Abnormal payment marking derivation method, system, device and storage medium

Abstract

The present application discloses a method and system for deriving marks of abnormal payments, the method comprising: a seed mark generation step: constructing a set including at least one abnormal payment account, and setting a seed mark for the abnormal payment account; a mark derivation step: based on the usage relationship, passing the seed mark of the abnormal payment account to at least one user who has used the abnormal payment account, and generating an abnormal user carrying the seed mark; a derivation iteration step: based on the usage relationship, passing the seed mark of the abnormal user to at least one abnormal payment account used by the abnormal user, and cyclically continuing to execute the mark derivation step and the derivation iteration step until the iteration stop condition is met, and completing the mark derivation of the abnormal user and the abnormal payment account. The method of the present invention accurately strikes malicious purchases of abnormal payments through mark derivation.

Description

Technical Field

[0001] The present application relates to the field of information query, and in particular to a method, system, computer device and computer-readable storage medium for deriving a mark of an abnormal payment. Background Art

[0002] At present, with the vigorous development of electronic payment networks, while facilitating daily life, it also provides opportunities for criminals to take advantage of. Take Internet payment as an example. Due to its large transaction volume and imperfect monitoring methods, it is easy for criminals to hide behind payment operations and complete illegal activities such as swiping orders and snatching tickets.

[0003] In particular, although the railway capacity has been greatly improved, which has largely alleviated the problem of ticket shortage, there are still situations where the capacity of popular routes and popular time periods cannot meet the travel needs of passengers, and the contradiction between supply and demand still exists to a certain extent. As a result, multiple malicious ticket grabbing platforms have emerged, which has brought great pressure to the railway Internet ticketing system and affected the fairness of users' ticket purchases. In order to maintain a fair, just and stable ticket purchasing environment, it is necessary to crack down on users who purchase tickets through unofficial channels. Given that users will make payments after booking tickets, the payment behavior will associate the user name with the bank account. For abnormal payment ticket purchases, the same payment account may be used to pay for multiple users. Therefore, the relationship between users and payment accounts is used to mark malicious payment accounts, and malicious payments are precisely cracked down through marked payment accounts.

[0004] The present invention provides a solution to the derivation of abnormal payment marks based on usage relationships, which enables the output of attribute marks of a large number of payment accounts from a small number of marked payment accounts through a mark derivation algorithm; at the same time, it mainly solves the problem of distinguishing payment account usage channels, and can increase the number of marked payment accounts from thousands to hundreds of millions, providing better data support for combating abnormal payments in the black and gray industries. Summary of the invention

[0005] The embodiment of the present application provides a solution to the derivation of abnormal payment tags based on usage relationships, which realizes the output of attribute tags of a large number of payment accounts using a small number of tagged payment accounts through a tag derivation algorithm; at the same time, it mainly solves the problem of distinguishing payment account usage channels.

[0006] In a first aspect, an embodiment of the present application provides a method for deriving a mark of an abnormal payment, including:

[0007] Seed mark generation step: constructing a set including at least one abnormal payment account, and setting a seed mark for the abnormal payment account;

[0008] Mark derivation step: based on the usage relationship, the seed mark of the abnormal payment account is transmitted to at least one user who has used the abnormal payment account, and an abnormal user carrying the seed mark is generated;

[0009] Derivative iterative step: Based on the usage relationship, the seed tag of the abnormal user is passed to at least one abnormal payment account used by the abnormal user, and the tag derivation step and the derivative iterative step are continuously executed in a loop until the iteration stop condition is met, thereby completing the tag derivation of the abnormal user and the abnormal payment account.

[0010] In some embodiments, the above-mentioned abnormal payment marking derivation method further includes:

[0011] Correction steps: Correct the seed marks of abnormal users and abnormal payment accounts, and output the final abnormal users and abnormal payment accounts.

[0012] In some embodiments, the marker derivatization step comprises:

[0013] Account weight ratio calculation steps: Calculate the weight ratio of the abnormal payment account to each purchase channel;

[0014] User weight score calculation steps: According to the weight ratio of each purchase channel of the abnormal payment account and the weight of the usage relationship between the abnormal payment account and the user, calculate the user's score for each purchase channel, determine the user's tag based on the channel score, and generate an abnormal user with a seed tag.

[0015] In some embodiments, the above-mentioned derivation iteration step includes:

[0016] User weight ratio calculation steps: Calculate the weight ratio of abnormal users belonging to each purchase channel;

[0017] Account weight score calculation steps: According to the weight ratio of each purchase channel of the abnormal user and the weight of the usage relationship between the abnormal user and the payment account, calculate the score of the payment account belonging to each channel, determine the tag of the payment account according to the channel score, and generate an abnormal payment account with a seed tag.

[0018] In some embodiments, the above-mentioned correction step includes:

[0019] Payment account correction step: perform statistical comparison between normal payment accounts and abnormal payment accounts, and complete the correction of abnormal payment accounts;

[0020] User correction step: Correct abnormal users based on the probability that they belong to normal purchasing channels.

[0021] In a second aspect, an embodiment of the present application provides a system for deriving a mark of an abnormal payment, which adopts the method for deriving a mark of an abnormal payment as described above, including:

[0022] A seed mark generation module: constructs a set including at least one abnormal payment account, and sets a seed mark for the abnormal payment account;

[0023] A tag derivation module: based on the usage relationship, the seed tag of the abnormal payment account is transferred to at least one user who has used the abnormal payment account, and an abnormal user carrying the seed tag is generated;

[0024] Derivative iteration module: Based on the usage relationship, the seed tag of the abnormal user is passed to at least one abnormal payment account used by the abnormal user, and the tag derivation module and the derivative iteration module are executed in a loop until the iteration stop condition is met, thereby completing the tag derivation of the abnormal user and the abnormal payment account.

[0025] In some embodiments, the abnormal payment tag derivation system further includes a module:

[0026] Correction module: Correct the seed marks of abnormal users and abnormal payment accounts, and output the final abnormal users and abnormal payment accounts.

[0027] In some embodiments, the marker derivation module comprises:

[0028] Account weight ratio calculation module: calculates the weight ratio of abnormal payment accounts to each purchase channel;

[0029] User weight score calculation module: Calculate the user's score for each channel based on the weight ratio of each purchase channel and the weight of the usage relationship between the abnormal payment account and the user, determine the user's tag based on the highest score of the channel, and generate abnormal users with seed tags.

[0030] In some embodiments, the derivative iteration module includes:

[0031] User weight ratio calculation module: calculates the weight ratio of abnormal users belonging to each purchase channel;

[0032] Account weight score calculation module: Calculate the score of the payment account belonging to each channel based on the weight ratio of each purchase channel and the weight of the usage relationship between the abnormal user and the payment account, determine the mark of the payment account based on the highest score of the channel, and generate an abnormal payment account with a seed mark.

[0033] In some embodiments, the correction module includes:

[0034] Payment account correction module: performs statistical comparison between normal payment accounts and abnormal payment accounts, and corrects abnormal payment accounts;

[0035] User correction module: Correct abnormal users based on the probability that they belong to normal purchasing channels.

[0036] In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the marking derivation method for abnormal payments as described in the first aspect above is implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the marking derivation method for abnormal payments as described in the first aspect above.

[0038] Compared with the related prior art, it has the following outstanding beneficial effects:

[0039] 1. The present invention mainly realizes the derivative marking of the payment account usage channel, provides favorable data support for combating abnormal payments in the black and gray industries, and better protects the ticket purchasing rights of passengers;

[0040] 2. It mainly solves the problem of distinguishing payment account usage channels, and can increase the number of marked payment accounts from thousands to hundreds of millions, providing better data support for combating abnormal payments in the black and gray industries. Through sampling tests, the accuracy of payment account marking reached 99%, and this algorithm has a good production application effect;

[0041] 3. Through the correction method, the results of abnormal payment accounts and abnormal users can be made more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0043] Figure 1 is a flow chart of a method for derivation of marking of abnormal payments of the present invention;

[0044] Figure 2 It is a flowchart of the algorithm of a specific embodiment of the present invention;

[0045] Figure 3 It is a diagram showing the relationship between a payment account and a user according to a specific embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram of label propagation from a payment account to a user in a specific embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram of label propagation from a user to a payment account in a specific embodiment of the present invention;

[0048] Figure 6 This is a schematic diagram of a user name label modification process according to a specific embodiment of the present invention;

[0049] Figure 7 It is a schematic diagram of the marking derivation system of abnormal payment of the present invention;

[0050] Figure 8 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present application.

[0051] In the above picture:

[0052] 10 Seed marker generation module 20 Marker derivation module

[0053] 30 Derivative Iteration Module 40 Correction Module

[0054] 81. Processor; 82. Memory; 83. Communication interface; 80. Bus. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0056] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0057] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent.

[0058] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0059] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0060] The present invention aims to provide a payment account tagging derivation method based on usage relationship, which mainly solves the problem of distinguishing payment account usage channels, and can increase the number of tagged payment accounts from thousands to hundreds of millions, providing better data support for combating abnormal payments in black and gray industries. Through sampling tests, the accuracy of payment account tagging reached 99%, and this algorithm has a good production application effect.

[0061] The method involved in the present application is to propagate tags based on usage relationships. First, through manual testing, a set of abnormal payment accounts is constructed as seeds for tag propagation; the tags of these payment accounts are passed to users who have used these payment accounts, and then the user tags are propagated to the payment accounts used by these users, completing a round of iteration and expanding the tagged payment accounts; then, the newly tagged payment accounts and users are used to iterate again until the number of iterations is met or the number of untagged payment accounts is less than a certain threshold, thus terminating the derivation process of payment accounts and users; finally, the generated payment account and user tags are corrected, and the final payment account and user tags are output.

[0062] Figure 1 The labeling derivative method for abnormal payment of the present invention, such as Figure 1 As shown, the method of the present invention provides a marking derivation method for abnormal payment, including:

[0063] Seed mark generation step S10: constructing a set including at least one abnormal payment account, and setting a seed mark for the abnormal payment account;

[0064] Tag derivation step S20: Based on the usage relationship, the seed tag of the abnormal payment account is transmitted to at least one user who has used the abnormal payment account, to generate an abnormal user carrying the seed tag;

[0065] Derivative iterative step S30: Based on the usage relationship, the seed tag of the abnormal user is passed to at least one abnormal payment account used by the abnormal user, and the tag derivation step S20 and the derivative iterative step S30 are continuously executed in a loop until the iteration stop condition is met, and the tag derivation of the abnormal user and the abnormal payment account is completed.

[0066] Furthermore, the abnormal payment mark derivation method of the present invention further includes:

[0067] Correction step S40: Correct the seed marks of the abnormal user and the abnormal payment account, and output the final abnormal user and the abnormal payment account.

[0068] The tag derivation step S20 includes:

[0069] Account weight ratio calculation steps: Calculate the weight ratio of the abnormal payment account to each purchase channel;

[0070] User weight score calculation steps: According to the weight ratio of each purchase channel of the abnormal payment account and the weight of the usage relationship between the abnormal payment account and the user, calculate the user's score for each purchase channel, determine the user's tag based on the channel score, and generate an abnormal user with a seed tag.

[0071] The above-mentioned derivation iteration step S30 includes:

[0072] User weight ratio calculation steps: Calculate the weight ratio of abnormal users belonging to each purchase channel;

[0073] Account weight score calculation steps: According to the weight ratio of each purchase channel of the abnormal user and the weight of the usage relationship between the abnormal user and the payment account, calculate the score of the payment account belonging to each channel, determine the tag of the payment account according to the channel score, and generate an abnormal payment account with a seed tag.

[0074] The above-mentioned correction step S40 includes:

[0075] Payment account correction step: perform statistical comparison between normal payment accounts and abnormal payment accounts, and complete the correction of abnormal payment accounts;

[0076] User correction step: Correct abnormal users based on the probability that they belong to normal purchasing channels.

[0077] The following is a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings:

[0078] Figure 2 It is a flow chart of the algorithm of the embodiment of the present invention, such as Figure 2 As shown, the present invention mainly realizes the derivative marking of the payment account usage channel, provides favorable data support for combating abnormal payments in the black and gray industries, and better protects the ticket purchasing rights of passengers.

[0079] The method involved in the present application is to propagate tags based on usage relationships. First, through manual testing, a set of abnormal payment accounts is constructed as seeds for tag propagation; the tags of these payment accounts are passed to users who have used these payment accounts, and then the user tags are propagated to the payment accounts used by these users, completing a round of iteration and expanding the tagged payment accounts; then, the newly tagged payment accounts and users are used to iterate again until the number of iterations is met or the number of untagged payment accounts is less than a certain threshold, thus terminating the derivation process of payment accounts and users; finally, the generated payment account and user tags are corrected, and the final payment account and user tags are output.

[0080] In the specific embodiment of the present invention, four ticket purchase channels are taken as an example to illustrate the derivation process of the payment account mark. The four channels are selected as (X), (M), (Z), and railway (T), among which the users who use the railway (T) channel are normal users and normal payment accounts, and the users who use (X), (M), and (Z) are abnormal users and abnormal payment accounts.

[0081] Step 1: Generate the initial seed of the payment account. Through manual ticket purchase test, determine the payment account types used by different channels, and output the tag attributes of the payment account. See Table 1.

[0082] Payment Account (X) (M) (Z) Railway (T) mark P1 9 3 4 0 (X)

[0083] Table 1 Payment Account

[0084] Step 2: Relationship diagram between initial user and payment account.

[0085] Select payment data within a period of time, use payment account + user name as unique key value, perform group statistics, and output the number of times the same payment account + user name purchases tickets. Each time a ticket is purchased, it means that the relationship between the account and the user name is closer, so the number of ticket purchases is used to represent the weight of the relationship. The statistical results are shown in Table 2.

[0086]

[0087] Table 2 Payment Account-User Account Table

[0088] Figure 3 This is a relationship diagram between payment accounts and users in a specific embodiment of the present invention. The relationship diagram formed is as follows Figure 3 As shown in the figure, P1 represents the payment account node, U1 and U2 represent the user nodes, and the relationship number represents the edge between the nodes, such as the edge of P1-U1. The weight of the edge is 10. The larger the weight of the edge, the stronger the similarity between the two nodes.

[0089] Step 3: Initialize user tag.

[0090] According to strict conditions, some normal payment accounts are determined, and some normal users are screened out from these normal payment accounts; some abnormal users are screened out using the abnormal payment accounts determined in Step 1. The two types of users are aggregated to form the initial user tag.

[0091] Step 4: Derive the known payment account and user name tags to find more payment account and user name tag attributes. Before each iteration, confirm whether the iteration number max has been reached and the remaining untagged payment account number Prenum is greater than a certain threshold t before iterating.

[0092] Step 4: Iteration process.

[0093] First transmission: transmit the payment account to the associated users.

[0094] It is known that P1 is a marked payment account, but it has not been used to derive a user. According to the relationship graph constructed in Step 2, the mark of payment account P1 is propagated to users U1 and U2. Figure 4 FIG. 1 is a schematic diagram of tag propagation from a payment account to a user in a specific embodiment of the present invention. Figure 4 shown.

[0095] The propagation process is mainly divided into two steps: (U1, U2 are unlabeled users)

[0096] (1) Calculate the proportion of P1 belonging to each channel, such as the proportion of X per for

[0097]

[0098] (2) Calculate the score of the user belonging to each channel based on the proportion of each channel and the weight of the edge between the user and the channel. For example, the score of user U1 belonging to X is: X uv =X per *10, the values ​​of other channels are calculated similarly, and finally the scores of each channel of user U1 are obtained. The highest score of each channel is taken by comparison to determine the channel tag of the user. The calculation process of user U2 is the same. Through the above calculation, the tag of the payment account can be propagated to the users associated with it.

[0099] Second propagation: propagate the user's tag to the associated payment account.

[0100] It is known that U1 and U2 are the latest tagged users and have not been used to derive new payment accounts. The propagation process is similar to the first propagation. Figure 5 FIG. 1 is a schematic diagram of the propagation of a tag from a user to a payment account in a specific embodiment of the present invention. Figure 5 shown.

[0101] The propagation process is mainly divided into two steps: (P2 and P3 are unmarked payment accounts)

[0102] (1) Calculate the proportion of U1 belonging to each channel, such as the proportion of X per1 for

[0103]

[0104] Calculate the proportion of U2 belonging to each channel, such as the proportion of X per2 for

[0105]

[0106] (2) Calculate the score of the user belonging to each channel based on the proportion of each channel and the weight of the edge between the user and the channel.

[0107] The score of user U1 belonging to X is: X uv1 =X per1 *20,

[0108] User U2's score for X is: X uv2 =X per2 *6,

[0109] The final score of payment account P2 belonging to X is X = X uv1 +X uv2 The score calculation for other channels is similar.

[0110] The calculation process of the P3 payment account associated with user U2 is consistent with the calculation process of P2.

[0111] Finally, the scores of each channel of payment accounts P2 and P3 are obtained, and the channel mark of each payment account is determined by comparing the highest score of each channel.

[0112] Through the above calculation process, the user's tag can be propagated to the payment account associated with it, realizing the payment account propagation process. Through a small number of payment accounts, more payment accounts can be marked by utilizing the relationship between users.

[0113] Continue to iterate until the termination condition is met, and output the final marked payment account and user name.

[0114] Step 5: Correct the markup of the payment account and username.

[0115] 1. Correct the mark of the payment account

[0116] (1) The final marked user name is propagated to all payment accounts associated with it, and the results of the current payment account are output to a table temp_bank, with one record for each payment account.

[0117] (2) The payment account for purchasing tickets from the railway (T) channel is also entered into this table temp_bank. Only the railway (T) mark has a value, and the values ​​of other channels are all 0.

[0118] (3) Group and count the table temp_bank using the payment account as the unique key value, and output the final result for each payment account.

[0119] In this way, the score of normal payment accounts belonging to the railway (T) ticket purchasing channel can be increased, thereby reducing accidental injuries.

[0120] For payment accounts with a large number of user names, assuming that the number is greater than the threshold q, the railway (T) mark is directly removed, and only malicious payment channels are considered. This is to prevent malicious payment accounts from being marked as normal.

[0121] Through the above two corrections, the payment account results can be made more accurate.

[0122] 2. Correct the username mark

[0123] Figure 6FIG. 1 is a schematic diagram of a user name tag correction process according to a specific embodiment of the present invention. The user name correction process is as follows: Figure 6 shown.

[0124] Step 1: Calculate the score of each channel for the user name using the marked payment account, such as Figure 6 Left side.

[0125] (1) Extract abnormal payment accounts with too many associated users, remove the data using abnormal payment accounts from the basic data association table, and output the filtered payment account-user account table.

[0126] (2) Calculate the proportion of marked payment accounts belonging to each channel.

[0127] (3) Associate the filtered payment account-user account table with the proportion of payment accounts belonging to each channel.

[0128] Use the payment account tag to propagate the tag and output the username tag attribute results to the summary table.

[0129] Step 2: Extract normal payment accounts and calculate the user scores of official channels in the basic table. Figure 6 Right side.

[0130] (1) To extract a normal payment account, first calculate the probability that the payment account is a normal payment account based on the number of usernames used. The fields of the output table are: payment account bankaccountno, number of users user_cnt, probability percent_rate.

[0131] (2) Using normal payment accounts to filter the payment account-user account table data, output the payment account-user account table with normal payment accounts.

[0132] (3) For the payment account-user account table with normal payment accounts, count the number of payment accounts under each user name. Different percentage values ​​are given to users according to the number of payment accounts associated with different user names. For example, if 5 payment accounts are associated, the percentage is 0.2, and if 4 payment accounts are associated, the percentage is 0.4. The fewer the number of payment accounts used by a user name, the greater the percentage of normal channels for that user name.

[0133] (4) Assign the Railway (T) channel to the user name in the basic table. As shown in the formula, the scores of other channels are all given 0, and the Railway (T) score of the normal user name is output.

[0134] The score of a user name belonging to the railway (T) ticket purchase channel = the number of times the user has purchased tickets using the payment account * the probability percent_rate that the payment account belongs to the normal channel for ticket purchase * the probability percent that the user belongs to the normal channel for ticket purchase.

[0135] The above formula means that the risk tag of the payment account is first passed to the username, and then the risk behavior of the username itself is accumulated, so two ratios are multiplied.

[0136] The final calculated username tag attribute results are entered into the summary table.

[0137] Step 3: Summarize the scores of each channel of the user name and output the score of the user belonging to each channel. Through the processing of the second step, the probability of marking the user as a malicious user can be reduced.

[0138] Step 6: After modification, output the payment account and the user’s final attribute tag.

[0139] Figure 7 Schematic diagram of the labeling derivatization system of the present invention, such as Figure 7 As shown, the present invention also provides a tag derivation system for abnormal payment, which adopts the tag derivation method for abnormal payment as described above, including:

[0140] A seed mark generation module 10: constructs a set including at least one abnormal payment account, and sets a seed mark for the abnormal payment account;

[0141] Tag derivation module 20: based on the usage relationship, transmit the seed tag of the abnormal payment account to at least one user who has used the abnormal payment account, and generate an abnormal user carrying the seed tag;

[0142] Derivative iteration module 30: Based on the usage relationship, the seed tag of the abnormal user is passed to at least one abnormal payment account used by the abnormal user, and the tag derivation module 20 and the derivative iteration module 30 are executed in a loop until the iteration stop condition is met, and the tag derivation of the abnormal user and the abnormal payment account is completed.

[0143] Furthermore, the above abnormal payment tag derivation system also includes modules:

[0144] Correction module 40: corrects the seed marks of abnormal users and abnormal payment accounts, and outputs the final abnormal users and abnormal payment accounts.

[0145] The above-mentioned mark derivation module 20 includes:

[0146] Account weight ratio calculation module: calculates the weight ratio of abnormal payment accounts to each purchase channel;

[0147] User weight score calculation module: Calculate the user's score for each channel based on the weight ratio of each purchase channel and the weight of the usage relationship between the abnormal payment account and the user, determine the user's tag based on the highest score of the channel, and generate abnormal users with seed tags.

[0148] The above-mentioned derivative iteration module 30 includes:

[0149] User weight ratio calculation module: calculates the weight ratio of abnormal users belonging to each purchase channel;

[0150] Account weight score calculation module: Calculate the score of the payment account belonging to each channel based on the weight ratio of each purchase channel and the weight of the usage relationship between the abnormal user and the payment account, determine the mark of the payment account based on the highest score of the channel, and generate an abnormal payment account with a seed mark.

[0151] The correction module 40 includes:

[0152] Payment account correction module: performs statistical comparison between normal payment accounts and abnormal payment accounts, and corrects abnormal payment accounts;

[0153] User correction module: Correct abnormal users based on the probability that they belong to normal purchasing channels.

[0154] In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the marking derivation method for abnormal payments as described in the first aspect above is implemented.

[0155] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the marking derivation method for abnormal payments as described in the first aspect above.

[0156] In addition, combined Figure 1 The abnormal payment marking derivation method described in the embodiment of the present application can be implemented by a computer device. Figure 8 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present application.

[0157] The computer device may include a processor 81 and a memory 82 storing computer program instructions.

[0158] Specifically, the processor 81 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0159] Among them, the memory 82 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include removable or non-removable (or fixed) media.

[0160] In appropriate cases, the memory 82 may be inside or outside the data processing device. In a specific embodiment, the memory 82 is a non-volatile memory. In a specific embodiment, the memory 82 includes a read-only memory (ROM) and a random access memory (RAM). In appropriate cases, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0161] The memory 82 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 81 .

[0162] The processor 81 implements any one of the marking derivation methods in the above embodiments by reading and executing computer program instructions stored in the memory 82 .

[0163] In some of these embodiments, the computer device may further include a communication interface 83 and a bus 80. Figure 8As shown, the processor 81, the memory 82, and the communication interface 83 are connected via a bus 80 and communicate with each other.

[0164] The communication interface 83 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication port 83 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0165] The bus 80 includes hardware, software or both, and couples the components of the computer device to each other. The bus 80 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infini Band interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0166] The computer device can be combined based on the usage relationship Figure 1Described marker derivatization method.

[0167] Compared with the prior art, the method of the present invention mainly realizes the derivative marking of the payment account usage channel, provides favorable data support for the railway to accurately crack down on abnormal payment ticket purchases, and better protects the ticket purchase rights of passengers; it mainly solves the problem of distinguishing the payment account usage channels, and can increase the number of marked payment accounts from thousands to hundreds of millions, providing better data support for combating abnormal payment ticket purchases. Through sampling testing, the accuracy of payment account marking reaches 99%, and this algorithm has a good production application effect; through the correction method, the payment account result can be made more accurate.

[0168] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described 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.

[0169] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A marking derivation method for abnormal payment, characterized in that: include: Seed mark generation step: constructing a set including at least one abnormal payment account, and setting a seed mark for the abnormal payment account; Mark derivation step: based on the usage relationship, the seed mark of the abnormal payment account is transmitted to at least one user who has used the abnormal payment account, and an abnormal user carrying the seed mark is generated; Derivative iterative step: based on the usage relationship, the seed tag of the abnormal user is transferred to at least one abnormal payment account used by the abnormal user, and the tag derivation step and the derivation iterative step are continuously executed in a loop until the iteration stop condition is met, and the tag derivation of the abnormal user and the abnormal payment account is completed; The marker derivatization step comprises: Account weight ratio calculation step: calculating the weight ratio of the abnormal payment account to each purchase channel; User weight score calculation step: according to the weight ratio of each purchase channel of the abnormal payment account and the weight of the usage relationship between the abnormal payment account and the user, the score of the user belonging to each purchase channel is calculated, and the channel mark of the user is determined by comparing and taking the highest score of each channel, and the seed mark of the abnormal payment account is propagated to the users associated with it to obtain the abnormal user carrying the seed mark; The derivation iteration steps include: User weight ratio calculation step: calculating the weight ratio of the abnormal user to each purchase channel; Account weight score calculation step: according to the weight ratio of each purchase channel of the abnormal user and the usage relationship weight between the abnormal user and the payment account used by the abnormal user, calculate the score of the payment account belonging to each of the channels, determine the channel mark of each payment account by comparing and taking the highest score of each channel, propagate the seed mark of the abnormal user to the payment account associated with it, and obtain the abnormal payment account carrying the seed mark.

2. The abnormal payment tag derivation method according to claim 1, characterized in that: Also includes: Correction step: Correct the seed marks of the abnormal user and the abnormal payment account, and output the final abnormal user and abnormal payment account.

3. The method for deriving a mark for abnormal payment according to claim 2, characterized in that: The correction steps include: Payment account correction step: statistically comparing the normal payment account with the abnormal payment account to correct the abnormal payment account; User correction step: based on the probability that the abnormal user belongs to a normal purchasing channel, correct the abnormal user.

4. A system for deriving marks for abnormal payments, using the method for deriving marks for abnormal payments as claimed in any one of claims 1 to 3, characterized in that: include: A seed mark generation module: constructs a set including at least one abnormal payment account, and sets a seed mark for the abnormal payment account; A tag derivation module: based on the usage relationship, the seed tag of the abnormal payment account is transferred to at least one user who has used the abnormal payment account, and an abnormal user carrying the seed tag is generated; Derivative iteration module: based on the usage relationship, the seed tag of the abnormal user is transferred to at least one abnormal payment account used by the abnormal user, and the tag derivation module and the derivation iteration module are continuously executed in a loop until the iteration stop condition is met, and the tag derivation of the abnormal user and the abnormal payment account is completed; The tag derivation module includes: Account weight ratio calculation module: calculates the weight ratio of the abnormal payment account to each purchase channel; User weight score calculation module: calculates the score of the user belonging to each purchase channel according to the weight ratio of each purchase channel of the abnormal payment account and the weight of the usage relationship between the abnormal payment account and the user, determines the channel mark of the user by comparing and taking the highest score of each channel, propagates the seed mark of the abnormal payment account to the users associated with it, and obtains the abnormal user carrying the seed mark; The derivative iteration module includes: User weight ratio calculation module: calculates the weight ratio of the abnormal user to each purchase channel; Account weight score calculation module: calculates the score of the payment account belonging to each channel according to the weight ratio of each purchase channel of the abnormal user and the usage relationship weight between the abnormal user and the payment account used by the abnormal user, determines the channel mark of each payment account by comparing and taking the highest score of each channel, propagates the seed mark of the abnormal user to the payment account associated with it, and obtains the abnormal payment account carrying the seed mark.

5. The abnormal payment tag derivation system according to claim 4, characterized in that: Also includes: Correction module: corrects the seed marks of the abnormal user and the abnormal payment account, and outputs the final abnormal user and abnormal payment account.

6. The abnormal payment tag derivation system according to claim 5, characterized in that: The correction module comprises: Payment account correction module: performs statistical comparison between the normal payment account and the abnormal payment account, and completes the correction of the abnormal payment account; User correction module: corrects the abnormal user based on the probability that the abnormal user belongs to the normal purchasing channel.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the abnormal payment marking derivation method according to any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for deriving a mark of abnormal payment as claimed in any one of claims 1 to 3 is implemented.

Images