Transaction identification method and device, electronic equipment and storage medium

By building a directed transaction graph and using a supervised transaction identification model, the problems of low efficiency and insufficient accuracy of transaction data identification in the existing technology are solved, and efficient identification and accurate screening of massive transaction data are achieved, ensuring the identification results Objectivity and reliability.

CN119089353AActive Publication Date: 2024-12-06CHINA CONSTRUCTION BANK +1
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411150873.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-12-06
Estimated Expiration
2044-08-21

AI Technical Summary

Technical Problem

In the prior art, transaction data identification efficiency is low and the accuracy is insufficient, and abnormal transaction data in massive transaction data cannot be effectively identified, and there is high subjectivity.

Method used

By obtaining transaction accounts and transaction transfer relationships, constructing a directed transaction graph, identifying and cutting, and using a supervised transaction identification model to filter out abnormal transaction data.

Benefits of technology

It improves the efficiency and accuracy of transaction data identification, reduces cost and time, and ensures the objectivity and reliability of identification results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089353A_ABST
    Figure CN119089353A_ABST
Patent Text Reader

Abstract

The invention relates to a transaction identification method and device, electronic equipment and a storage medium, and belongs to the technical field of information processing. The method comprises the steps of obtaining to-be-identified first transaction data, and obtaining transaction accounts and a transaction transfer relationship between every two transaction accounts from the first transaction data; constructing a first transaction directed graph based on transaction accounts and the transaction transfer relationship between every two transaction accounts; identifying the first transaction data to obtain a first identification result of the first transaction data, and determining normal transaction data in the first transaction data according to the first identification result; cutting the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph; and determining the second transaction data according to the nodes in the second transaction directed graph, and identifying the second transaction data to screen the abnormal third transaction data from the second transaction data, thereby improving the accuracy and efficiency of obtaining the abnormal transaction data.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of information processing, and in particular to a transaction identification method, device, electronic device and storage medium. Background Art

[0002] It is often difficult to identify abnormal transaction data from massive transaction data. In related technologies, abnormal transaction data is identified through manual monitoring and identification of abnormal and suspicious transactions, and through rules formulated by experts. However, the above methods often have low recognition efficiency through manual identification, and cannot perform large-scale transaction data identification. Moreover, the accuracy and timeliness of abnormal transaction data identification cannot be guaranteed, and identification through rules often has a certain degree of subjectivity. Summary of the invention

[0003] The present disclosure provides a transaction identification method, device, electronic device, computer-readable storage medium and computer program product to at least solve the problem of low accuracy and efficiency in the transaction identification process in the related art.

[0004] The technical solution of the present disclosure is as follows:

[0005] According to a first aspect of an embodiment of the present disclosure, a transaction identification method is provided, the method comprising: obtaining first transaction data to be identified, and obtaining a transaction account and a transaction transfer relationship between every two transaction accounts from the first transaction data; constructing a first transaction directed graph based on the transaction account and the transaction transfer relationship between every two transaction accounts; identifying the first transaction data to obtain a first identification result of the first transaction data, and determining normal transaction data in the first transaction data based on the first identification result; trimming the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph; determining second transaction data based on nodes in the second transaction directed graph, and identifying the second transaction data to filter out abnormal third transaction data from the second transaction data.

[0006] According to a second aspect of an embodiment of the present disclosure, a transaction identification device is provided, the device comprising: a first acquisition module, configured to acquire first transaction data to be identified, and acquire transaction accounts and transaction transfer relationships between every two transaction accounts from the first transaction data; a second acquisition module, configured to construct a first transaction directed graph based on the transaction accounts and the transaction transfer relationships between every two transaction accounts; a determination module, configured to identify the first transaction data, acquire a first identification result of the first transaction data, and determine normal transaction data in the first transaction data based on the first identification result; a cropping module, configured to crop the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph; an identification module, configured to determine second transaction data based on nodes in the second transaction directed graph, and identify the second transaction data to filter out abnormal third transaction data from the second transaction data.

[0007] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the transaction identification method as described in the first aspect.

[0008] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the transaction identification method as described in the first aspect.

[0009] According to a fifth aspect of an embodiment of the present disclosure, there is provided a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the transaction identification method as described in the first aspect is implemented.

[0010] The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects: obtaining first transaction data to be identified, and obtaining transaction accounts and transaction transfer relationships between every two transaction accounts from the first transaction data, constructing a first transaction directed graph based on the transaction accounts and the transaction transfer relationships between every two transaction accounts, identifying the first transaction data, obtaining a first identification result of the first transaction data, determining normal transaction data in the first transaction data based on the first identification result, trimming the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph, determining second transaction data based on nodes in the second transaction directed graph, and identifying the second transaction data to screen out abnormal third transaction data from the second transaction data. Therefore, the present disclosure can identify massive amounts of transaction data, improve the efficiency of identifying abnormal transaction data, ensure the objectivity of obtaining abnormal transaction identification data, save cost and time in the transaction identification process, and improve the accuracy and reliability of obtaining abnormal transaction identification data.

[0011] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute improper limitations on the present disclosure.

[0013] Figure 1 It is a flowchart of a transaction identification method according to the first embodiment of the present disclosure.

[0014] Figure 2 It is a schematic diagram of the first transaction directed graph of the present disclosure.

[0015] Figure 3 It is a flowchart of the supervised transaction recognition model training according to the first embodiment of the present disclosure.

[0016] Figure 4 It is a flowchart of a transaction identification method according to the second embodiment of the present disclosure.

[0017] Figure 5 It is a schematic diagram of the second transaction directed graph of the present disclosure.

[0018] Figure 6 It is a flowchart of a transaction identification method according to the third embodiment of the present disclosure.

[0019] Figure 7 It is a flowchart of a transaction identification method according to the fourth embodiment of the present disclosure.

[0020] Figure 8It is a flowchart of a transaction identification method according to the fifth embodiment of the present disclosure.

[0021] Fig. 9 is a block diagram of a transaction identification device according to a first embodiment of the present disclosure.

[0022] Fig.10 It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0023] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0025] It should be noted that the information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards.

[0026] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of the present disclosure are in compliance with the relevant provisions of relevant laws and regulations. In the embodiments of the present disclosure, certain software, components, models, and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present disclosure, but it does not mean that the applicant has or will necessarily use the solution.

[0027] Figure 1 It is a flowchart of a transaction identification method according to the first embodiment of the present disclosure.

[0028] like Figure 1 As shown, the transaction identification method of the first embodiment of the present disclosure includes the following steps:

[0029] S101, obtaining first transaction data to be identified, and obtaining transaction accounts and transaction transfer relationships between every two transaction accounts from the first transaction data.

[0030] It should be noted that the present disclosure does not limit the specific method for obtaining the first transaction data to be identified, and it can be selected according to actual conditions.

[0031] Optionally, the original transaction data to be identified may be obtained through a transaction database. To improve the efficiency of the transaction identification process, a transaction data filtering strategy may be pre-set for transaction parameters in the original transaction data, and the original transaction data may be filtered based on the transaction data filtering strategy to obtain the first transaction data to be identified.

[0032] For example, for the transaction amount in the original transaction data, a transaction amount threshold par_m is pre-set, and the original transaction data less than the transaction amount threshold par_m is filtered. For the transaction time in the original transaction data, a transaction time period [par_d_min, par_d_max] is pre-set, and the original transaction data not within the transaction time period [par_d_min, par_d_max] is filtered. For the transaction accounts in the original transaction data, the original transaction data corresponding to the transaction accounts in the transaction account whitelist can be filtered.

[0033] In the embodiment of the present disclosure, after the first transaction data is obtained, the transaction account and the transaction transfer relationship between every two transaction accounts can be obtained from the first transaction data.

[0034] S102: construct a first transaction directed graph based on the transaction accounts and the transaction transfer relationship between every two transaction accounts.

[0035] Among them, the transaction directed graph G(V,E), V is the node set of the transaction directed graph, E is the edge set of the transaction directed graph, the nodes in the transaction directed graph are transaction accounts, the edges are the transaction transfer relationships between every two transaction accounts, and each edge carries transaction information, which includes transaction amount and transaction time.

[0036] For example, Figure 2 As shown, for trading account A 1 -A 6 and the transaction transfer relationship between every two transaction accounts, construct the first transaction directed graph Graph1, where node A i is the trading account, and side is the trading account A i To trading account A j Initiate a transfer transaction, (Mi, Ti) is the transaction amount and transaction time of the transfer transaction.

[0037] For example, Figure 2 As shown, for trading account A 1 and A 2 , Trading Account A1 To trading account A 2 Initiate a transfer transaction, where the transaction amount is M1 and the transaction time is T1.

[0038] S103, identifying the first transaction data, obtaining a first identification result of the first transaction data, and determining normal transaction data in the first transaction data according to the first identification result.

[0039] It should be noted that the present disclosure does not limit the specific method of identifying the first transaction data and obtaining the first identification result of the first transaction data, which can be selected according to actual conditions.

[0040] Optionally, a feature vector of the first transaction data may be obtained, and the feature vector may be input into a pre-trained supervised transaction recognition model to obtain a first transaction label prediction value of the first transaction data, and a first recognition result of the first transaction data may be obtained based on the first transaction label prediction value.

[0041] For example, in response to the first transaction tag prediction value being greater than a preset first threshold, the first transaction data is determined to be normal transaction data; in response to the first transaction tag prediction value being less than or equal to the preset first threshold, the first transaction data is determined to be abnormal transaction data.

[0042] In the embodiment of the present disclosure, after the first recognition result is obtained, normal transaction data in the first transaction data can be determined according to the first recognition result.

[0043] S104: trim the first transaction directed graph based on normal transaction data to obtain a second transaction directed graph.

[0044] In an embodiment of the present disclosure, a first transaction account and a second transaction account having a transaction transfer relationship in normal transaction data can be obtained, a first node associated with the first transaction account and a second node associated with the second transaction account are determined in a first transaction directed graph, and the edge between the first node and the second node is deleted (trimmed) to obtain a second transaction directed graph Graph2.

[0045] For example, after obtaining normal transaction data, the first transaction account A that has a transaction transfer relationship in the normal transaction data m and the second trading account A n , determine the first node A associated with the first transaction account in the first transaction directed graph m The second node A associated with the second transaction account n , the first node A m With the second node A n Delete the edges between them to obtain the second transaction directed graph Graph2.

[0046] S105, determining the second transaction data according to the nodes in the second transaction directed graph, and identifying the second transaction data to filter out abnormal third transaction data from the second transaction data.

[0047] In the disclosed embodiment, after obtaining the second transaction directed graph, the nodes in the second transaction directed graph can be divided according to the weight of each node in the second transaction directed graph to obtain a node set of the second transaction directed graph, and a second recognition result of the second transaction data is determined based on the target transaction label prediction value by obtaining the target transaction label prediction value, and based on the second recognition result, the third transaction data with abnormalities is screened out from the second transaction data.

[0048] For example, for the node set {A} in the second transaction directed graph, if the node set {A} includes node A 1 Node A 2 and node A 3 , node A 1 Node A 2 and node A 3 The target transaction label prediction values ​​are y 1 ,y 2 and 3 , then the target transaction label prediction and value y of the node set {A} sum =y 1 +y 2 +y 3 , if the target transaction label prediction and value y sum If the score is less than the preset second threshold bad_score, it is determined that the transaction data in the node set are all abnormal, that is, node A 1 Node A 2 and node A 3 The transaction data of are all abnormal. If the target transaction label prediction and value y sum If the score is greater than or equal to the preset second threshold bad_score, it is determined that the transaction data in the node set are all normal, that is, node A 1 Node A 2 and node A 3 The transaction data are all normal.

[0049] In summary, according to the transaction identification method provided by the embodiment of the present disclosure, by obtaining the first transaction data to be identified, and obtaining the transaction transfer relationship between the transaction account and every two transaction accounts from the first transaction data, a first transaction directed graph is constructed based on the transaction account and the transaction transfer relationship between every two transaction accounts, the first transaction data is identified, and a first identification result of the first transaction data is obtained. According to the first identification result, normal transaction data in the first transaction data is determined, and the first transaction directed graph is trimmed based on the normal transaction data to obtain a second transaction directed graph. According to the nodes in the second transaction directed graph, the second transaction data is determined, and the second transaction data is identified to filter out abnormal third transaction data from the second transaction data. Therefore, the present disclosure can identify massive transaction data, improve the efficiency of identifying abnormal transaction data, ensure the objectivity of obtaining abnormal transaction identification data, save cost and time in the transaction identification process, and improve the accuracy and reliability of obtaining abnormal transaction identification data.

[0050] Figure 3 It is a flowchart of a transaction identification method according to the second embodiment of the present disclosure.

[0051] like Figure 3 As shown, the transaction identification method of the second embodiment of the present disclosure includes the following steps:

[0052] S301, obtaining first transaction data to be identified, and obtaining transaction accounts and transaction transfer relationships between every two transaction accounts from the first transaction data.

[0053] S302: construct a first transaction directed graph based on the transaction accounts and the transaction transfer relationship between every two transaction accounts.

[0054] For the relevant contents of step S301 to step S302, please refer to the above embodiment and will not be repeated here.

[0055] As a possible implementation method, based on the above implementation, the specific process of identifying the first transaction data in step S103 and obtaining the first identification result of the first transaction data includes steps S303 to S305:

[0056] S303, obtaining a feature vector of the first transaction data, and inputting the feature vector into a pre-trained supervised transaction recognition model to obtain a first transaction label prediction value of the first transaction data.

[0057] As a possible way to achieve this, Figure 4 As shown, the specific process of supervised transaction recognition model training includes steps S401 to S405:

[0058] S401, obtaining a training sample set, wherein each training sample in the training sample set includes sample transaction data and a true value of a sample transaction label.

[0059] Among them, for the true value of the sample transaction label, if a transfer transaction transi between every two transaction accounts is an abnormal transaction, then the true value of the sample transaction label y i is 1. If a transfer transaction transi between two transaction accounts is a normal transaction, the true value of the sample transaction label y i is 0.

[0060] It should be noted that the present disclosure does not limit the specific method for obtaining the training sample set, which can be selected according to actual conditions.

[0061] Optionally, a historical transaction data set may be obtained, an initial training sample set may be constructed according to the historical transaction data set, and sampling may be performed on the initial training sample set to obtain a training sample set.

[0062] For example, when there are abnormal transactions in the sample accounts before, the sample accounts of this type are identified as abnormal accounts, and all abnormal accounts are retained. All abnormal accounts are aggregated to obtain a set {B}. When there are no abnormal transactions in the sample accounts before, the accounts of this type are identified as normal accounts. Normal accounts can be extracted according to the ratio of "abnormal account: normal account = 1:r1", where r1 is an adjustable parameter. The extracted normal accounts are aggregated to obtain a set {C}. The sets {B} and {C} are merged to obtain a set {D} = {B}U{C}. The transaction data of the transaction accounts in the set {D} are obtained, and the transaction data of the transaction accounts in the set {D} are aggregated. All abnormal transaction data in the data are summarized to obtain set {E}, other transaction data in the transaction data in set {D}, namely normal transaction data, are summarized to obtain set {F}, and all abnormal transaction data are selected from set {E}, and normal accounts are extracted from set {F} according to the ratio of "abnormal transaction: normal transaction = 1:r2", where r2 is an adjustable parameter, and the extracted normal accounts are summarized to obtain set {G}, and set {E} and set {G} are subjected to set {H} = {E}U{G}. After obtaining set {H}, set {H} can be divided into a training sample set and a test sample set according to a preset ratio.

[0063] S402, obtaining a sample feature vector of the sample transaction data, inputting the sample feature vector into an initial transaction recognition model, and obtaining a transaction label prediction value.

[0064] In the embodiment of the present disclosure, after the sample transaction data is acquired, feature extraction may be performed on the sample transaction data to acquire a sample feature vector of the sample transaction data.

[0065] It should be noted that after obtaining the sample transaction data, the true value of the sample transaction label and the sample feature vector of the sample transaction data, a wide table can be constructed based on the sample transaction data, the true value of the sample transaction label and the sample feature vector of the sample transaction data.

[0066] For example, as shown in Table 1, transi is a transfer transaction between every two transaction accounts, FeaVarj is the characteristic variable corresponding to transi, and x i,j is the eigenvalue of the feature variable FeaVarj corresponding to transi, and yi is the true value of the sample transaction label.

[0067] Table 1

[0068]

[0069] In the embodiment of the present disclosure, after obtaining the sample feature vector of the sample transaction data, the sample feature vector may be input into the initial transaction recognition model to obtain a transaction label prediction value.

[0070] S403, performing supervised training on the initial transaction recognition model according to the actual value of the sample transaction label and the predicted value of the transaction label to obtain a supervised transaction recognition model.

[0071] In the disclosed embodiment, the target loss of the initial transaction recognition model can be determined based on the true value of the sample transaction label and the predicted value of the transaction label, the model parameters of the initial transaction recognition model can be adjusted based on the target loss, and the adjusted initial transaction recognition model can continue to be supervised trained based on the next training sample until the training is completed to obtain a supervised transaction recognition model.

[0072] It should be noted that the present disclosure does not limit the specific method of supervised training. For example, supervised training methods include but are not limited to logistic regression algorithm, random forest algorithm, and decision tree-based integrated machine learning algorithm (eXtreme gradient boosting, referred to as Xgboost).

[0073] It should be noted that the present disclosure does not limit the setting of the model training end condition, and the model training end condition can be set according to actual conditions.

[0074] Optionally, the model training termination condition can be set as the target loss value being less than a preset loss threshold; optionally, the model training termination condition can also be set as the number of adjustments to the model parameters of the initial transaction identification model reaching a preset number threshold.

[0075] In the embodiment of the present disclosure, the feature vector of the first transaction data can be input into a pre-trained supervised transaction recognition model to obtain a first transaction label prediction value y of the first transaction data.m .

[0076] Among them, when the first transaction label prediction value y m The larger the value, the lower the probability that the first transaction data is abnormal.

[0077] S304: In response to the first transaction tag prediction value being greater than a preset first threshold, determining that the first transaction data is normal transaction data.

[0078] It should be noted that the present disclosure does not limit the setting of the first threshold par_s, and it can be set according to actual conditions.

[0079] In the embodiment of the present disclosure, when the first transaction tag prediction value y m When y is greater than the preset first threshold par_s, m >par_s, it is determined that the first transaction data is normal transaction data.

[0080] S305: In response to the first transaction tag prediction value being less than or equal to a preset first threshold, determining that the first transaction data is abnormal transaction data.

[0081] In the embodiment of the present disclosure, when the first transaction tag prediction value y m When y is less than or equal to the preset first threshold par_s, m ≤par_s, the first transaction data is determined to be abnormal transaction data.

[0082] S306: Determine normal transaction data in the first transaction data according to the first identification result.

[0083] As a possible implementation method, based on the above implementation, the specific process of clipping the first transaction directed graph based on normal transaction data in step S104 to obtain the second transaction directed graph includes steps S307 to S308:

[0084] S307, obtaining a first transaction account and a second transaction account having a transaction transfer relationship in the normal transaction data.

[0085] S308, determining a first node associated with the first transaction account and a second node associated with the second transaction account in the first transaction directed graph, and deleting an edge between the first node and the second node to obtain a second transaction directed graph.

[0086] For example, Figure 5 As shown, after obtaining the normal transaction data, the first transaction account A having a transaction transfer relationship in the normal transaction data 5 and the second trading account A 6 , determine the first node A associated with the first transaction account in the first transaction directed graph5 The second node A associated with the second transaction account 6 , delete the edge between the first node and the second node, that is, the first node A 5 With the second node A 6 Delete the edges between them to obtain the second transaction directed graph Graph2.

[0087] S309: Determine second transaction data according to the nodes in the second transaction directed graph.

[0088] For the relevant contents of step S309, please refer to the above embodiment, which will not be repeated here.

[0089] As a possible implementation method, based on the above implementation, the specific process of identifying the second transaction data in step S105 to filter out the abnormal third transaction data from the second transaction data includes steps S3010 to S3013:

[0090] S3010, obtaining the transaction probability of each node in the second transaction directed graph, and using the transaction probability as the weight of each node in the second transaction directed graph.

[0091] As a possible way to achieve this, Figure 6 As shown, based on the above implementation, the specific process of obtaining the transaction probability of each node in the second transaction directed graph in step S2010 includes steps S601 to S602:

[0092] S601, obtaining the number of nodes in the second transaction directed graph, and initializing a first probability of a transaction occurring at each node at time t according to the number of nodes.

[0093] It should be noted that if the number of nodes in the second transaction directed graph Graph2 is N, and the probability of each node being visited is the same, then the first probability of each node having a transaction at time t is 1 / N.

[0094] S602, iterating the second probability of a transaction occurring at each node at time t+1 according to the first probability, and in response to satisfying an iteration end condition, using the second probability corresponding to the last iteration as the transaction probability of each node in the second transaction directed graph.

[0095] It should be noted that the present disclosure does not limit the setting of the iteration end condition, which can be set according to actual conditions. Optionally, the iteration end condition is that the number of iterations is greater than or equal to a preset iteration number threshold; optionally, the iteration end condition is that the error value between the second probability and the first probability is less than or equal to a preset error threshold.

[0096] It should be noted that if the number of nodes in the second transaction digraph Graph2 is N, the probability that node A has a transfer transaction (node A is transferred in) at the initial time t = 0 is P t=0 (A); the probability that node A has a transfer transaction to node B (node A transfers out and node B transfers in) at the next time t = 1 is P t=1 (B|A). If there is a transfer transaction with node A and it transfers out from node A, the set of nodes that this node transfers into is TransLink1(A). The probability that node A transfers to each node in the set TransLink1(A) is the same. Then where |TransLink1(A)| is the number of nodes in the set TransLink1(A); there is a transfer transaction for node A at the initial time t = 0, and the probability P t=0 (A)*P t=1 (B|A) that node A has a transfer transaction to node B at t = 1; the probability that node B has a transfer transaction (node B is transferred in) at t = 1 is P t=1 (B) = ∑ AinTransLink2(B) P t=0 (A)*P t=1 (B|A) = ∑ AinTransLink2(B) P t=0 (A) / |TransLink1(A)| (Equation 1). Here, TransLink2(B) is the set of account nodes that have a transfer transaction with node B and are transferred in by account node B and transfer out from this node; generalizing Equation (1), that is, replacing the time t = 0 with any time t = i, we can get:

[0097] P t=i+1 (B) = ∑ AinTransLink2(B) P t=i (A) / |TransLink1(A)| (Equation 2)

[0098] For example, if the iteration end condition is that the error value between the second probability and the first probability is less than a preset error threshold, calculate the second probability of each node having a transaction at time t + 1 according to Equation (2), sum up the second probabilities of each node having a transaction at time t + 1. When ∑ BinGraph2 P t=i+1 -∑ BinGraph2 P t=i <w, then stop the iterative calculation. In this case, take the second probability corresponding to the last iteration of each node as the final transaction probability of each node in the second transaction digraph. Here, B is all the nodes in the second transaction digraph, ∑ BinGraph2 P t=i+1 is the second probability, ∑ BinGraph2 P t=i is the first probability, and w is the error threshold.

[0099] In the embodiment of the present disclosure, after obtaining the transaction probability of each node, the transaction probability is used as the weight wgt of each node in the second transaction directed graph. i .

[0100] S3011, divide the nodes in the second transaction directed graph according to weights, and obtain a node set of the second transaction directed graph.

[0101] As a possible way to achieve this, Figure 7 As shown, based on the above implementation, the specific process of dividing the nodes in the second transaction directed graph according to the weights in step S2011 and obtaining the node set of the second transaction directed graph includes steps S701 to S703:

[0102] S701, obtaining key nodes and important nodes of key nodes in the second transaction directed graph.

[0103] In an embodiment of the present disclosure, a node quantity threshold minCount and a weight threshold minWgt preset for a node set are obtained, the transaction path length between node i and node j is obtained, and based on the transaction path length, a neighbor node set of node i in the second transaction directed graph is determined, in response to the number of nodes in the neighbor node set of node i being greater than or equal to the node quantity threshold and the weight sum of the neighbor node set of node i being greater than or equal to the weight threshold, node i is determined to be a key node, and in response to node k being located in the neighbor node set of node i and node i being a key node, node k is determined to be an important node of node i.

[0104] For example, for nodes A and B, if the number of nodes in the neighbor node set of node A is greater than or equal to the node number threshold minCount, and the weight and value of the neighbor node set of node A are If it is greater than or equal to the weight threshold minWgt, node A is a key node; if node B is in the neighboring node set of node A and node A is a key node, node B is an important node of node A.

[0105] In an embodiment of the present disclosure, the maximum number of edges from node i to node j is determined in the second transaction directed graph, and based on the maximum number of edges, the transaction path length between node i and node j is determined, and a preset transaction path length threshold len is obtained. In response to the transaction path length between node i and node j being less than or equal to the transaction path length threshold, node j is treated as a neighbor node of node i in the second transaction directed graph, wherein the neighbor node set includes all neighbor nodes of node i.

[0106] For example, Figure 5 As shown, node A 1 and node A2 There is a transaction, node A 2 and node A 4 If there is a transaction, then node A 1 With node A 2 The transaction path length between them is 2.

[0107] S702, dividing each key node and the important nodes of each key node into a candidate node set, and determining whether there are identical nodes in the candidate node set.

[0108] S703, in response to the existence of identical nodes in the candidate node set, merge the candidate node set until there are no identical nodes in the merged candidate node set, thereby obtaining a node set in the second transaction directed graph.

[0109] For example, node A is a key node, node B and node C are important nodes of node A, and account node B and node C are also key nodes, node D is an important node of node B, and node E is an important node of node C. Then nodes A, B, C, D, and E are merged and divided into the same node set.

[0110] S3012, obtaining a target transaction tag prediction value of each node in the node set, and determining a second recognition result of the second transaction data according to the target transaction tag prediction value.

[0111] As a possible way to achieve this, Figure 8 As shown, based on the above implementation, the specific process of obtaining the target transaction tag prediction value of each node in the node set in step S2012 and determining the second recognition result of the second transaction data according to the target transaction tag prediction value includes steps S801 to S805:

[0112] S801, obtaining target transaction data corresponding to each node in the node set.

[0113] In the embodiment of the present disclosure, after the node set in the second transaction directed graph is obtained, the target transaction data corresponding to each node in the node set may be obtained.

[0114] S802, obtaining a target feature vector of the target transaction data, and inputting the target feature vector into a pre-trained supervised transaction recognition model to obtain a target transaction label prediction value.

[0115] In the disclosed embodiment of the present invention, after obtaining the target transaction data, feature extraction can be performed on the target transaction data to obtain a target feature vector of the target transaction data, and the target feature vector is input into a pre-trained supervised transaction recognition model, and the supervised transaction recognition model outputs a target transaction label prediction value y n .

[0116] S803, accumulating the target transaction tag prediction values ​​to obtain the target transaction tag prediction and value of the node set.

[0117] For example, for the node set {A} in the second transaction directed graph, if the node set {A} includes node A 1 Node A 2 and node A 3 , node A 1 Node A 2 and node A 3 The target transaction label prediction values ​​are y 1 ,y 2 and 3 , then the target transaction label prediction and value y of the node set {A} sum =y 1 +y 2 +y 3 .

[0118] S804: In response to the target transaction tag prediction and value being less than a preset second threshold, determining that all transaction data in the node set are abnormal.

[0119] It should be noted that the present disclosure does not limit the setting of the second threshold bad_score, and it can be set according to actual conditions.

[0120] For example, if the node set {A} includes node A 1 , A 2 and A 3 , the target transaction label prediction and value y of the node set {A} sum , if the target transaction label prediction and value y sum If the score is less than the preset second threshold bad_score, it is determined that the transaction data in the node set are all abnormal, that is, node A 1 Node A 2 and node A 3 The transaction data are all abnormal.

[0121] S805 , in response to the target transaction tag prediction and value being greater than or equal to a preset second threshold, determining that the transaction data in the node set are all normal.

[0122] For example, if the node set {A} includes node A 1 , A 2 and A 3 , the target transaction label prediction and value y of the node set {A} sum , if the target transaction label prediction and value y sumIf the score is greater than or equal to the preset second threshold bad_score, it is determined that the transaction data in the node set is normal, that is, node A 1 Node A 2 and node A 3 The transaction data are all normal.

[0123] S3013: Filter the third transaction data having anomalies from the second transaction data according to the second identification result.

[0124] In the embodiment of the present disclosure, after the second recognition result is obtained, the third transaction data with abnormalities can be screened from the second transaction data.

[0125] In summary, according to the transaction identification method provided by the embodiment of the present disclosure, based on the transaction account and the transaction transfer relationship between every two transaction accounts, a first transaction directed graph is constructed, wherein the nodes of the first transaction directed graph are transaction accounts, and the edges of the first transaction directed graph are transaction transfer relationships between every two transaction accounts, and the initial transaction identification model is supervisedly trained through the training sample set to obtain a supervised transaction identification model, the first transaction data is identified through the supervised transaction identification model, the normal transaction data in the first transaction data is determined, the first transaction directed graph is cropped based on the normal transaction data to obtain a second transaction directed graph, and the nodes in the second transaction directed graph are trained. The method comprises the following steps: performing row division, obtaining a node set of the second transaction directed graph, determining a second recognition result of the second transaction data according to a target transaction label prediction value of each node in the node set, and screening out abnormal third transaction data from the second transaction data according to the second recognition result. Thus, the present invention can recognize a large amount of transaction data, improve the efficiency of obtaining abnormal transaction data, reduce the time of manual monitoring and identifying abnormal transaction data, avoid the problems of omissions and misjudgments in the transaction data identification process due to subjective factors, and does not rely on pre-set rules, thereby ensuring the objectivity of the transaction identification result and improving the accuracy and reliability of obtaining abnormal transaction identification data.

[0126] Fig. 9 FIG. 4 is a block diagram of a transaction identification device according to a first embodiment of the present disclosure.

[0127] like Fig. 9 As shown, the transaction identification device 900 of the embodiment of the present disclosure includes: a first acquisition module 901 , a second acquisition module 902 , a determination module 903 , a clipping module 904 and an identification module 905 .

[0128] A first acquisition module 901 is configured to acquire first transaction data to be identified, and acquire transaction accounts and transaction transfer relationships between every two transaction accounts from the first transaction data;

[0129] A second acquisition module 902 is configured to construct a first transaction directed graph based on the transaction account and the transaction transfer relationship between each two transaction accounts;

[0130] The determination module 903 is configured to identify the first transaction data, obtain a first identification result of the first transaction data, and determine normal transaction data in the first transaction data according to the first identification result;

[0131] A trimming module 904 is configured to trim the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph;

[0132] The identification module 905 is configured to determine the second transaction data according to the nodes in the second transaction directed graph, and identify the second transaction data to filter out abnormal third transaction data from the second transaction data.

[0133] In one embodiment of the present disclosure, the trimming module 904 is further configured to: obtain a first transaction account and a second transaction account having a transaction transfer relationship in the normal transaction data; determine a first node associated with the first transaction account and a second node associated with the second transaction account in the first transaction directed graph; and delete the edge between the first node and the second node to obtain the second transaction directed graph.

[0134] In one embodiment of the present disclosure, the identification module 905 is further configured to: obtain the transaction probability of each node in the second transaction directed graph, and use the transaction probability as the weight of each node in the second transaction directed graph; divide the nodes in the second transaction directed graph according to the weights to obtain a node set of the second transaction directed graph; obtain a target transaction label prediction value for each node in the node set, and determine a second identification result of the second transaction data based on the target transaction label prediction value; and filter out abnormal third transaction data from the second transaction data based on the second identification result.

[0135] In one embodiment of the present disclosure, the identification module 905 is further configured to: obtain the number of nodes in the second transaction directed graph, and initialize the first probability of each node having a transaction at time t according to the number of nodes; iterate the second probability of each node having a transaction at time t+1 according to the first probability, and in response to satisfying the iteration end condition, use the second probability corresponding to the last iteration as the transaction probability of each node in the second transaction directed graph.

[0136] In one embodiment of the present disclosure, the identification module 905 is further configured to: obtain the key nodes and the important nodes of the key nodes in the second transaction directed graph; divide each of the key nodes and the important nodes of each of the key nodes into a candidate node set, and determine whether there are identical nodes in the candidate node set; in response to the existence of identical nodes in the candidate node set, merge the candidate node set until there are no identical nodes in the merged candidate node set, and obtain the node set in the second transaction directed graph.

[0137] In one embodiment of the present disclosure, the identification module 905 is further configured to: obtain a node quantity threshold and a weight threshold preset for a node set; obtain a transaction path length between node i and node j, and determine a neighbor node set of node i in the second transaction directed graph based on the transaction path length; in response to the number of nodes in the neighbor node set of node i being greater than or equal to the node quantity threshold and the weight and value of the neighbor node set of node i being greater than or equal to the weight threshold, determine that node i is a key node; in response to node k being in the neighbor node set of node i and node i being a key node, determine that node k is an important node of node i.

[0138] In one embodiment of the present disclosure, the identification module 905 is further configured to: determine the maximum number of edges from node i to node j in the second transaction directed graph; based on the maximum number of edges, determine the transaction path length between node i and node j to obtain a preset transaction path length threshold; in response to the transaction path length between node i and node j being less than or equal to the transaction path length threshold, treat node j as a neighbor node of node i in the second transaction directed graph, wherein the neighbor node set includes all neighbor nodes of node i.

[0139] In one embodiment of the present disclosure, the identification module 905 is further configured to: obtain target transaction data corresponding to each node in the node set; obtain a target feature vector of the target transaction data, and input the target feature vector into a pre-trained supervised transaction recognition model to obtain the target transaction label prediction value; accumulate the target transaction label prediction values ​​to obtain the target transaction label prediction and value of the node set; in response to the target transaction label prediction and value being less than a preset second threshold, determine that the transaction data in the node set are all abnormal; or, in response to the target transaction label prediction and value being greater than or equal to the preset second threshold, determine that the transaction data in the node set are all normal.

[0140] In one embodiment of the present disclosure, the determination module 903 is further configured to: obtain a feature vector of the first transaction data, input the feature vector into a pre-trained supervised transaction recognition model, and obtain a first transaction label prediction value of the first transaction data; in response to the first transaction label prediction value being greater than a preset first threshold, determine that the first transaction data is normal transaction data; or, in response to the first transaction label prediction value being less than or equal to a preset first threshold, determine that the first transaction data is abnormal transaction data.

[0141] In one embodiment of the present disclosure, the training process of the supervised transaction recognition model includes: obtaining a training sample set, wherein each training sample in the training sample set includes sample transaction data and a true value of a sample transaction label; obtaining a sample feature vector of the sample transaction data, inputting the sample feature vector into the initial transaction recognition model to obtain a transaction label prediction value; and performing supervised training on the initial transaction recognition model according to the true value of the sample transaction label and the transaction label prediction value to obtain the supervised transaction recognition model.

[0142] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0143] In summary, the transaction identification device provided by the embodiment of the present disclosure obtains the first transaction data to be identified, and obtains the transaction transfer relationship between the transaction account and every two transaction accounts from the first transaction data, constructs a first transaction directed graph based on the transaction account and the transaction transfer relationship between every two transaction accounts, identifies the first transaction data, obtains a first identification result of the first transaction data, determines normal transaction data in the first transaction data based on the first identification result, trims the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph, determines the second transaction data based on the nodes in the second transaction directed graph, and identifies the second transaction data to filter out abnormal third transaction data from the second transaction data. Therefore, the present disclosure can identify massive transaction data, improve the efficiency of identifying abnormal transaction data, ensure the objectivity of obtaining abnormal transaction identification data, save cost and time in the transaction identification process, and improve the accuracy and reliability of obtaining abnormal transaction identification data.

[0144] Fig.10 It is a block diagram of an electronic device according to an exemplary embodiment.

[0145] like Fig.10 As shown, the electronic device 1000 includes:

[0146] The memory 1010 and the processor 1020, the bus 1030 connecting different components (including the memory 1010 and the processor 1020), the memory 1010 stores a computer program, and when the processor 1020 executes the program, the transaction identification method described in the embodiment of the present disclosure is implemented.

[0147] Bus 1030 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0148] The electronic device 1000 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by the electronic device 1000, including volatile and non-volatile media, removable and non-removable media.

[0149] The memory 1010 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 1040 and / or cache memory 1050. The electronic device 1000 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 1060 may be used to read and write non-removable, non-volatile magnetic media ( Fig.10 not shown, usually called a "hard drive"). Although Fig.10 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 1030 via one or more data medium interfaces. The memory 1010 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present disclosure.

[0150] A program / utility 1080 having a set (at least one) of program modules 1070 may be stored, for example, in the memory 1010, such program modules 1070 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 1070 generally perform the functions and / or methods of the embodiments described in the present disclosure.

[0151] The electronic device 1000 may also communicate with one or more external devices 1090 (e.g., keyboard, pointing device, display 1091, etc.), one or more devices that enable a user to interact with the electronic device 1000, and / or any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 1092. Furthermore, the electronic device 1000 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 1093. Fig.10 As shown, the network adapter 1093 communicates with other modules of the electronic device 1000 via the bus 1030. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0152] The processor 1020 executes various functional applications and data processing by running the programs stored in the memory 1010 .

[0153] It should be noted that the implementation process and technical principles of the electronic device of this embodiment refer to the aforementioned explanation of the transaction identification method of the embodiment of the present disclosure, and will not be repeated here.

[0154] In summary, the electronic device provided by the embodiment of the present disclosure can execute the transaction identification method as described above, by obtaining the first transaction data to be identified, and obtaining the transaction transfer relationship between the transaction account and every two transaction accounts from the first transaction data, constructing a first transaction directed graph based on the transaction account and the transaction transfer relationship between every two transaction accounts, identifying the first transaction data, and obtaining a first identification result of the first transaction data. According to the first identification result, normal transaction data in the first transaction data is determined, and the first transaction directed graph is trimmed based on the normal transaction data to obtain a second transaction directed graph. According to the nodes in the second transaction directed graph, the second transaction data is determined, and the second transaction data is identified to filter out abnormal third transaction data from the second transaction data. Therefore, the present disclosure can identify massive transaction data, improve the efficiency of identifying abnormal transaction data, ensure the objectivity of obtaining abnormal transaction identification data, save cost and time in the transaction identification process, and improve the accuracy and reliability of obtaining abnormal transaction identification data.

[0155] In order to implement the above embodiments, the present disclosure also proposes a computer-readable storage medium.

[0156] When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can perform the above-mentioned or the transaction identification method as described above. Optionally, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0157] In order to implement the above embodiments, the present disclosure further provides a computer program product, including a computer program, characterized in that when the computer program is executed by a processor, the transaction identification method as described above is implemented.

[0158] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0159] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A transaction identification method, characterized in that: The method comprises: Acquire first transaction data to be identified, and acquire transaction accounts and transaction transfer relationships between every two transaction accounts from the first transaction data; Constructing a first transaction directed graph based on the transaction account and the transaction transfer relationship between each two transaction accounts; identifying the first transaction data, obtaining a first identification result of the first transaction data, and determining normal transaction data in the first transaction data according to the first identification result; Cutting the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph; The second transaction data is determined according to the nodes in the second transaction directed graph, and the second transaction data is identified to filter out abnormal third transaction data from the second transaction data.

2. The identification method according to claim 1, characterized in that: The step of trimming the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph includes: Acquire a first transaction account and a second transaction account having a transaction transfer relationship in the normal transaction data; Determining, in the first transaction directed graph, a first node associated with the first transaction account and a second node associated with the second transaction account; The edge between the first node and the second node is deleted to obtain the second transaction directed graph.

3. The identification method according to claim 2, characterized in that: The identifying the second transaction data to filter out abnormal third transaction data from the second transaction data includes: Obtaining a transaction probability of each node in the second transaction directed graph, and using the transaction probability as a weight of each node in the second transaction directed graph; Dividing the nodes in the second transaction directed graph according to the weights to obtain a node set of the second transaction directed graph; Obtaining a target transaction tag prediction value of each node in the node set, and determining a second recognition result of the second transaction data according to the target transaction tag prediction value; The third transaction data having anomalies is screened from the second transaction data according to the second recognition result.

4. The identification method according to claim 3, characterized in that: The obtaining the transaction probability of each node in the second transaction directed graph includes: Obtaining the number of nodes in the second transaction directed graph, and initializing a first probability of a transaction occurring at each node at time t according to the number of nodes; According to the first probability, the second probability of a transaction occurring at each node at time t+1 is iterated, and in response to satisfying an iteration end condition, the second probability corresponding to the last iteration is used as the transaction probability of each node in the second transaction directed graph.

5. The identification method according to claim 3, characterized in that: The dividing the nodes in the second transaction directed graph according to the weights to obtain a node set of the second transaction directed graph includes: Obtain the key nodes and important nodes of the key nodes in the second transaction directed graph; Divide each of the key nodes and each of the important nodes of the key nodes into a candidate node set, and determine whether there are identical nodes in the candidate node set; In response to the existence of identical nodes in the candidate node set, the candidate node set is merged until there are no identical nodes in the merged candidate node set, thereby obtaining a node set in the second transaction directed graph.

6. The identification method according to claim 5, characterized in that: The acquiring of the key nodes and the important nodes of the key nodes in the second transaction directed graph includes: Get the node quantity threshold and weight threshold preset for the node set; Obtaining a transaction path length between node i and node j, and determining a set of neighboring nodes of node i in the second transaction directed graph according to the transaction path length; In response to the number of nodes in the neighboring node set of the node i being greater than or equal to the node number threshold and the weight sum value of the neighboring node set of the node i being greater than or equal to the weight threshold, determining that the node i is a key node; In response to the node k being in the neighbor node set of the node i and the node i being a key node, the node k is determined to be an important node of the node i.

7. The identification method according to claim 3, characterized in that: The acquiring the transaction path length between node i and node j, and determining the neighboring node set of node i in the second transaction directed graph according to the transaction path length, includes: Determining a maximum number of edges from node i to node j in the second transaction directed graph; Based on the maximum number of edges, determine the transaction path length between node i and node j Get the preset transaction path length threshold; In response to the transaction path length between the node i and the node j being less than or equal to the transaction path length threshold, the node j is used as a neighbor node of the node i in the second transaction directed graph, wherein the neighbor node set includes all neighbor nodes of the node i.

8. The identification method according to claim 3, characterized in that: The acquiring the target transaction tag prediction value of each node in the node set and determining the second recognition result of the second transaction data according to the target transaction tag prediction value includes: Obtain target transaction data corresponding to each node in the node set; Obtaining a target feature vector of the target transaction data, and inputting the target feature vector into a pre-trained supervised transaction recognition model to obtain a predicted value of the target transaction label; Accumulating the target transaction tag prediction values ​​to obtain the target transaction tag prediction and value of the node set; In response to the target transaction tag prediction and value being less than a preset second threshold, determining that all transaction data in the node set are abnormal; or, In response to the target transaction tag prediction and value being greater than or equal to a preset second threshold, it is determined that the transaction data in the node set are all normal.

9. The identification method according to claim 1, characterized in that: The identifying the first transaction data to obtain a first identification result of the first transaction data includes: Acquire a feature vector of the first transaction data, input the feature vector into a pre-trained supervised transaction recognition model, and obtain a first transaction label prediction value of the first transaction data; In response to the first transaction tag prediction value being greater than a preset first threshold, determining that the first transaction data is normal transaction data; or, In response to the first transaction tag prediction value being less than or equal to a preset first threshold, the first transaction data is determined to be abnormal transaction data.

10. The identification method according to claim 9, characterized in that: The training process of the supervised transaction recognition model includes: Acquire a training sample set, wherein each training sample in the training sample set includes sample transaction data and a true value of a sample transaction label; Obtaining a sample feature vector of the sample transaction data, inputting the sample feature vector into the initial transaction recognition model, and obtaining a transaction label prediction value; According to the true value of the sample transaction label and the predicted value of the transaction label, the initial transaction recognition model is supervised trained to obtain the supervised transaction recognition model.

11. A transaction identification device, characterized in that: The device comprises: A first acquisition module is configured to acquire first transaction data to be identified, and acquire transaction accounts and transaction transfer relationships between every two transaction accounts from the first transaction data; A second acquisition module is configured to construct a first transaction directed graph based on the transaction account and the transaction transfer relationship between every two transaction accounts; a determination module configured to identify the first transaction data, obtain a first identification result of the first transaction data, and determine normal transaction data in the first transaction data according to the first identification result; A trimming module, configured to trim the first transaction directed graph based on the normal transaction data to obtain a second transaction directed graph; The identification module is configured to determine the second transaction data according to the nodes in the second transaction directed graph, and identify the second transaction data to filter out the abnormal third transaction data from the second transaction data.

12. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the transaction identification method according to any one of claims 1-10.

13. A computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the transaction identification method according to any one of claims 1 to 10.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the transaction identification method according to any one of claims 1 to 10 is implemented.

Citation Information

Patent Citations

  • Method and device for identifying associated specific account and storage medium

    CN111831923A

  • Network training method, abnormal transaction behavior identification method and device, and medium

    CN112435122A

  • Abnormal account identification method and device and storage medium

    CN116188020A

  • Method and device for obtaining transaction dependency relationship in blockchain

    WO2021047541A1