Transaction data processing method and device, electronic equipment and readable storage medium

Abstract

The invention provides a transaction data processing method and device, electronic equipment and a readable storage medium, and can be applied to the technical field of big data, the technical field of cloud computing and the technical field of financial science and technology. The transaction data processing method comprises the following steps: reading to-be-processed transaction data associated with a target transaction from a message middleware; reading a total conditional probability table pre-constructed for the M risk association factors from a database, and reading a preset prior risk probability of each risk association factor; based on the M association arrays, the total conditional probability table and the preset prior risk probability of each risk association factor, calculating to obtain the posterior risk probability of each risk association factor; and inputting the posterior risk probability of each risk association factor and a preset prior risk probability into a risk model, and outputting a risk prediction result of the target transaction.

Description

Technical Field

[0001] The present disclosure relates to the fields of big data technology, cloud computing technology, and financial technology technology, and more specifically to a transaction data processing method and device, an electronic device, and a readable storage medium. Background Art

[0002] With the development of the global economy and the growth of international trade, remittance transactions have become an increasingly important business. How to identify and control the risks of remittance transactions and improve the security and efficiency of remittances are the key links that need to be controlled in business processing.

[0003] In the process of realizing the concept of the present disclosure, the inventors found that there are at least the following problems in the related technology: At present, most of the commonly used transaction risk monitoring methods are based on traditional rule engines or static statistical models. For real-time changing transaction scenarios, it is impossible to obtain reference prediction results, and thus the security of transactions cannot be guaranteed. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a transaction data processing method and device, an electronic device and a readable storage medium.

[0005] One aspect of the present disclosure provides a transaction data processing method, comprising: reading from a message middleware unprocessed transaction data associated with a target transaction, wherein the unprocessed transaction data includes M association arrays corresponding to M risk association factors; reading from a database a full conditional probability table pre-constructed for the M risk association factors, and reading a preset a priori risk probability of each risk association factor; calculating a posterior risk probability of each risk association factor based on the M association arrays, the full conditional probability table, and the preset a priori risk probability of each risk association factor; inputting the posterior risk probability of each risk association factor and the preset a priori risk probability into a risk model, and outputting a risk prediction result of the target transaction; and sending the risk prediction result to a monitoring system.

[0006] According to an embodiment of the present disclosure, based on M associative arrays, the full conditional probability table, and the preset a priori risk probability of each risk association factor, the posterior risk probability of each risk association factor is calculated, including: associating the M associative arrays with the full conditional probability table to determine the target conditional probability of each of the M risk association factors based on the target transaction; calculating the posterior risk probability of each risk association factor according to the full conditional probability table, the target conditional probability of each of the M risk association factors, and the preset a priori risk probability of each risk association factor.

[0007] According to an embodiment of the present disclosure, the transaction data processing method also includes: reading from a database multiple groups of first historical transaction data associated with multiple groups of first historical transactions within a first predetermined historical time period, wherein each group of first historical transaction data includes at least M first historical transaction arrays corresponding to M risk association factors; constructing a directed association structure graph based on the M risk association factors, wherein the directed association structure graph includes M nodes corresponding to the M risk association factors, the M nodes are associated with each other through directed edges, and the weights of the directed edges are used to characterize the conditional probabilities between the associated nodes directly connected to the directed edges; constructing a full conditional probability table for the M risk association factors based on the multiple groups of first historical transaction data and the directed association structure graph.

[0008] According to an embodiment of the present disclosure, the transaction data processing method also includes: reading from a database multiple groups of second historical transaction data associated with multiple groups of second historical transactions within a second predetermined historical time period, wherein each group of second historical transaction data includes at least M second historical transaction arrays corresponding to M risk association factors; and updating the full conditional probability table based on the multiple groups of second historical transaction data.

[0009] According to an embodiment of the present disclosure, the transaction data processing method also includes: performing data preprocessing on multiple groups of first historical transaction data, and the data preprocessing at least includes: removing abnormal data in the multiple groups of first historical transaction data, completing missing data in the multiple groups of first historical transaction data, and removing duplicate data in the multiple groups of first historical transaction data.

[0010] According to an embodiment of the present disclosure, the abnormal data in the above-mentioned multiple groups of first historical transaction data include at least: first historical transaction data in which the remittance amount is greater than a preset amount threshold, first historical transaction data in which the remittance frequency within a predetermined time window is greater than a preset frequency threshold, first historical transaction data in which the payment address involves a predetermined risk area, and first historical transaction data in which the remittance purpose involves a predetermined risk purpose.

[0011] According to an embodiment of the present disclosure, the above-mentioned M risk-related factors include: remitter information, remittance information, payee economic development index, remittance purpose, payee information, and payee environmental stability index.

[0012] According to an embodiment of the present disclosure, in the above-mentioned directed association structure diagram, M nodes correspond to M risk association factors, among which the remitter information node, the remittance information node, and the payee economic development index node are root nodes, and the remittance purpose node, the payee information node, and the payee environmental stability index node are child nodes, and the root node and the child nodes are connected by directed edges pointing to the child nodes.

[0013] According to an embodiment of the present disclosure, the posterior risk probability includes a first posterior risk probability and a second posterior risk probability, and the preset a priori risk probability includes a first a priori risk probability and a second a priori risk probability; the posterior risk probability and the preset a priori risk probability of each risk-related factor are input into the risk model, and the risk prediction result of the target transaction output includes: a basic reference value is calculated based on the first posterior risk probability, the first a priori risk probability, the second posterior risk probability, and the second a priori risk probability of each risk-related factor; a first reference value is calculated based on the first posterior risk probability and the first a priori risk probability of each risk-related factor; a second reference value is calculated based on the second posterior risk probability and the second a priori risk probability of each risk-related factor; a first risk prediction result is calculated based on the first reference value and the basic reference value; a second risk prediction result is calculated based on the second reference value and the basic reference value.

[0014] Another aspect of the present disclosure provides a transaction data processing device, including: a first reading module, a second reading module, a calculation module, an output module and a sending module.

[0015] The first reading module is used to read the pending transaction data associated with the target transaction from the message middleware, wherein the pending transaction data includes M association arrays corresponding to M risk association factors. The second reading module is used to read the full conditional probability table pre-built for the M risk association factors from the database, and read the preset prior risk probability of each risk association factor. The calculation module is used to calculate the posterior risk probability of each risk association factor based on the M association arrays, the full conditional probability table, and the preset prior risk probability of each risk association factor. The output module is used to input the posterior risk probability of each risk association factor and the preset prior risk probability into the risk model, and output the risk prediction result of the target transaction. The sending module is used to send the risk prediction result to the monitoring system.

[0016] Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above-mentioned transaction data processing method.

[0017] Another aspect of the present disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the transaction data processing method.

[0018] Another aspect of the present disclosure also provides a computer program product, including a computer program, which implements the above transaction data processing method when executed by a processor.

[0019] According to the embodiments of the present disclosure, by setting risk association factors and conditional probability tables, calculating the posterior probability of risk association factors in combination with the conditional probability tables, and calculating the risk of remittance transactions using the posterior risk probability of risk association factors, preset prior risk probability and risk model, it is possible to comprehensively consider a variety of factors affecting the risk of remittance transactions, and also to fully consider the impact of the dependency relationship between the various factors affecting the risk of remittance transactions on the risk results. This improves the accuracy of remittance transaction risk prediction. By further evaluating and verifying high-risk remittance transactions, the security of remittance transactions is improved, the risk of remittance transactions is reduced, and the interests of financial institutions and customers are protected. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above contents and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0021] Figure 1 A diagram schematically shows an application scenario of a transaction data processing method and device, an electronic device, and a readable storage medium according to an embodiment of the present disclosure;

[0022] Figure 2 A flowchart of a transaction data processing method according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 3 A system structure diagram schematically shows a method for processing transaction data according to an embodiment of the present disclosure;

[0024] Figure 4 A directed association structure diagram according to an embodiment of the present disclosure is schematically shown;

[0025] Figure 5 A flowchart schematically shows a transaction data processing method according to another embodiment of the present disclosure;

[0026] Figure 6 A block diagram schematically shows a structure of a transaction data processing device according to an embodiment of the present disclosure; and

[0027] Figure 7 A block diagram of an electronic device suitable for implementing a transaction data processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0028] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0029] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0030] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0031] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0032] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] An embodiment of the present disclosure provides a transaction data processing method, comprising: reading from a message middleware unprocessed transaction data associated with a target transaction, wherein the unprocessed transaction data includes M association arrays corresponding to M risk association factors; reading from a database a full conditional probability table pre-constructed for the M risk association factors, and reading a preset a priori risk probability for each risk association factor; calculating a posterior risk probability for each risk association factor based on the M association arrays, the full conditional probability table, and the preset a priori risk probability for each risk association factor; inputting the posterior risk probability of each risk association factor and the preset a priori risk probability into a risk model, and outputting a risk prediction result for the target transaction; and sending the risk prediction result to a monitoring system.

[0034] Figure 1 The application scenario diagram of the transaction data processing method according to the embodiment of the present disclosure is schematically shown.

[0035] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0036] The user may use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications may be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0037] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0038] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0039] In the application scenario of the embodiment of the present disclosure, the user can use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to initiate a request for transaction data processing to the server 105. In response to the above request, the server 105 can be used to execute the transaction data processing method of the embodiment of the present disclosure, including: reading the to-be-processed transaction data associated with the target transaction from the message middleware, wherein the to-be-processed transaction data includes M association arrays corresponding to M risk association factors; reading the full conditional probability table pre-constructed for the M risk association factors from the database, and reading the preset priori risk probability of each risk association factor; calculating the posterior risk probability of each risk association factor based on the M association arrays, the full conditional probability table, and the preset priori risk probability of each risk association factor; inputting the posterior risk probability of each risk association factor and the preset priori risk probability into the risk model, and outputting the risk prediction result of the target transaction; sending the risk prediction result to the monitoring system, and after generating the corresponding transaction data processing result, returning it to the terminal devices 101, 102, and 103, so as to display the result to the user through the terminal devices 101, 102, and 103.

[0040] It should be noted that the transaction data processing method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the transaction data processing device provided in the embodiment of the present disclosure can generally be set in the server 105. The transaction data processing method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Accordingly, the transaction data processing device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0041] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0042] The following will be based on Figure 1The scene described by Figure 2 to Figure 7 The transaction data processing method of the disclosed embodiment is described in detail.

[0043] Figure 2 The flowchart of the transaction data processing method according to the embodiment of the present disclosure is schematically shown. Figure 3 The following schematically shows a system structure diagram for implementing the transaction data processing method of the embodiment of the present disclosure. Figure 2 , Figure 3 The transaction data processing method is described.

[0044] like Figure 2 As shown, the transaction data processing method of this embodiment includes operations S201 to S205.

[0045] In operation S201, to-be-processed transaction data associated with a target transaction is read from a message middleware, wherein the to-be-processed transaction data includes M association arrays corresponding to M risk association factors, where M is a positive integer;

[0046] In operation S202, a pre-built full conditional probability table for M risk-related factors is read from a database, and a preset a priori risk probability of each risk-related factor is read;

[0047] In operation S203, based on the M association arrays, the full conditional probability table, and the preset priori risk probability of each risk association factor, the posterior risk probability of each risk association factor is calculated;

[0048] In operation S204, the posterior risk probability of each risk-related factor and the preset priori risk probability are input into the risk model, and the risk prediction result of the target transaction is output;

[0049] In operation S205, the risk prediction result is sent to the monitoring system.

[0050] According to the embodiments of the present disclosure, the transaction data processing method can be applied in scenarios where the risk of remittance transactions is assessed, such as assessing the risk level of a cross-border remittance transaction. The risk of remittance transactions is affected by many factors. For example, when the payee remits money to a certain account too frequently, the amount of remittances is large, the legal system of the receiving area is imperfect, etc., the risk of remittance transactions will increase. Therefore, financial institutions need to assess the risk of remittance transactions based on various factors that affect the risk of remittance transactions, and adopt corresponding measures for high-risk remittance transactions.

[0051] According to the embodiments of the present disclosure, Figure 3 As shown, the system applying the above-mentioned transaction data processing method may include a transaction system, a message middleware, a risk prediction system, one or more databases (such as database 1, database 2), and a monitoring system.

[0052] According to an embodiment of the present disclosure, the transaction system can be used to process transactions between financial institutions and between financial institutions and customers. For example, for a certain transaction, the transaction system generates pending transaction data related to the transaction. For example, when a customer remits money to financial institution B through financial institution A, the transaction system generates pending transaction data for the remittance transaction and sends the pending transaction data to a message middleware, which can be MQ, Kafka, etc.

[0053] According to an embodiment of the present disclosure, the risk prediction system is used to execute the transaction data processing method of the embodiment of the present disclosure. Through the above operation S201, after the transaction system sends the transaction data to be processed to the message middleware, the risk prediction system reads the transaction data to be processed from the message middleware.

[0054] According to an embodiment of the present disclosure, the transaction data to be processed includes M association arrays corresponding to M risk association factors. The risk association factor can be any factor that may affect the risk of a remittance transaction, for example, it may include one or more of remitter information, remittance information, payee economic development indicators, remittance purposes, payee information, and payee environmental stability indicators, but is not limited thereto, and may also include the relationship between the remitter and the payee, the remitter's credit rating, etc.

[0055] According to an embodiment of the present disclosure, each risk association factor may include multiple sub-association factors. For example, the remitter information may include the remitter's gender, age, marital status, fixed income, education, occupation, income and other sub-association factors; the remittance information may include the remittance amount, remittance time, remittance method and other sub-association factors; the payee information may include the receiving financial institution, the receiving country / region, the identity information of the payee and other sub-association factors; the remittance purpose may be shopping, education and other sub-association factors; the payee's economic development indicators may include the GDP, inflation rate, population and other economic indicators of the receiving country / region; the payee's environmental stability may include the degree of perfection of the legal system of the receiving area, the degree of perfection of the risk supervision policy, etc. All sub-association factors included in a risk association factor are an array.

[0056] For example, user A remits 2,000 yuan to recipient B through a financial institution for education expenses. The transaction system of the financial institution generates pending transaction data for the transaction and sends the pending transaction data to the message middleware. The risk prediction system reads the pending transaction data from the message middleware. The pending transaction data may include three risk-related factors, namely, remittance information, remittance information, and remittance purpose. The remittance information includes: the remitter is male and 40 years old; the remittance information includes: the remittance amount is 2,000 yuan; the remittance purpose is education expenses. For the risk-related factor of remittance information, the remitter's age and gender together constitute the array of the risk-related factor.

[0057] According to an embodiment of the present disclosure, the database is used to store the full conditional probability table pre-constructed for M risk-related factors, and to store the preset a priori risk probability of each risk-related factor. For example, database 1 can store the full conditional probability table, and database 2 can store the preset a priori risk probability.

[0058] According to an embodiment of the present disclosure, a conditional probability table may be pre-constructed. For example, all or part of the pending transaction data within a certain time period may be counted. Based on the pending transaction data, the probability of the value of the information contained in each risk association factor appearing within the time period is counted and calculated to construct a conditional probability table. For example: all pending transaction data for 20xx are counted. The pending transaction data contains risk association factors: remitter information, remittance purpose, etc. The remitter information includes the remitter's gender and age. The gender value is male or female; the age value can be 20, 30, etc. Through statistics and calculations, it is found that in 20xx, the probability that the remitter is male and 20 years old is 0.2, and the probability that the remitter is male and 30 years old is 0.3... Based on the above statistical data, a conditional probability table of the remitter information for 20xx is generated, as shown in Table 1:

[0059] Table 1: Conditional probability table of remittance information in 20xx

[0060] gender age P(sex, age) male 20 0.2 male 30 0.3 male 40 0.2 male 50 0.1 male 60 0.1 female 20 0.1 female 30 0.2 female 40 0.3 female 50 0.2 female 60 0.1

[0061] The conditional probability tables of the M risk-related factors within a certain historical period are calculated respectively to obtain the full conditional probability table for the M risk-related factors.

[0062] According to an embodiment of the present disclosure, the preset priori risk probability of the risk association factor may be automatically generated by the system or set by the user. The preset priori risk probability of the risk association factor may include a high-risk preset priori risk probability and a low-risk preset priori risk probability. For example, the high-risk preset priori risk probability of the remitter information may be set to 0.7, and the low-risk preset priori risk probability may be set to 0.3.

[0063] According to an embodiment of the present disclosure, through the above operation S202, the risk prediction system can read the full conditional probability table pre-constructed for M risk association factors from the database, and read the preset priori risk probability of each risk association factor.

[0064] For example, the risk prediction system can read the conditional probability table of the remitter information in 20xx from database 1, and obtain the conditional probability of 0.1 that the remitter in 20xx is a female and 60 years old, and read the high-risk preset prior risk probability of 0.7 and the low-risk preset prior risk probability of 0.3 of the remitter information from database 2.

[0065] It should be noted that in the embodiment of the present disclosure, in operation S202, before reading the pending transaction data associated with the target transaction, the user's consent or authorization may be obtained. For example, before operation S202, a request to obtain the pending transaction data may be issued to the user. When the user agrees or authorizes that the user information may be obtained, operation S202 is performed.

[0066] According to an embodiment of the present disclosure, after the risk prediction system reads the full conditional probability table and the preset prior risk probability from the database, through operation S203, based on M association arrays, the full conditional probability table, and the preset prior risk probability of each risk association factor, the posterior risk probability of each risk association factor is calculated.

[0067] According to an embodiment of the present disclosure, the posterior risk probability may include a high risk posterior probability and a low risk posterior probability. The calculation methods for calculating the posterior risk probability of each risk association factor are respectively:

[0068] The calculation method of the above high-risk posterior probability is shown in formula (1):

[0069]

[0070] The calculation method of the above low-risk posterior probability is shown in formula (2):

[0071]

[0072] The meanings of the parameters in the above formulas (1)-(2) are as follows:

[0073] P(posterior risk probability / high risk): posterior probability of high risk of risk-associated factor;

[0074] P(posterior risk probability / low risk): the posterior probability of low risk of the risk-associated factor;

[0075] P (high risk preset a priori risk probability): high risk preset a priori risk probability of risk association factor;

[0076] P (low risk preset a priori risk probability): low risk preset a priori risk probability of risk association factor;

[0077] P (conditional probability): conditional probability read from the conditional probability table;

[0078] P (total probability): the probability of the entire sample space.

[0079] For example, remitter A remits 2,000 yuan to recipient B. The risk prediction system needs to calculate the high-risk posterior probability of the remitter information: the risk prediction system reads the associative array corresponding to the remitter information from the message middleware, including: the remitter is male and 20 years old; based on the above information, the remitter information conditional probability table is read from database 1 (for example, as shown in Table 1), and the conditional probability that the remitter is male and 20 years old is 0.2, that is, P (conditional probability) is 0.2; the high-risk preset prior risk probability of the remitter information read from database 2 is 0.7, that is, P (high-risk preset prior risk probability) is 0.7; P (total probability) is 0.28. Based on the above formula (1), the high-risk posterior probability of the remitter information can be obtained:

[0080]

[0081] According to an embodiment of the present disclosure, after respectively calculating the high-risk posterior probability and the low-risk posterior probability of each risk-related factor, the risk prediction system inputs the high-risk posterior probability, the low-risk posterior probability and the preset a priori risk probability of each risk-related factor into the risk model through operation S204, and outputs the risk prediction result of the target transaction.

[0082] According to an embodiment of the present disclosure, the risk model may include a high risk model and a low risk model.

[0083] The above high-risk model can be expressed by formula (3):

[0084]

[0085] The above low-risk model can be expressed by formula (4):

[0086]

[0087] The meanings of the parameters in the above formulas (3)-(4) are as follows:

[0088] P(high risk / posterior probability): the high risk posterior probability of the target transaction;

[0089] P(low risk / posterior probability): low risk posterior probability of the target transaction;

[0090] Pi (posterior probability / high risk): the posterior probability of high risk for each risk-related factor;

[0091] Pi (posterior probability / low risk): the posterior probability of low risk for each risk-related factor;

[0092] P (high risk): high risk preset a priori risk probability;

[0093] P(low risk): Low risk presets the prior risk probability.

[0094] For example, we need to obtain the risk prediction result of a remittance transaction: first, the risk prediction system reads the full conditional probability table and the preset prior risk probability from the database, and then calculates the posterior risk probability of each risk-related factor through equations (1) and (2):

[0095] Remitter information: high risk posterior probability is 0.15, low risk posterior probability is 0.85;

[0096] Remittance information: high risk posterior probability is 0.1, low risk posterior probability is 0.9;

[0097] Remittance purpose: high risk posterior probability is 0.6, low risk posterior probability is 0.4;

[0098] Secondly, the risk prediction system reads from the database that the high risk preset priori risk probability is 0.6 and the low risk preset priori risk probability is 0.4. The risk prediction system inputs the posterior risk probability of the above risk-related factors and the preset priori risk probability into the risk model shown in formula (3)-formula (4), and obtains the high risk posterior probability and low risk posterior probability of the remittance transaction respectively:

[0099]

[0100]

[0101] Based on the calculation results obtained by the above risk model, the risk prediction system outputs the risk prediction results of the above remittance transaction as follows: the high risk posterior probability of the above remittance transaction is 0.37, and the low risk posterior probability is 0.63.

[0102] According to an embodiment of the present disclosure, through operation S205, after outputting the risk prediction result, the risk prediction system sends the risk prediction result to the monitoring system.

[0103] According to an embodiment of the present disclosure, a monitoring system is used to receive risk prediction results sent by a risk prediction system and perform subsequent processing. The subsequent processing includes: based on the above risk prediction results, the monitoring system marks high-risk remittance transactions and low-risk remittance transactions. The marking method can be that the system automatically generates or manually sets a threshold value. When the high-risk posterior probability in the risk prediction result is higher than the threshold, the corresponding remittance transaction is marked as a high-risk remittance transaction. For example, it can be: the threshold is manually set to 0.2, and the high-risk posterior probability output by the risk prediction system is 0.37. The monitoring system compares the high-risk posterior probability with the manually set threshold. Since the high-risk posterior probability is higher than the set threshold, the corresponding remittance transaction is marked as a high-risk transaction.

[0104] According to an embodiment of the present disclosure, the subsequent processing also includes: verifying the remittance transaction to ensure that it really has a high risk. The verification method may be, for example, re-verifying the identity information of both parties to the remittance and checking whether the purpose of the remittance is legal.

[0105] According to an embodiment of the present disclosure, for remittances that have been verified as high-risk, the monitoring system needs to take corresponding processing measures, such as suspending or rejecting the remittance, reporting to relevant regulatory agencies, conducting investigations, etc., and all high-risk remittance information needs to be recorded for future supervision and tracing.

[0106] According to the embodiments of the present disclosure, remittances marked as non-high-risk remittances can be directly processed, such as transferring them to a designated account, or remitting them according to normal procedures. At the same time, the monitoring system needs to record the information of all non-high-risk remittances for future supervision and tracing.

[0107] According to an embodiment of the present disclosure, subsequent processing may also include: conducting a more in-depth risk assessment on remittances marked as high-risk. For example, it may be a more stringent identity verification of the identity of the payee and the remitter, checking the purpose and source of the remittance, further analyzing the remittance data to identify potential abnormal transactions, etc. For high-risk remittances, the monitoring system may issue an alarm, and the alarm content includes detailed information related to the high-risk remittance, such as remitter and payee information, remittance amount, remittance purpose, destination, etc.

[0108] According to an embodiment of the present disclosure, subsequent processing may further include: recording the risk identification and assessment results of all the above remittances, and storing them in a risk database for reference and future analysis.

[0109] For example, the monitoring system receives the risk prediction result of a remittance transaction sent by the risk prediction system: the high risk posterior probability of the remittance transaction is 0.8, the low risk posterior probability is 0.2, and the threshold is set to 0.6. The monitoring system marks the above remittance transaction as a high-risk remittance transaction, and verifies that the transaction is indeed a high-risk transaction by verifying the identity information of both parties to the remittance and checking the remittance. The monitoring system can report the remittance transaction to the relevant regulatory authorities and conduct an investigation; and conduct stricter identity verification of the identities of the payee and the remitter, and check the purpose and source of the remittance. The monitoring system also needs to record the risk identification and assessment results of the above remittance transaction and store them in the risk database.

[0110] According to the embodiments of the present disclosure, by setting risk association factors and conditional probability tables, calculating the posterior probability of risk association factors in combination with the conditional probability tables, and calculating the risk of remittance transactions using the posterior risk probability of risk association factors, preset prior risk probability and risk model, it is possible to comprehensively consider a variety of factors affecting the risk of remittance transactions, and also to fully consider the impact of the dependency relationship between the various factors affecting the risk of remittance transactions on the risk results. This improves the accuracy of remittance transaction risk prediction. By further evaluating and verifying high-risk remittance transactions, the security of remittance transactions is improved and the risk of remittance transactions is reduced.

[0111] According to the embodiments of the present disclosure, further, by setting up a message middleware, decoupling between the upstream trading system and the downstream risk prediction system can be achieved, reducing the complexity of program design of each system, focusing on one's own business, and eliminating the need to repeat work for porting programs on different system software, thereby greatly reducing the technical burden.

[0112] According to the embodiments of the present disclosure, further, information and instruction interaction between multiple systems such as trading systems, risk prediction systems, message middleware, and monitoring systems distributes each link in the risk prediction process to multiple different application systems for orderly execution. On the basis of realizing computer automatic execution of risk monitoring, each link in the supervision process is distributed to multiple different application systems for orderly execution, which can be assigned to multiple computers for synchronous and parallel processing, which can reduce the pressure of data processing on the main system, save overall computing time, improve computer efficiency, have strong scalability, and higher flexibility in business system layout, and is easier to install and deploy.

[0113] According to an embodiment of the present disclosure, specifically, in operation S203, based on M associative arrays, the full conditional probability table, and the preset priori risk probability of each risk association factor, the posterior risk probability of each risk association factor is calculated, including: associating the M associative arrays with the full conditional probability table to determine the target conditional probability of each of the M risk association factors based on the target transaction; calculating the posterior risk probability of each risk association factor according to the full conditional probability table, the target conditional probability of each of the M risk association factors, and the preset priori risk probability of each risk association factor.

[0114] According to an embodiment of the present disclosure, M association arrays are associated with the full conditional probability table. For example, it can be: based on the transaction data to be processed, determine the value of the information contained in the association array of each risk association factor, and then read the conditional probability corresponding to the value from the conditional probability table of the risk association factor. For example, it can be: the information contained in the association array of the remitter information of a certain remittance includes: gender, age, and the value of the above information is: gender is male, age is 20 years old. Read the conditional probability table of the remitter information from the database (for example, it can be the above Table 1). Based on the table, it can be known that the conditional probability corresponding to the gender of male and the age of 20 years old is 0.2, that is: the conditional probability of the remitter information corresponding to the remittance transaction is 0.2. Then associate the M association arrays with the corresponding conditional probability tables respectively, and obtain the target conditional probabilities of the M risk association factors respectively.

[0115] According to the embodiments of the present disclosure, after respectively obtaining the target conditional probabilities of the M risk-associated factors, based on the above target conditional probabilities and the preset a priori risk probabilities of each risk-associated factor, the high-risk posterior probability and the low-risk posterior probability of each risk-associated factor are respectively calculated by formula (1) and formula (2).

[0116] For example: the risk prediction system needs to calculate the high-risk posterior probability of the remitter information of a remittance transaction: the risk prediction system reads the associative array corresponding to the remitter information, including: the remitter is a female, aged 40 years old; based on the above information, the remitter information conditional probability table is read from database 1 (such as shown in Table 1), and the target conditional probability is 0.3, that is, P (conditional probability) is 0.3; the high-risk preset prior risk probability of the remitter information is read from database 2, which is 0.7, that is, P (high-risk preset prior risk probability) is 0.7; P (total probability) is 0.28. Based on the above formula (1), the high-risk posterior probability of the remitter information can be obtained as:

[0117] P(posterior risk probability / high risk) = (0.3 × 0.7) / 0.28 = 0.75

[0118] According to the embodiments of the present disclosure, by statistically calculating the posterior risk probability of each risk-related factor, the impact of various factors on the remittance transaction can be comprehensively considered, thereby improving the accuracy of risk prediction.

[0119] According to an embodiment of the present disclosure, the transaction data processing method further includes:

[0120] Operation 11: reading from a database a plurality of groups of first historical transaction data associated with a plurality of groups of first historical transactions within a first predetermined historical time period, wherein each group of first historical transaction data includes at least M first historical transaction arrays corresponding to M risk association factors;

[0121] Operation 12: construct a directed association structure graph based on M risk association factors;

[0122] Operation 13: Construct a full conditional probability table for M risk association factors based on multiple groups of first historical transaction data and the directed association structure graph.

[0123] According to an embodiment of the present disclosure, in operation 11, the first scheduled historical time period may be a time period automatically generated by the system or a time period set by a user. The first historical transaction may be all or part of the remittance transaction within the first historical time period. The first historical transaction within the first historical time period is read, and first historical transaction data is generated, wherein the first historical transaction data includes M risk association factors, and the M risk association factors correspond to M association arrays.

[0124] For example, the user sets the first booking historical time period to 2011-2012, and reads all remittance transactions within the historical time period, where all the above remittance transactions constitute the first historical transaction; reads M risk association factors included in the first historical transaction data, which may include, for example: remitter information, remittance information, payee economic development indicators, remittance purpose, payee information, and payee environmental stability.

[0125] According to an embodiment of the present disclosure, in operation 12, a directed association structure graph is constructed based on the M risk association factors included in the first historical transaction data. The directed association structure graph includes M nodes, and the M nodes are associated with each other through directed edges, and the weights of the directed edges are used to characterize the conditional probabilities between the associated nodes directly connected to the directed edges.

[0126] Figure 4 The figure schematically shows a directed association structure diagram according to an embodiment of the present disclosure.

[0127] exist Figure 4In the directed association structure diagram, the M nodes correspond to M risk association factors, among which the remitter information node, remittance information node, and payee economic development index node are root nodes, and the remittance purpose node, payee information node, and payee environmental stability index node are child nodes. The status of the child node will be affected by the root node, for example, the status of the remittance purpose node, payee information node, and payee environmental stability index node is affected by the remitter information node, remittance information node, and payee economic development index node.

[0128] The remitter information node and the remittance purpose node are associated through a directed edge pointing to the remittance purpose node, the remitter information node and the payee information node are associated through a directed edge pointing to the payee information node, and the remitter information node and the payee environment stability indicator node are associated through a directed edge pointing to the payee environment stability indicator node.

[0129] The remittance information node is associated with the remittance purpose node through a directed edge pointing to the remittance purpose node, the remittance information node is associated with the payee information node through a directed edge pointing to the payee information node, and the remittance information node is associated with the payee environment stability indicator node through a directed edge pointing to the payee environment stability indicator node.

[0130] The economic development index node is associated with the remittance purpose node through a directed edge pointing to the remittance purpose node, the economic development index node is associated with the payee information node through a directed edge pointing to the payee information node, and the economic development index node is associated with the payee environment stability index node through a directed edge pointing to the payee environment stability index node.

[0131] According to an embodiment of the present disclosure, in operation 13, based on multiple groups of first historical transaction data and a directed association structure graph, a full conditional probability table for M risk association factors is constructed. For example, it can be: for each information value contained in the association array of the risk association factor corresponding to each node, the frequency of values ​​of other nodes under this value is counted, and then divided by the number of samples of the node value, the conditional probability table of the node when the values ​​of other nodes are given can be obtained.

[0132] For example, the directed association structure diagram includes a remittance information node, and the risk association factor corresponding to the remittance information node is the remittance information, and the information included in the risk association factor includes the historical remittance amount. In the first historical transaction data, the values ​​of the historical remittance amount are 1000, 2000, 3000, 4000, and 5000 respectively. The frequency of values ​​of other nodes under all values ​​is counted respectively, and then divided by the number of samples of the node value, the conditional probability table of the remittance information node can be obtained as shown in Table 2:

[0133] Table 2: Conditional probability table of remittance information

[0134] Historical remittance amount P(Historical remittance amount) 1000 0.2 2000 0.3 3000 0.3 4000 0.1 5000 0.1

[0135] The conditional probability table corresponding to each node is obtained separately to obtain the full conditional probability table, as shown in Table 3-7:

[0136] Table 3: Conditional probability table of economic development indicators of the recipient

[0137] exchange rate P(Exchange Rate) rise 0.4 Flat 0.3 Fall 0.3

[0138] Table 4: Conditional probability table of remittance usage

[0139] Remittance Purpose P (Purpose of remittance | Personal information, historical remittance records, economic factors) Shopping 0.3 travel 0.4 educate 0.3

[0140] Table 5: Conditional probability table of payee information

[0141] destination P (destination | remittance party information, remittance purpose, recipient's economic development indicators) domestic 0.6 internationality 0.4

[0142] Table 6: Conditional probability table of environmental stability indicators of the recipient

[0143]

[0144] The meanings of the parameters in Tables (2)-(6) are as follows:

[0145] P (historical remittance amount): conditional probability when the historical remittance amount is a certain value;

[0146] P(Exchange Rate): Conditional probability when the exchange rate is a certain value

[0147] P(remittance purpose|personal information, historical remittance records, economic factors): conditional probability when the historical remittance amount is a certain value;

[0148] P(destination|remittance party information, remittance purpose, recipient's economic development index): conditional probability that the historical remittance amount is a certain value given the remittance party information, remittance purpose, and recipient's economic development index;

[0149] P(payee environment stability index | payee information): conditional probability that the payee environment stability index is a certain value given the payee information.

[0150] According to the embodiments of the present disclosure, by constructing a directed association structure diagram, the association relationship between multiple risk association factors can be clearly reflected, which can be used as the data basis for constructing a full conditional probability table.

[0151] According to an embodiment of the present disclosure, the above-mentioned transaction data processing method also includes: reading multiple groups of second historical transaction data associated with multiple groups of second historical transactions within a second predetermined historical time period from a database, and updating the full conditional probability table based on the multiple groups of second historical transaction data.

[0152] According to an embodiment of the present disclosure, the second predetermined historical time period may be automatically generated by the system or may be set by a user. The second predetermined historical time period is later than the first predetermined historical time period. The second historical transaction may be all or part of the remittance transaction within the second historical time period. The second historical transaction within the historical time period is read, and second historical transaction data is generated, wherein the second historical transaction data includes M risk association factors, and the M risk association factors correspond to M historical transaction arrays.

[0153] According to an embodiment of the present disclosure, based on multiple groups of second historical transaction data, the full conditional probability table for the first predetermined historical time period is updated. For example, a value in the full conditional probability table for the first historical time period may be adjusted, or a risk association factor conditional probability table may be added or deleted, so that the updated full conditional probability table is more in line with the actual situation of the second historical transactions within the second predetermined historical time period.

[0154] For example, the first booking historical time period set by the user is 2011-2012, and the second booking historical time period set is 2011-2013. The second historical data in the second historical time period is read, and the full conditional probability table for 2011-2012 is updated: for example, the conditional probabilities in the full conditional probability table can be adjusted to make it more consistent with the actual situation of recent historical transactions, making it more referenceable.

[0155] According to the embodiments of the present disclosure, based on the update of historical transaction data, the full conditional probability can be dynamically updated, thereby improving the accuracy of risk prediction and ensuring the reference value of risk prediction.

[0156] According to an embodiment of the present disclosure, the above-mentioned transaction data processing method also includes: performing data preprocessing on multiple groups of first historical transaction data, and the data preprocessing at least includes: removing abnormal data in multiple groups of first historical transaction data, completing missing data in multiple groups of first historical transaction data, and removing duplicate data in multiple groups of first historical transaction data.

[0157] According to an embodiment of the present disclosure, the abnormal data in the multiple groups of first historical transaction data at least include: first historical transaction data with a remittance amount greater than a preset amount threshold, first historical transaction data with a remittance frequency greater than a preset frequency threshold within a predetermined time window, first historical transaction data with a payment address involving a predetermined risk area, and first historical transaction data with a remittance purpose involving a predetermined risk purpose. The preset amount threshold and the preset frequency threshold can be automatically generated by the system or set by the user.

[0158] For example, if the remittance amount of the first historical transaction data A is 150,000 yuan in multiple sets of first historical transaction data, which exceeds the preset amount threshold of 100,000 yuan set by the user, the first historical transaction data corresponding to the above transaction is abnormal data; it is also found that some data is missing in the first historical transaction data B. For the above first historical transaction data A and the first historical transaction data B, the preprocessing to be performed is: deleting the first historical transaction data A and completing the missing data in the first historical transaction data B.

[0159] According to the embodiments of the present disclosure, data is preprocessed before constructing the conditional probability table, thereby avoiding interference of invalid data in constructing the conditional probability table and improving the referenceability of the conditional probability table.

[0160] According to an embodiment of the present disclosure, the posterior risk probability of each risk-related factor and the preset a priori risk probability are input into the risk model, and the risk prediction result of the target transaction is output, including: a basic reference value is calculated based on the first posterior risk probability, the first a priori risk probability, the second posterior risk probability, and the second a priori risk probability of each risk-related factor; a first reference value is calculated based on the first posterior risk probability and the first a priori risk probability of each risk-related factor; a second reference value is calculated based on the second posterior risk probability and the second a priori risk probability of each risk-related factor; a first risk prediction result is calculated based on the first reference value and the basic reference value; and a second risk prediction result is calculated based on the second reference value and the basic reference value.

[0161] According to an embodiment of the present disclosure, the posterior risk probability may include a first posterior risk probability and a second posterior risk probability, and the first posterior risk probability and the second posterior risk probability may respectively represent one of a high risk posterior probability and a low risk posterior probability, and the meanings represented by the first posterior risk probability and the second posterior risk probability cannot be the same. For example, it may be that the first posterior risk probability represents a high risk posterior probability, and the second posterior risk probability represents a low risk posterior probability; for example, it may also be that the first posterior risk probability represents a low risk posterior probability, and the second posterior risk probability represents a high risk posterior probability.

[0162] According to an embodiment of the present disclosure, the preset a priori risk probability may include a first a priori risk probability and a second a priori risk probability, and the first a priori risk probability and the second a priori risk probability may respectively represent one of a high risk a priori probability and a low risk a priori probability, and the meanings represented by the first a priori risk probability and the second a priori risk probability cannot be the same. For example, it may be that the first a priori risk probability represents a high risk a priori probability, and the second a priori risk probability represents a low risk a priori probability; for example, it may also be that the first a priori risk probability represents a low risk a priori probability, and the second a priori risk probability represents a high risk a priori probability.

[0163] According to an embodiment of the present disclosure, a basic reference value is calculated based on the first a posteriori risk probability, the first a priori risk probability, the second a posteriori risk probability, and the second a priori risk probability of each risk association factor, for example, as shown in formula (5):

[0164] Basic reference value = ∑Pi(posterior probability / high risk)×P(high risk)+∑Pi(posterior probability / low risk)×P(low risk) (5)

[0165] According to an embodiment of the present disclosure, a first reference value is calculated based on the first posterior risk probability and the first a priori risk probability of each risk association factor. For example, the first posterior risk probability represents a high risk posterior probability, and the first a priori risk probability represents a high risk a priori probability. The calculation method of the above first reference value can be shown as formula (6):

[0166] First reference value = ∑Pi(posterior probability / high risk)×P(high risk) (6)

[0167] According to an embodiment of the present disclosure, a second reference value is calculated based on the second posterior risk probability and the second a priori risk probability of each risk association factor. For example, the second posterior risk probability represents a low risk posterior probability, and the second a priori risk probability represents a low risk a priori probability. The calculation method of the above second reference value can be shown as formula (7):

[0168] Second reference value = ∑Pi (posterior probability / low risk) × P (low risk) (7)

[0169] According to an embodiment of the present disclosure, the first risk prediction result and the second risk prediction result may respectively represent the probability that the remittance transaction is high risk and the probability that the remittance transaction is low risk, and the meanings represented by the first risk prediction result and the second risk prediction result cannot be the same. For example, it may be: the first risk prediction result probability represents the probability that the remittance transaction is high risk, and the second a priori risk probability represents the probability that the remittance transaction is low risk; for example, it may also be: the first risk prediction result represents the probability that the remittance transaction is low risk, and the second a priori risk probability represents the probability that the remittance transaction is high risk.

[0170] According to an embodiment of the present disclosure, a first risk prediction result is calculated based on the first reference value and the basic reference value, and the calculation method can be as shown in formula (3).

[0171] According to an embodiment of the present disclosure, the second risk prediction result is calculated based on the second reference value and the basic reference value, and the calculation method can be shown as formula (4).

[0172] For example: the first posterior risk probability represents the high risk posterior probability, and the second posterior risk probability represents the low risk posterior probability; the first prior risk probability represents the high risk prior probability, which is 0.6, and the second prior risk probability represents the low risk prior probability, which is 0.4. Through formula (1)-formula (2), the high risk posterior probability and low risk posterior probability of the risk association factor are calculated as follows:

[0173] Remitter information: high risk posterior probability is 0.1, low risk posterior probability is 0.2;

[0174] Remittance information: high risk posterior probability is 0.2, low risk posterior probability is 0.7;

[0175] Remittance purpose: high risk posterior probability is 0.6, low risk posterior probability is 0.4;

[0176] The basic reference value is calculated based on the high risk posterior probability, low risk posterior probability, high risk prior probability and low risk prior probability of the above risk association factors:

[0177] Basic reference value = 0.1 × 0.6 + 0.2 × 0.6 + 0.6 × 0.6 + 0.2 × 0.4 + 0.7 × 0.4 + 0.4 × 0.4 = 1.06

[0178] The first reference value is calculated based on the high risk posterior probability, high risk prior probability, and low risk prior probability of the above risk association factors:

[0179] First reference value = 0.1 × 0.6 + 0.2 × 0.6 + 0.6 × 0.6 = 0.54

[0180] The second reference value is calculated based on the low risk posterior probability and low risk prior probability of the above risk association factors:

[0181] Second reference value = 0.2 × 0.4 + 0.7 × 0.4 + 0.4 × 0.4 = 0.52

[0182] The first risk prediction result is calculated based on the first reference value and the basic reference value. The probability of the first risk prediction result indicates the probability that the remittance transaction is high risk:

[0183]

[0184] The second risk prediction result is calculated based on the second reference value and the basic reference value. The second priori risk probability indicates the probability that the remittance transaction is low risk:

[0185]

[0186] Figure 5 A flowchart of a transaction data processing method according to another embodiment of the present disclosure is schematically shown.

[0187] like Figure 5 As shown, the transaction data processing method of this embodiment includes operations S501 to S505.

[0188] In operation S501, the transaction data to be processed is read;

[0189] In operation S502, data preprocessing is performed;

[0190] In operation S503, a risk prediction result (such as a first risk prediction result) is calculated;

[0191] In operation S504, it is determined whether the risk prediction result is greater than a set threshold. For example, if it is less than the set threshold, it is treated as non-high risk.

[0192] In operation S505, if the risk prediction result is greater than the set threshold, the transaction data to be processed is verified and processed, for example, a risk prediction result indicating that the transaction is high-risk is sent to the monitoring system so that the monitoring system can perform subsequent processing (such as blocking the transaction, issuing early warning prompts, etc.).

[0193] Based on the above transaction data processing method, the present disclosure also provides a transaction data processing device. Figure 6 The device is described in detail.

[0194] Figure 6 The structural block diagram of the transaction data processing device according to the embodiment of the present disclosure is schematically shown.

[0195] like Figure 6 As shown, the transaction data processing device 600 of this embodiment includes a first reading module 610 , a second reading module 620 , a calculation module 630 , an output module 640 and a sending module 650 .

[0196] The first reading module 610 is used to read the pending transaction data associated with the target transaction from the message middleware, wherein the pending transaction data includes M association arrays corresponding to the M risk association factors. In one embodiment, the first reading module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0197] The second reading module 620 is used to read the pre-built full conditional probability table for the M risk association factors from the database, and read the preset priori risk probability of each risk association factor. In one embodiment, the second reading module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0198] The calculation module 630 is used to calculate the posterior risk probability of each risk association factor based on the M association arrays, the full conditional probability table, and the preset priori risk probability of each risk association factor. In one embodiment, the calculation module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0199] The output module 640 is used to input the posterior risk probability of each risk association factor and the preset priori risk probability into the risk model, and output the risk prediction result of the target transaction. In one embodiment, the first reading module 640 can be used to perform the operation S240 described above, which will not be repeated here.

[0200] The sending module 650 is used to send the risk prediction result to the monitoring system. In one embodiment, the first reading module 650 can be used to perform the operation S250 described above, which will not be repeated here.

[0201] According to an embodiment of the present disclosure, the calculation module includes a determination association submodule and a first calculation submodule.

[0202] The association submodule is used to associate M association arrays with the full conditional probability table to determine the target conditional probability of each of the M risk-related factors based on the target transaction; the calculation submodule is used to calculate the posterior risk probability of each risk-related factor based on the full conditional probability table, the target conditional probability of each of the M risk-related factors, and the preset prior risk probability of each risk-related factor.

[0203] According to an embodiment of the present disclosure, the transaction data processing device 600 further includes a third reading module, a first building submodule, and a second building submodule.

[0204] The third reading module is used to read from the database multiple groups of first historical transaction data associated with multiple groups of first historical transactions within a first predetermined historical time period, wherein each group of first historical transaction data includes at least M first historical transaction arrays corresponding to M risk association factors; the first construction sub-module is used to construct a directed association structure graph based on the M risk association factors, wherein the directed association structure graph includes M nodes corresponding to the M risk association factors, and the M nodes are associated with each other through directed edges, and the weights of the directed edges are used to characterize the conditional probabilities between the associated nodes directly connected to the directed edges; the second construction sub-module is used to construct a full conditional probability table for the M risk association factors based on the multiple groups of first historical transaction data and the directed association structure graph.

[0205] According to an embodiment of the present disclosure, the transaction data processing device 600 further includes a fourth reading module and an updating module.

[0206] The fourth reading module is used to read from the database multiple groups of second historical transaction data associated with the multiple groups of second historical transactions within a second predetermined historical time period, wherein each group of second historical transaction data includes at least M second historical transaction arrays corresponding to M risk association factors; the updating module is used to update the full conditional probability table based on the multiple groups of second historical transaction data.

[0207] According to an embodiment of the present disclosure, the transaction data processing device 600 further includes a processing submodule.

[0208] The processing submodule is used to perform data preprocessing on multiple groups of first historical transaction data, and the data preprocessing at least includes: removing abnormal data in multiple groups of first historical transaction data, completing missing data in multiple groups of first historical transaction data, and removing duplicate data in multiple groups of first historical transaction data.

[0209] According to an embodiment of the present disclosure, the output module includes a second computing submodule, a third computing submodule, a fourth computing submodule, a fifth computing submodule, and a sixth computing submodule.

[0210] The second calculation submodule is used to calculate the basic reference value based on the first posterior risk probability, the first a priori risk probability, the second posterior risk probability, and the second a priori risk probability of each risk-related factor; the third calculation submodule is used to calculate the first reference value based on the first posterior risk probability and the first a priori risk probability of each risk-related factor; the fourth calculation submodule is used to calculate the second reference value based on the second posterior risk probability and the second a priori risk probability of each risk-related factor; the fifth calculation submodule is used to calculate the first risk prediction result based on the first reference value and the basic reference value; the sixth calculation submodule is used to calculate the second risk prediction result based on the second reference value and the basic reference value.

[0211] According to an embodiment of the present disclosure, any multiple modules of the first reading module 610, the second reading module 620, the calculation module 630, the output module 640 and the sending module 650 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first reading module 610, the second reading module 620, the calculation module 630, the output module 640 and the sending module 650 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or by any one of the three implementation methods of software, hardware and firmware or by a suitable combination of any of them. Alternatively, at least one of the first reading module 610 , the second reading module 620 , the calculating module 630 , the outputting module 640 and the sending module 650 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be executed.

[0212] Figure 7 A block diagram of an electronic device suitable for implementing a transaction data processing method according to an embodiment of the present disclosure is schematically shown.

[0213] like Figure 7 As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0214] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in one or more memories.

[0215] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the input / output (I / O) interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 707 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0216] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0217] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0218] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the transaction data processing method provided by the embodiment of the present disclosure.

[0219] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 701. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0220] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 707, and / or installed from the removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0221] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 707, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0222] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0223] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0224] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0225] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. The scope of the present disclosure is defined by the attached claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A transaction data processing method, comprising: Reading transaction data to be processed associated with the target transaction from the message middleware, wherein the transaction data to be processed includes M association arrays corresponding to the M risk association factors; Reading a pre-constructed full conditional probability table for the M risk-related factors from a database, and reading a preset a priori risk probability of each of the risk-related factors; Based on the M association arrays, the full conditional probability table, and the preset priori risk probability of each risk association factor, the posterior risk probability of each risk association factor is calculated; Inputting the posterior risk probability of each risk association factor and the preset a priori risk probability into a risk model, and outputting a risk prediction result of the target transaction; The risk prediction result is sent to a monitoring system.

2. The method according to claim 1, wherein: Based on the M association arrays, the full conditional probability table, and the preset a priori risk probability of each risk association factor, the posterior risk probability of each risk association factor is calculated, including: Associating the M association arrays with the full conditional probability table to determine the target conditional probability of each of the M risk association factors based on the target transaction; The posterior risk probability of each risk association factor is calculated based on the full conditional probability table, the target conditional probability of each of the M risk association factors, and the preset priori risk probability of each risk association factor.

3. The method according to claim 1, further comprising: Reading from a database a plurality of groups of first historical transaction data associated with a plurality of groups of first historical transactions within a first predetermined historical time period, wherein each group of the first historical transaction data at least includes M first historical transaction arrays corresponding to the M risk association factors; Constructing a directed association structure graph based on the M risk association factors, wherein the directed association structure graph includes M nodes corresponding to the M risk association factors, the M nodes are associated with each other through directed edges, and the weights of the directed edges are used to represent the conditional probabilities between the associated nodes directly connected to the directed edges; A full conditional probability table for the M risk association factors is constructed based on the multiple groups of first historical transaction data and the directed association structure graph.

4. The method according to claim 3, further comprising: Reading from the database a plurality of groups of second historical transaction data associated with the plurality of groups of second historical transactions within a second predetermined historical time period, wherein each group of the second historical transaction data at least includes M second historical transaction arrays corresponding to the M risk association factors; Based on the multiple groups of second historical transaction data, the full conditional probability table is updated.

5. The method according to claim 3, further comprising: The multiple groups of first historical transaction data are subjected to data preprocessing, wherein the data preprocessing at least includes: removing abnormal data in the multiple groups of first historical transaction data, completing missing data in the multiple groups of first historical transaction data, and removing duplicate data in the multiple groups of first historical transaction data.

6. The method according to claim 5, wherein: The abnormal data in the multiple groups of first historical transaction data include at least: first historical transaction data in which the remittance amount is greater than a preset amount threshold, first historical transaction data in which the remittance frequency within a predetermined time window is greater than a preset frequency threshold, first historical transaction data in which the payment address involves a predetermined risk area, and first historical transaction data in which the remittance purpose involves a predetermined risk purpose.

7. The method according to any one of claims 1 to 6, wherein: The M risk-related factors include: remitter information, remittance information, payee economic development index, remittance purpose, payee information, and payee environmental stability index.

8. The method according to claim 7, wherein: In the directed association structure diagram, the M nodes correspond to the M risk association factors, wherein the remitter information node, the remittance information node, and the payee economic development index node are root nodes, and the remittance purpose node, the payee information node, and the payee environmental stability index node are child nodes, and the root node and the child nodes are connected by directed edges pointing to the child nodes.

9. The method according to claim 1, wherein: The posterior risk probability includes a first posterior risk probability and a second posterior risk probability, and the preset a priori risk probability includes a first a priori risk probability and a second a priori risk probability; Inputting the posterior risk probability of each risk association factor and the preset a priori risk probability into a risk model, and outputting the risk prediction result of the target transaction comprises: A basic reference value is calculated based on the first a priori risk probability, the first a priori risk probability, the second a priori risk probability, and the second a priori risk probability of each of the risk association factors; A first reference value is calculated based on the first a priori risk probability and the first a priori risk probability of each of the risk association factors; A second reference value is calculated based on the second a priori risk probability and the second a priori risk probability of each of the risk association factors; Calculate a first risk prediction result according to the first reference value and the basic reference value; A second risk prediction result is calculated based on the second reference value and the basic reference value.

10. A transaction data processing device, comprising: A first reading module is used to read the to-be-processed transaction data associated with the target transaction from the message middleware, wherein the to-be-processed transaction data includes M association arrays corresponding to the M risk association factors; A second reading module is used to read a pre-constructed full conditional probability table for the M risk-related factors from a database, and to read a preset a priori risk probability of each of the risk-related factors; A calculation module, configured to calculate the posterior risk probability of each risk association factor based on the M association arrays, the full conditional probability table, and the preset priori risk probability of each risk association factor; an output module, configured to input the posterior risk probability of each risk association factor and the preset a priori risk probability into a risk model, and output a risk prediction result of the target transaction; and A sending module is used to send the risk prediction result to the monitoring system.

11. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the method according to any one of claims 1 to 9.

Images