the first community and / or the second community; If the payment terminal dispersion is greater than or equal to a preset dispersion threshold, determining that the first community and / or the second community includes the abnormal payment terminal; The abnormal payment terminal is output.

10. The method according to any one of claims 1 to 4 or 6 to 9, characterized in that: The weight of any edge in the payment terminal association network is related to the transaction time interval between two nodes corresponding to the edge.

11. The method according to claim 10, characterized in that The weight of any edge in the payment terminal association network is related to the minimum transaction time interval between two nodes corresponding to the edge and a preset duration, and the preset duration is used to determine whether there is an association between two nodes in the payment terminal association network based on the payment transaction data.

12. A payment terminal identification device, characterized in that: include: an acquisition module, configured to acquire a community of a payment terminal, wherein the community belongs to a payment terminal associated network corresponding to the payment terminal, the payment terminal associated network being generated according to payment transaction data of the payment terminal, the community comprising a first community and a second community, and the transaction time intervals of the payment transaction data corresponding to the first community and the second community being different; a processing module, configured to determine whether the first community and / or the second community includes an abnormal payment terminal according to the similarity between the first community and the second community; An output module is used to output the abnormal payment terminal if the abnormal payment terminal is included.

13. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the payment terminal identification method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 11 when being executed by a processor.

Images