Method, device, storage medium and electronic device for determining transaction risk

Abstract

The present application discloses a method, device, storage medium, and electronic device for determining transaction risks. The method includes: obtaining transaction information generated when a user conducts a transaction with a merchant, where the transaction information includes at least one of the following: user data, merchant data; inputting the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; inputting the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; calculating the difference between the first risk probability and the second risk probability to obtain a first difference; and determining the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability. Through the present application, the problem in the related art of being unable to efficiently and accurately control transaction risks is solved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and specifically, to a method, device, storage medium and electronic device for determining transaction risks. Background Art

[0002] In recent years, with the rapid development of e-commerce merchants, online payment has become an important support for the development of e-commerce. As more and more users use the Internet to conduct transactions, the Internet acquiring industry has developed synchronously, and its business has involved various fields such as cash withdrawal, business activities, tourism, shopping, and consumption. In particular, the Internet acquiring business belongs to the card not present (CNP) payment model, which has many transaction risks.

[0003] At present, traditional acquiring business is usually controlled by major financial institutions using a three-in-one control method of pre-, in-, and post-monitoring. Among them, pre-risk monitoring mainly relies on evaluating the risk status of merchants before signing contracts. The evaluation process is complex and inefficient, and the evaluation results are too subjective, resulting in low evaluation accuracy. Post-risk control usually analyzes the transaction big data after completion, and matches historical transaction information by formulating a series of expert rules. The accuracy of post-risk control is high, but the efficiency is low and the response is slow. Risks are often discovered some time after the transaction. At this time, the risk has already occurred and only subsequent remedial measures can be adopted. In-process monitoring is to monitor each ongoing transaction in a timely manner, and to judge the risk of ongoing transactions through key features and other methods, but the accuracy of the judgment is low, and there may be a phenomenon of being too tight or too loose.

[0004] Currently, no effective solution has been proposed to address the problem that related technologies cannot efficiently and accurately manage transaction risks. Summary of the invention

[0005] The present application provides a method, device, storage medium and electronic device for determining transaction risk to solve the problem in related technologies that transactions cannot be efficiently and accurately managed and controlled.

[0006] According to one aspect of the present application, a method for determining transaction risk is provided. The method includes: obtaining transaction information generated when a user and a merchant trade, wherein the transaction information includes at least one of the following: user data and merchant data; inputting the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; inputting the transaction information into a target cluster analysis model to obtain a second risk probability corresponding to the transaction information; calculating the difference between the first risk probability and the second risk probability to obtain a first difference; determining the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability and the second risk probability.

[0007] Optionally, determining the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability includes: determining whether the first difference is within a preset range; in the case where the first difference is within the preset range, determining the risk level corresponding to the transaction information according to the first risk probability or the second risk probability; in the case where the first difference is not within the preset range, determining the risk level corresponding to the transaction information according to the transaction information, the first risk probability, and the second risk probability.

[0008] Optionally, in the case where the first difference is not within the preset range, determining the risk level corresponding to the transaction information according to the transaction information, the first risk probability, and the second risk probability includes: inputting the transaction information into a level determination model to obtain a third risk probability corresponding to the transaction information; calculating the difference between the third risk probability and the first risk probability to obtain a second difference; calculating the difference between the third risk probability and the second risk probability to obtain a third difference; in the case where the second difference is greater than the third difference, determining the risk level corresponding to the second risk probability as the risk level of the transaction information; in the case where the second difference is less than the third difference, determining the risk level corresponding to the first risk probability as the risk level of the transaction information; in the case where the first difference is equal to the second difference, determining the high-risk probability from the first risk probability and the second risk probability, and determining the risk level corresponding to the high-risk probability as the risk level of the transaction information.

[0009] Optionally, inputting the transaction information into a level determination model to obtain a third risk probability corresponding to the transaction information includes: obtaining characteristic information of the transaction information to obtain at least one piece of characteristic information; respectively determining the characteristic risk probabilities of the at least one piece of characteristic information to obtain at least one characteristic risk probability; determining the risk probability of the transaction information according to the at least one characteristic risk probability to obtain a third risk probability.

[0010] Optionally, before inputting the transaction information into the target classification model to obtain the first risk probability corresponding to the transaction information, the method further includes: obtaining first sample information, where the first sample information includes a plurality of historical transaction information and the risk level corresponding to each historical transaction information; performing learning and training on the initial classification model through the first sample information to obtain the target classification model.

[0011] Optionally, the target classification model is a semi-supervised graph neural network model. Obtaining the first sample information includes: obtaining a plurality of historical transaction information and the risk level corresponding to each historical transaction information, where the historical transaction information includes at least one of the following: historical user data, historical merchant data; determining each historical user data as a source node, determining each historical merchant data as a target node, determining the transaction relationship between the historical user and the historical merchant as a directed edge, and determining the risk level of the historical transaction information corresponding to the transaction relationship as the value of the directed edge, to obtain directed graph structure data corresponding to a plurality of historical transaction information; determining the directed graph structure data as the first sample information.

[0012] Optionally, before inputting the transaction information into the target clustering analysis model to obtain the second risk probability corresponding to the transaction information, the method further includes: obtaining second sample information, where the second sample information includes a plurality of historical transaction information and the risk level corresponding to each historical transaction information; training the initial clustering analysis model with the second sample information to obtain the target clustering analysis model.

[0013] Optionally, training the initial clustering analysis model with the second sample information to obtain the target clustering analysis model includes: randomly generating a plurality of cluster centers in the initial clustering analysis model; calculating the belonging cluster corresponding to each historical transaction information, and updating the center point of each belonging cluster to obtain a plurality of clusters; obtaining historical transaction information with a risk level greater than the first risk threshold from each cluster to obtain a target number of historical transaction information; determining the risk level corresponding to each cluster according to the target number of historical transaction information, and determining the target clustering analysis model according to each cluster and the risk level corresponding to each cluster, where, when the target number is greater than or equal to the number threshold, determining the risk level corresponding to the cluster as the first risk level; when the target number is less than the number threshold, determining the risk level corresponding to the cluster as the second risk level, where the risk degree of the first risk level is higher than the risk degree of the second risk level.

[0014] According to another aspect of the present application, there is provided an apparatus for determining transaction risk. The apparatus includes: a first obtaining unit, configured to obtain transaction information generated when a user transacts with a merchant, where the transaction information includes at least one of the following: user data, merchant data; a first input unit, configured to input the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; a second input unit, configured to input the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; a calculation unit, configured to calculate the difference between the first risk probability and the second risk probability to obtain a first difference; a determination unit, configured to determine the risk level corresponding to the transaction information according to the first difference, the transaction information, the first risk probability, and the second risk probability.

[0015] According to another aspect of the embodiments of the present invention, there is also provided a computer storage medium for storing a program, wherein when the program runs, it controls a device where the computer storage medium is located to execute a method for determining transaction risks.

[0016] According to another aspect of the embodiments of the present invention, there is also provided an electronic device including one or more processors and a memory; computer-readable instructions are stored in the memory, and the processor is configured to run the computer-readable instructions, wherein when the computer-readable instructions run, they execute a method for determining transaction risks.

[0017] Through the present application, the following steps are adopted: obtaining transaction information generated when a user conducts a transaction with a merchant, wherein the transaction information includes at least one of the following: user data, merchant data; inputting the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; inputting the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; calculating the difference between the first risk probability and the second risk probability to obtain a first difference; determining a risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability, thereby solving the problem in the related art that transaction risk control cannot be efficiently and accurately performed. By simultaneously judging the transaction information through the target classification model and the target clustering analysis model, comparing the judgment results, and then comprehensively judging again through the judgment results and the transaction information, the transaction risk is determined, and thus the effect of accurately and efficiently controlling the transaction risk is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings constituting a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0019] Figure 1 is a flowchart of a method for determining transaction risks provided according to an embodiment of the present application;

[0020] Figure 2 is an optional directed graph structure provided according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a device for determining transaction risks provided according to an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other. The following will describe the present application in detail with reference to the accompanying drawings and in combination with the embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so as to describe the embodiments of the present application here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] It should be noted that the relevant information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in the present disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set between the present system and relevant users or institutions. Before obtaining relevant information, a request for obtaining information needs to be sent to the aforementioned users or institutions through the interface, and after receiving the consent information feedback from the aforementioned users or institutions, the relevant information is obtained.

[0027] It should be noted that the method, device, storage medium, and electronic device for determining transaction risks determined by the present disclosure can be used in the field of fintech, and can also be used in any field other than the field of fintech. The application fields of the method, device, storage medium, and electronic device for determining transaction risks determined by the present disclosure are not limited.

[0028] For the convenience of description, the following explains some nouns or terms related to the embodiments of the present application:

[0029] Acquiring business: Refers to the fund settlement service provided by a bank to merchants.

[0030] According to the embodiments of the present application, a method for determining transaction risks is provided.

[0031] Figure 1 is a flowchart of a method for determining transaction risk provided by an embodiment of the present application. As Figure 1 shown, the method includes the following steps:

[0032] Step S101, obtain transaction information generated when a user conducts a transaction with a merchant. Among them, the transaction information includes at least one of the following: user data, merchant data.

[0033] Specifically, the transaction information may be the transaction information when the user conducts a transaction with the merchant, including: user data, for example, the user's bank card account, the number of transactions of the user in the recent week, the transaction amount of the user in the recent week, etc. information, and also includes merchant data, for example, the merchant's account information, the number of transactions of the merchant in the recent week, the acquisition amount of the merchant in the recent week, etc. information, and may also include information such as the transaction amount and transaction time of this transaction, thus constituting the transaction information.

[0034] Step S102, input the transaction information into the target classification model to obtain a first risk probability corresponding to the transaction information.

[0035] Specifically, the target classification model may be a model used to determine the risk probability of a transaction, and the risk probability of a transaction can be determined through the transaction information to obtain the first risk probability. For example, the target classification model may be a neural network model trained through historical transactions. After inputting the transaction information into the neural network model, the risk probability determination result of the model for this transaction information can be directly obtained.

[0036] It should be noted that the risk probability may be a risk level, and the risk probability can indicate the probability of a certain transaction information being a certain risk. For example, the probability of transaction information A being a high risk is 20%, the probability of being a medium risk is 20%, and the probability of being a low risk is 60%. Therefore, the risk probability can be used as a manifestation form of a risk level.

[0037] To improve the accuracy of the target classification model in determining the risk probability of transaction information, optionally, in the method for determining transaction risk provided by an embodiment of the present application, before inputting the transaction information into the target classification model to obtain a first risk probability corresponding to the transaction information, the method further includes: obtaining first sample information, where the first sample information includes multiple historical transaction information and the risk level corresponding to each historical transaction information; learning and training the initial classification model through the first sample information to obtain the target classification model.

[0038] Specifically, before obtaining the target classification model, the initial classification model needs to be trained. The sample information used for training can be historical transaction information for which the transaction risk level has been determined. The historical transaction information is input into the initial classification model for training, and the training of the initial classification model is completed when the initial classification model can obtain the transaction risk level corresponding to each historical transaction information, thereby obtaining the target classification model. This embodiment achieves the effect of improving the determination of the first risk probability of transaction information.

[0039] To improve the training effect of the target classification model and the judgment accuracy of the target classification model. Optionally, in the method for determining transaction risk provided in the embodiments of the present application, the target classification model is a semi-supervised graph neural network model. Obtaining the first sample information includes: obtaining a plurality of historical transaction information and the risk level corresponding to each historical transaction information, where the historical transaction information includes at least one of the following: historical user data, historical merchant data; determining each historical user data as a source node, determining each historical merchant data as a target node, determining the transaction relationship between the historical user and the historical merchant as a directed edge, and determining the risk level of the historical transaction information corresponding to the transaction relationship as the value of the directed edge, obtaining directed graph structure data corresponding to a plurality of historical transaction information; determining the directed graph structure data as the first sample information.

[0040] Specifically, since the target classification model is a semi-supervised graph neural network model, sample information can be generated by connecting a plurality of historical transaction information into a graph, thereby training the semi-supervised graph neural network model so that the semi-supervised graph neural network model can more accurately determine the first risk probability of transaction information.

[0041] It should be noted that for the identification of the acquiring risk level of transaction information, it can be considered that there is an association between transaction information. The transaction information occurring between similar users and similar merchants is also roughly the same, with a high degree of homogeneity. A user may initiate multiple risky transactions, and a merchant may be involved in multiple risky transactions. The risks of transactions with unknown risks can be determined by the similar characteristics shown between these risk nodes. At the same time, the nodes will also affect each other. Related merchants may affect each other, resulting in phenomena such as the escalation of fraud means, leading to an increase in risky transactions among associated merchants.

[0042] Therefore, by constructing a relational graph of transaction information, a large amount of transaction information can be represented in a single relational graph, and the semi-supervised graph neural network model can be trained using the relational graph, so that the semi-supervised graph neural network model can accurately determine the risk level of transaction information with an unknown risk level. In the process of connecting multiple historical transaction information into a graph, users and merchants can be used as nodes, the transactions between users and merchants can be used as directed edges, and the risk level can be determined as the value of the directed edge. Figure 2 is an optional directed graph structure provided according to an embodiment of the present application, as Figure 2 shown. User A has a transaction with Merchant A, User B has transactions with Merchant A and Merchant B, and User C has transactions with Merchant A and Merchant B. Each directed edge is labeled according to the transaction risk level to obtain a transaction connection graph.

[0043] Furthermore, in the semi-supervised graph neural network model, Chebyshev first-order expansion approximation spectral convolution can be used. Each layer of convolution processes first-order neighborhood information, and then hierarchical propagation and superposition are used to achieve multi-order neighborhood information propagation. The graph structure can reflect the similarity between nodes. Adding a large number of samples (nodes) to the model helps to improve the sample classification effect. This algorithm is applicable to the acquiring risk transaction scenario. Nodes are constructed using users and merchants, and directed edges are constructed using transactions between accounts. Some node labels can be given according to verified risk transactions to predict whether unlabeled transactions are risky. This embodiment achieves the effect of improving the accuracy of the semi-supervised graph neural network model in judging the risk level of transaction information.

[0044] The convolution algorithm is described here. The Chebyshev approximation spectral convolution is:

[0045]

[0046] H (l) is the output of the previous convolution layer, which is represented as the embedding of this node, where H (0) = X, representing the self-feature of the node. is the first-order approximation convolution kernel, which can be understood as the weighted average adjacent feature and is used to learn the relationship between fraud accounts. σ is a non-linear activation unit, such as the relu function, and W (l) is the parameter of the convolution layer, which is shared by each node.

[0047] The main process of the algorithm is as follows:

[0048] 1. Prepare the training set, including labeled data verified by business personnel and unlabeled transaction data;

[0049] 2. Establish a feature matrix X according to the acquiring data;

[0050] 3. Establish an adjacency matrix A according to the transferor and transferee of the trading account;

[0051] 4. Preprocessing:

[0052] 5. for i = 1; i <= k - 1; do (k represents the number of convolutional layers);

[0053] (1) Convolve the i-th layer and perform a non-linear transformation;

[0054]

[0055] (2) Convolve the (i + 1)-th layer and perform a softmax transformation;

[0056]

[0057] In step S103, input the transaction information into the target clustering analysis model to obtain the second risk probability corresponding to the transaction information.

[0058] Specifically, the target clustering analysis model can be a model used to determine the risk probability of a transaction, and the risk probability of a transaction can be determined through the transaction information to obtain the second risk probability. For example, the target clustering analysis model can be a clustering model trained by historical transactions. After inputting the transaction information into the clustering model, the cluster to which the transaction information belongs can be judged through the clusters stored in the model, and thus the risk probability of the transaction information can be determined according to the risk probability of the cluster.

[0059] To improve the accuracy of the target clustering analysis model in determining the risk probability of transaction information, optionally, in the method for determining transaction risk provided in the embodiments of the present application, before inputting the transaction information into the target clustering analysis model to obtain the second risk probability corresponding to the transaction information, the method further includes: obtaining second sample information, where the second sample information includes multiple historical transaction information and the risk level corresponding to each historical transaction information; training the initial clustering analysis model through the second sample information to obtain the target clustering analysis model.

[0060] Specifically, before obtaining the target clustering analysis model, the initial clustering analysis model needs to be trained. The sample information used for training can be historical transaction information whose transaction risk level has been determined. The historical transaction information is input into the initial clustering analysis model for training, and the training of the initial clustering analysis model is completed when the initial clustering analysis model completes the clustering of historical transaction data and can accurately determine the transaction risk level corresponding to each historical transaction information through the clusters after clustering, so as to obtain the target clustering analysis model. This embodiment achieves the effect of improving the determination of the second risk probability of transaction information.

[0061] To improve the training effect of the target clustering analysis model and enhance the judgment accuracy of the target clustering analysis model. Optionally, in the method for determining transaction risks provided in the embodiments of the present application, training the initial clustering analysis model with the second sample information to obtain the target clustering analysis model includes: randomly generating multiple cluster centers in the initial clustering analysis model; calculating the belonging clusters corresponding to each historical transaction information and updating the center points of each belonging cluster to obtain multiple clusters; obtaining the historical transaction information with a risk level greater than the first risk threshold from each cluster to obtain the target number of historical transaction information; determining the risk level corresponding to each cluster according to the target number of historical transaction information, and determining the target clustering analysis model according to each cluster and the risk level corresponding to each cluster, where, when the target number is greater than or equal to the number threshold, determining the risk level corresponding to the cluster as the first risk level; when the target number is less than the number threshold, determining the risk level corresponding to the cluster as the second risk level, where the risk degree of the first risk level is higher than the risk degree of the second risk level.

[0062] Specifically, the K-means clustering method can be adopted in the target clustering analysis model for unsupervised clustering. First, randomly generate K cluster centers, and calculate the belonging clusters of each data according to each historical transaction information, so as to divide a large amount of historical transaction information into K clusters. Further, re-determine the center point of each cluster according to the dispersion of each historical transaction information in each cluster, so as to obtain the updated cluster center, and determine the cluster corresponding to the new transaction information according to the updated cluster center and the range of the cluster.

[0063] After dividing the historical transaction information into multiple clusters, it is possible to determine the historical transaction information with a risk level greater than the first risk threshold in each cluster, and determine the number of historical transaction information with a risk level greater than the first risk threshold, so that the second risk probability corresponding to each cluster can be determined by the number.

[0064] For example, the first risk threshold can be historical transaction information with a high-risk probability of 90%. At this time, it is possible to judge the number of historical transaction information with a high-risk probability greater than 90% in each cluster, and determine the risk level of each cluster according to the number. The number threshold can be 50%. When there is more than 50% of the historical transaction information in a cluster with a risk level of 90% probability of high risk, it can be determined that the risk level of the cluster is high risk. When there is less than 50% of the historical transaction information in a cluster with a risk level of 90% probability of high risk, it can be determined that the risk level of the cluster is low risk. It should be noted that in the present application, the number threshold can be one or more, and the types of risk levels of the clusters can also be two or more, so as to more accurately and diversely determine the risk level of the transaction information for application in different risk scenarios. This embodiment achieves the effect of improving the judgment accuracy of the risk level of transaction information by the target clustering analysis model.

[0065] Step S104, calculate the difference between the first risk probability and the second risk probability to obtain a first difference.

[0066] Specifically, the first risk probability and the second risk probability may not be exactly the same. At this time, it is necessary to judge whether the risk level of the transaction information can be directly determined using the first risk probability and the second risk probability according to the magnitude of the difference between the two.

[0067] Step S105, determine the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability.

[0068] Specifically, when the difference between the first risk probability and the second risk probability is too large, it may be caused by the misjudgment of a certain model. At this time, it is possible to make a judgment again based on information such as the transaction characteristics in the transaction information, so as to select the correct risk judgment result from the first risk probability and the second risk probability.

[0069] The method for determining transaction risk provided by the embodiments of the present application obtains transaction information generated when a user conducts a transaction with a merchant, where the transaction information includes at least one of the following: user data, merchant data; input the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; input the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; calculate the difference between the first risk probability and the second risk probability to obtain a first difference; determine the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability, solving the problem in the related art that transaction risk control cannot be carried out efficiently and accurately. By simultaneously judging the transaction information through the target classification model and the target clustering analysis model, comparing the judgment results, and making a comprehensive judgment again through the judgment results and the transaction information, the transaction risk is determined, and thus the effect of accurately and efficiently controlling the transaction risk is achieved.

[0070] To judge whether there is a misjudgment in the first risk probability and the second risk probability, optionally, determining the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability includes: judging whether the first difference is within a preset range; in the case where the first difference is within the preset range, determine the risk level corresponding to the transaction information according to the first risk probability or the second risk probability; in the case where the first difference is not within the preset range, determine the risk level corresponding to the transaction information according to the transaction information, the first risk probability, and the second risk probability.

[0071] Specifically, the first difference can be the difference between the first risk probability and the second risk probability. When the first difference is within a preset range, it proves that the difference between the first risk probability and the second risk probability is not significant, and it can be determined that the first risk probability and the second risk probability are correct in judging the transaction information. Therefore, any one of the first risk probability and the second risk probability can be selected as the risk level of the transaction information.

[0072] When the first difference is not within the preset range, it proves that the difference between the first risk probability and the second risk probability is too large, that is, there is an incorrect risk probability among the first risk probability and the second risk probability. At this time, it is necessary to make a comprehensive judgment through the risk level corresponding to the characteristic information in the transaction information, so as to select the correct risk probability from the first risk probability and the second risk probability as the risk level of the transaction information.

[0073] Optionally, in the method for determining transaction risk provided in the embodiments of the present application, when the first difference is not within the preset range, determining the risk level corresponding to the transaction information according to the transaction information, the first risk probability and the second risk probability includes: inputting the transaction information into a level determination model to obtain a third risk probability corresponding to the transaction information; calculating the difference between the third risk probability and the first risk probability to obtain a second difference; calculating the difference between the third risk probability and the second risk probability to obtain a third difference; when the second difference is greater than the third difference, determining the risk level corresponding to the second risk probability as the risk level of the transaction information; when the second difference is less than the third difference, determining the risk level corresponding to the first risk probability as the risk level of the transaction information; when the first difference is equal to the second difference, determining the high-risk probability from the first risk probability and the second risk probability, and determining the risk level corresponding to the high-risk probability as the risk level of the transaction information.

[0074] Specifically, when the first difference is not within the preset range, it is necessary to input the transaction information into the level determination model, determine the third risk probability of the transaction information through the level determination model, and compare the third risk probability with the first risk probability and the second risk probability, so as to judge which risk probability among the third risk probability, the first risk probability and the second risk probability is the closest, and thus determine the risk probability closest to the third risk probability as the risk level corresponding to the transaction information.

[0075] It should be noted that when the difference between the third risk probability and the first risk probability and the second risk probability is the same, in order to avoid high-risk transactions from passing the screening, the higher risk probability among the first risk probability and the second risk probability is determined as the risk level corresponding to the transaction information. This embodiment achieves the effect of accurately determining the risk level of the transaction information and avoiding misjudgment of high-risk level transaction information.

[0076] Optionally, in the method for determining transaction risk provided in the embodiments of the present application, inputting the transaction information into the level determination model to obtain the third risk probability corresponding to the transaction information includes: obtaining the characteristic information of the transaction information to obtain at least one piece of characteristic information; respectively determining the characteristic risk probabilities of at least one piece of characteristic information to obtain at least one characteristic risk probability; and determining the risk probability of the transaction information according to at least one characteristic risk probability to obtain the third risk probability.

[0077] Specifically, in the level determination model, the risk levels corresponding to multiple pieces of characteristic information are stored, and the risk level of the transaction information can be determined according to the risk level corresponding to the characteristic information corresponding to the transaction information, so as to obtain the third risk probability. Before using the level determination model, the risk levels corresponding to each piece of characteristic information can be determined through historical transaction information, where the historical transaction information are all high-risk transaction information. For continuous characteristics, such as the time interval between transactions and the number of initiation times, the consistency of the characteristic information in the risk transaction dataset can be evaluated, and whether there is an obvious difference in the variance between the risk transactions and normal transactions of the characteristic information can be evaluated, so as to output according to the consistency and variance difference, and determine the risk level of the characteristic information according to the risk level of the transaction information corresponding to the characteristic information; for non-continuous characteristics, traverse the values, analyze the fraud ratio of different values, and find the most likely fraud characteristic distribution; perform statistical analysis on the existing expert characteristics in the existing system, such as domain names, accounts, mobile phone numbers, device portraits, etc., to help discover other characteristics of fraudulent transactions, so as to accurately determine the risk levels of different types of characteristic information.

[0078] For example, obtain all high-risk transaction times, and judge the transaction time. It is found that most transaction times are between 0:00 and 3:00. At this time, obtain the transaction times of low-risk transaction information and find that most transaction times are between 12:00 and 15:00. Then it can be determined that the risk level corresponding to the characteristic information of 0:00 - 3:00 is high risk.

[0079] After determining the risk levels corresponding to different pieces of characteristic information, the third risk probability can be determined by means of machine learning or manual identification, and the risk level of the transaction information can be determined according to the third risk probability.

[0080] It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0081] The embodiments of the present application also provide a device for determining transaction risks. It should be noted that the device for determining transaction risks in the embodiments of the present application can be used to execute the method for determining transaction risks provided in the embodiments of the present application. The following introduces the device for determining transaction risks provided in the embodiments of the present application.

[0082] Figure 3 It is a schematic diagram of the device for determining transaction risks according to the embodiments of the present application. As Figure 3 shown, the device includes: a first acquisition unit 31, a first input unit 32, a second input unit 33, a calculation unit 34, and a determination unit 35.

[0083] The first acquisition unit 31 is used to acquire transaction information generated when a user conducts a transaction with a merchant. Among them, the transaction information includes at least one of the following: user data, merchant data;

[0084] The first input unit 32 is used to input the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information;

[0085] The second input unit 33 is used to input the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information;

[0086] The calculation unit 34 is used to calculate the difference between the first risk probability and the second risk probability to obtain a first difference;

[0087] The determination unit 35 is used to determine the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability.

[0088] For the device for determining transaction risks provided in the embodiments of the present application, the first acquisition unit 31 acquires transaction information generated when a user conducts a transaction with a merchant. Among them, the transaction information includes at least one of the following: user data, merchant data; the first input unit 32 inputs the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; the second input unit 33 inputs the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; the calculation unit 34 calculates the difference between the first risk probability and the second risk probability to obtain a first difference; the determination unit 35 determines the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability. This solves the problem in the related art that transaction risk control cannot be carried out efficiently and accurately. By simultaneously judging the transaction information through the target classification model and the target clustering analysis model, comparing the judgment results, and then comprehensively judging again through the judgment results and the transaction information, the transaction risk is determined, and thus the effect of accurately and efficiently controlling the transaction risk is achieved.

[0089] Optionally, in the transaction risk determination device provided in the embodiments of the present application, the determination unit 35 includes: a judgment subunit, configured to judge whether the first difference is within a preset range; a first determination subunit, configured to determine the risk level corresponding to the transaction information according to the first risk probability or the second risk probability when the first difference is within the preset range; and a second determination subunit, configured to determine the risk level corresponding to the transaction information according to the transaction information, the first risk probability, and the second risk probability when the first difference is not within the preset range.

[0090] Optionally, in the transaction risk determination device provided in the embodiments of the present application, the second determination subunit includes: an input module, configured to input the transaction information into a level determination model to obtain a third risk probability corresponding to the transaction information; a calculation module, configured to calculate the difference between the third risk probability and the first risk probability to obtain a second difference; a second calculation module, configured to calculate the difference between the third risk probability and the second risk probability to obtain a third difference; a first determination module, configured to determine the risk level corresponding to the second risk probability as the risk level of the transaction information when the second difference is greater than the third difference; a second determination module, configured to determine the risk level corresponding to the first risk probability as the risk level of the transaction information when the second difference is less than the third difference; and a third determination module, configured to determine the high-risk probability from the first risk probability and the second risk probability and determine the risk level corresponding to the high-risk probability as the risk level of the transaction information when the first difference is equal to the second difference.

[0091] Optionally, in the transaction risk determination device provided in the embodiments of the present application, the input module includes: an acquisition sub-module, configured to acquire the feature information of the transaction information to obtain at least one piece of feature information; a first determination sub-module, configured to respectively determine the feature risk probabilities of the at least one piece of feature information to obtain at least one feature risk probability; and a second determination sub-module, configured to determine the risk probability of the transaction information according to the at least one feature risk probability to obtain a third risk probability.

[0092] Optionally, in the transaction risk determination device provided in the embodiments of the present application, the device further includes: a second acquisition unit, configured to acquire first sample information, where the first sample information includes a plurality of historical transaction information and the risk level corresponding to each historical transaction information; and a first training unit, configured to perform learning and training on the initial classification model through the first sample information to obtain a target classification model.

[0093] Optionally, in the transaction risk determination device provided in the embodiments of the present application, the target classification model is a semi-supervised graph neural network model, and the second acquisition unit includes: a first acquisition subunit, configured to acquire a plurality of historical transaction information and the risk level corresponding to each historical transaction information, where the historical transaction information includes at least one of the following: historical user data, historical merchant data; a first determination subunit, configured to determine each historical user data as a source node, determine each historical merchant data as a target node, determine the transaction relationship between the historical user and the historical merchant as a directed edge, and determine the risk level of the historical transaction information corresponding to the transaction relationship as the value of the directed edge, to obtain directed graph structure data corresponding to the plurality of historical transaction information; a second determination subunit, configured to determine the directed graph structure data as the first sample information.

[0094] Optionally, in the transaction risk determination device provided in the embodiments of the present application, the device further includes: a third acquisition unit, configured to acquire second sample information, where the second sample information includes a plurality of historical transaction information and the risk level corresponding to each historical transaction information; a second training unit, configured to train an initial clustering analysis model with the second sample information to obtain a target clustering analysis model.

[0095] Optionally, in the transaction risk determination device provided in the embodiments of the present application, the second training unit includes: a generation subunit, configured to randomly generate a plurality of cluster centers in the initial clustering analysis model; a calculation subunit, configured to calculate the belonging cluster corresponding to each historical transaction information and update the center point of each belonging cluster to obtain a plurality of clusters; a second acquisition subunit, configured to acquire historical transaction information with a risk level greater than a first risk threshold from each cluster to obtain a target number of historical transaction information; a third determination subunit, configured to determine the risk level corresponding to each cluster according to the target number of historical transaction information, and determine the target clustering analysis model according to each cluster and the risk level corresponding to each cluster, where, when the target number is greater than or equal to a number threshold, the risk level corresponding to the cluster is determined as the first risk level; a fourth determination subunit, configured to, when the target number is less than the number threshold, determine the risk level corresponding to the cluster as the second risk level, where the risk degree of the first risk level is higher than the risk degree of the second risk level.

[0096] The above-mentioned transaction risk determination device includes a processor and a memory. The above-mentioned first acquisition unit 31, first input unit 32, second input unit 33, calculation unit 34, determination unit 35, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to implement corresponding functions.

[0097] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set, and by adjusting the kernel parameters, the problem in the related art of being unable to efficiently and accurately control the transaction risk is solved.

[0098] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.

[0099] An embodiment of the present invention provides a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, the method for determining the transaction risk is implemented.

[0100] An embodiment of the present invention provides a processor, which is used to run a program, and when the program runs, the method for determining the transaction risk is executed.

[0101] As Figure 4 shown, an embodiment of the present invention provides an electronic device. The electronic device 40 includes a processor, a memory, and a program stored on the memory and executable on the processor. When the processor executes the program, the following steps are implemented: obtaining transaction information generated when a user conducts a transaction with a merchant, where the transaction information includes at least one of the following: user data, merchant data; inputting the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; inputting the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; calculating the difference between the first risk probability and the second risk probability to obtain a first difference; determining the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability. The device herein can be a server, a PC, a PAD, a mobile phone, etc.

[0102] The present application also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program initialized with the following method steps: obtaining transaction information generated when a user conducts a transaction with a merchant, where the transaction information includes at least one of the following: user data, merchant data; inputting the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; inputting the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; calculating the difference between the first risk probability and the second risk probability to obtain a first difference; determining the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability.

[0103] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0104] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0105] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0107] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0108] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0109] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0110] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0111] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining transaction risk, characterized in that, it includes: Obtain transaction information generated when a user conducts a transaction with a merchant, where the transaction information includes at least one of the following: user data, merchant data; Input the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; Input the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; Calculate the difference between the first risk probability and the second risk probability to obtain a first difference; Determine the risk level corresponding to the transaction information based on the first difference, the transaction information, the first risk probability, and the second risk probability, including: Judge whether the first difference is within a preset range; When the first difference is within the preset range, determine the risk level corresponding to the transaction information according to the first risk probability or the second risk probability; When the first difference is not within the preset range, determine the risk level corresponding to the transaction information according to the transaction information, the first risk probability, and the second risk probability, including: Input the transaction information into a level determination model to obtain a third risk probability corresponding to the transaction information; calculate the difference between the third risk probability and the first risk probability to obtain a second difference; calculate the difference between the third risk probability and the second risk probability to obtain a third difference; when the second difference is greater than the third difference, determine the risk level corresponding to the second risk probability as the risk level of the transaction information; when the second difference is less than the third difference, determine the risk level corresponding to the first risk probability as the risk level of the transaction information; when the first difference is equal to the second difference, determine the high-risk probability from the first risk probability and the second risk probability, and determine the risk level corresponding to the high-risk probability as the risk level of the transaction information.

2. The method according to claim 1, characterized in that, Inputting the transaction information into a level determination model to obtain a third risk probability corresponding to the transaction information includes: Obtain the feature information of the transaction information to obtain at least one piece of the feature information; Respectively determine the feature risk probabilities of at least one piece of the feature information to obtain at least one feature risk probability; Determine the risk probability of the transaction information according to the at least one feature risk probability to obtain the third risk probability.

3. The method according to claim 1, characterized in that, Before inputting the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information, the method further includes: Obtain first sample information, where the first sample information includes a plurality of historical transaction information and the risk level corresponding to each piece of the historical transaction information; Learn and train an initial classification model through the first sample information to obtain the target classification model.

4. The method according to claim 3, characterized in that, The target classification model is a semi-supervised graph neural network model, and obtaining first sample information includes: Obtain the multiple historical transaction information and the risk level corresponding to each piece of the historical transaction information, where the historical transaction information includes at least one of the following: historical user data, historical merchant data; Determine each piece of the historical user data as a source node, determine each piece of the historical merchant data as a target node, determine the transaction relationship between the historical user and the historical merchant as a directed edge, and determine the risk level of the historical transaction information corresponding to the transaction relationship as the value of the directed edge, to obtain the directed graph structure data corresponding to the multiple historical transaction information; Determine the directed graph structure data as the first sample information.

5. The method according to claim 1, wherein, before inputting the transaction information into the target clustering analysis model to obtain the second risk probability corresponding to the transaction information, the method further includes: Obtain second sample information, where the second sample information includes multiple historical transaction information and the risk level corresponding to each piece of the historical transaction information; Train the initial clustering analysis model with the second sample information to obtain the target clustering analysis model.

6. The method according to claim 5, wherein, Training the initial clustering analysis model with the second sample information to obtain the target clustering analysis model includes: Randomly generate multiple cluster centers in the initial clustering analysis model; Calculate the belonging cluster corresponding to each piece of the historical transaction information, and update the center point of each belonging cluster to obtain multiple clusters; Obtain the historical transaction information with a risk level greater than the first risk threshold from each of the clusters to obtain a target number of historical transaction information; Determine the risk level corresponding to each of the clusters according to the target number of historical transaction information, and determine the target clustering analysis model according to each of the clusters and the risk level corresponding to each cluster, where when the target number is greater than or equal to the number threshold, determine the risk level corresponding to the cluster as the first risk level; when the target number is less than the number threshold, determine the risk level corresponding to the cluster as the second risk level, where the risk degree of the first risk level is higher than the risk degree of the second risk level.

7. A device for determining transaction risk, wherein, comprises: A first acquisition unit, configured to acquire transaction information generated when a user transacts with a merchant, where the transaction information includes at least one of the following: user data, merchant data; A first input unit, configured to input the transaction information into a target classification model to obtain a first risk probability corresponding to the transaction information; A second input unit, configured to input the transaction information into a target clustering analysis model to obtain a second risk probability corresponding to the transaction information; A calculation unit, configured to calculate the difference between the first risk probability and the second risk probability to obtain a first difference; A determination unit, configured to determine the risk level corresponding to the transaction information according to the first difference, the transaction information, the first risk probability, and the second risk probability; The determining unit includes: a judging subunit, configured to judge whether the first difference is within a preset range; a first determining subunit, configured to, when the first difference is within the preset range, determine a risk level corresponding to the transaction information according to the first risk probability or the second risk probability; and a second determining subunit, configured to, when the first difference is not within the preset range, determine a risk level corresponding to the transaction information according to the transaction information, the first risk probability, and the second risk probability: The second determining subunit includes: an input module, configured to input the transaction information into a level determining model to obtain a third risk probability corresponding to the transaction information; a calculating module, configured to calculate a difference between the third risk probability and the first risk probability to obtain a second difference; a second calculating module, configured to calculate a difference between the third risk probability and the second risk probability to obtain a third difference; a first determining module, configured to, when the second difference is greater than the third difference, determine the risk level corresponding to the second risk probability as the risk level of the transaction information; a second determining module, configured to, when the second difference is less than the third difference, determine the risk level corresponding to the first risk probability as the risk level of the transaction information; and a third determining module, configured to, when the first difference is equal to the second difference, determine a high-risk probability from the first risk probability and the second risk probability, and determine the risk level corresponding to the high-risk probability as the risk level of the transaction information.

8. A computer storage medium, wherein, the computer storage medium is used for storing a program, and when the program runs, it controls a device where the computer storage medium is located to execute the method for determining transaction risk according to any one of claims 1 to 6.

9. An electronic device, wherein, it includes one or more processors and a memory, and the memory is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for determining transaction risk according to any one of claims 1 to 6.

Images