Suspicious Transaction Report Screening Task Allocation Method, Device, Equipment and Storage Medium

Abstract

Embodiments of the present invention relate to the field of big data technology, and disclose a method, device, equipment, and storage medium for allocating suspicious transaction report screening tasks. Based on suspicious transaction data, the implementing institutions of the suspicious transaction reports to be screened are determined respectively according to the set allocation rules and machine learning models, and a result set of implementing institutions corresponding to the suspicious transaction reports to be screened is formed. The two determination methods complement each other to form a result set of implementing institutions corresponding to the suspicious transaction reports to be screened. Then, according to the integrity of the customer information of the implementing institutions in the result set of implementing institutions corresponding to the suspicious transaction reports to be screened, the target implementing institution corresponding to the suspicious transaction reports to be screened is determined, which can realize determining the implementing institution with the most complete customer information as the target implementing institution of the suspicious transaction reports to be screened, and further provide an effective basis for the analysis of the screening personnel. The technical solution of this embodiment is beneficial to improving the accuracy of the method for allocating suspicious transaction report screening tasks and beneficial to improving the task transfer speed.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of big data technology, and in particular, to a method, device, equipment, and storage medium for allocating suspicious transaction report screening tasks. Background Art

[0002] Economic crimes caused by suspicious transactions pose a threat to the security and stability of the financial system.

[0003] Suspicious transactions are transactions screened through transaction monitoring standards, and illegal fund transfers are one type of suspicious transactions. After a financial institution obtains a suspicious transaction report corresponding to a suspicious transaction, it needs to submit the suspicious transaction report to screening personnel in a timely manner.

[0004] The existing methods for allocating manual screening tasks for suspicious transaction reports generally allocate them to the customer affiliated institution (the account opening institution) or the institution with the largest transaction amount. However, the above allocation methods may cause the screening personnel to need to analyze customers or trading counterparts outside their jurisdiction, and without the necessary customer information and counterparty information, it will lead to the screening personnel being unable to conduct effective analysis. Summary of the Invention

[0005] The present invention provides a method, device, equipment, and storage medium for allocating suspicious transaction report screening tasks to allocate the suspicious transaction reports to be screened to at least the executing institutions with relatively complete customer information.

[0006] In a first aspect, the embodiments of the present invention provide a method for allocating suspicious transaction report screening tasks, including:

[0007] Obtain suspicious transaction data;

[0008] Based on the suspicious transaction data, determine the executing institutions of the suspicious transaction reports to be screened according to the set allocation rules and machine learning models respectively, and form a result set of executing institutions corresponding to the suspicious transaction reports to be screened;

[0009] According to the completeness of the customer information of the executing institutions in the result set of executing institutions corresponding to the suspicious transaction reports to be screened, determine the target executing institution corresponding to the suspicious transaction reports to be screened.

[0010] Optionally, the suspicious transaction data includes historical suspicious transaction data and suspicious transaction reports to be screened, and the historical suspicious transaction data includes historical suspicious transaction reports and corresponding actual executing institutions;

[0011] Based on the suspicious transaction data, determine the executing institutions of the suspicious transaction reports to be screened according to the set allocation rules and machine learning models respectively, and form a result set of executing institutions corresponding to the suspicious transaction reports to be screened, including:

[0012] Based on the specific information of the suspicious transaction report to be screened, determine the first implementing agency of the suspicious transaction report to be screened according to the set allocation rules;

[0013] Based on the historical suspicious transaction reports and the corresponding actual implementing agencies, as well as the specific information of the suspicious transaction report to be screened, determine the second implementing agency of the suspicious transaction report to be screened according to the machine learning model;

[0014] Take the first implementing agency and the second implementing agency corresponding to the suspicious transaction report to be screened as the result set of the implementing agencies corresponding to the suspicious transaction report to be screened.

[0015] Optionally, based on the specific information of the suspicious transaction report to be screened, determining the first implementing agency of the suspicious transaction report to be screened according to the set allocation rules includes:

[0016] Based on the specific information of the suspicious transaction report to be screened, determine whether there is a place where the suspicious transaction occurred for multiple suspicious transactions corresponding to the suspicious transaction report to be screened;

[0017] If so, determine the first implementing agency of the suspicious transaction report to be screened as the implementing agency at the place where the suspicious transaction occurred;

[0018] If not, determine the first implementing agency of the suspicious transaction report to be screened as the implementing agency at the place where the frequent transactions occurred or the account opening institution.

[0019] Optionally, the specific information of the suspicious transaction report to be screened includes multiple suspicious transactions and the administrative division code of the corresponding counterparty financial institution network point for each suspicious transaction;

[0020] Based on the specific information of the suspicious transaction report to be screened, determining whether there is a place where the suspicious transaction occurred for multiple suspicious transactions corresponding to the suspicious transaction report to be screened includes:

[0021] According to the total amount of all suspicious transactions in the suspicious transaction report to be screened and the total amount of suspicious transactions corresponding to the same administrative division code of the counterparty financial institution network point, determine whether there is a place where the suspicious transaction occurred for multiple transactions corresponding to the suspicious transaction report to be screened; or,

[0022] According to the total number of transaction records of all suspicious transactions in the suspicious transaction report to be screened and the number of transaction records of suspicious transactions corresponding to the same administrative division code of the counterparty financial institution network point, determine whether there is a place where the suspicious transaction occurred for multiple suspicious transactions corresponding to the suspicious transaction report to be screened.

[0023] Optionally, determining the first implementing agency for screening the suspicious transaction report to be screened as the implementing agency where the frequent transactions occurred or the account opening institution includes:

[0024] Based on the specific information of the suspicious transaction report to be screened, determine whether there is a frequent transaction place for multiple transactions corresponding to the suspicious transaction report to be screened;

[0025] If so, determine that the first implementing institution of the suspicious transaction report to be screened is the implementing institution at the frequent transaction place;

[0026] If not, determine that the first implementing institution of the suspicious transaction report to be screened is the account opening institution.

[0027] Optionally, the specific information of the suspicious transaction report to be screened includes multiple transactions and the financial institution branch code corresponding to each transaction;

[0028] Based on the specific information of the suspicious transaction report to be screened, determining whether there is a frequent transaction place for the transaction corresponding to the suspicious transaction report to be screened includes:

[0029] According to the total amount of transactions of the set transaction type in the suspicious transaction report to be screened and the total amount of transactions of the set transaction type corresponding to the same financial institution branch code, determine whether there is a frequent transaction place for multiple transactions corresponding to the suspicious transaction report to be screened; or,

[0030] According to the number of transactions of the set transaction type in the suspicious transaction report to be screened and the number of transactions of the set transaction type corresponding to the same pair of financial institution branch codes, determine whether there is a frequent transaction place for multiple transactions corresponding to the suspicious transaction report to be screened;

[0031] Among them, the transactions of the set type are transactions other than exempted transactions.

[0032] Optionally, based on the historical suspicious transaction reports and the corresponding actual implementing institutions, and the specific information of the suspicious transaction report to be screened, determine the second implementing institution of the suspicious transaction report to be screened according to a machine learning model, including:

[0033] Use the historical suspicious transaction reports as the input of the machine learning model, and use the actual implementing institutions corresponding to the historical suspicious transaction reports as the output of the machine learning model to train the machine learning model to obtain a trained machine learning model;

[0034] Input each suspicious transaction report to be screened into the trained machine learning model to determine the second implementing institution of the suspicious transaction report to be screened.

[0035] Optionally, the machine learning model is a discriminant model.

[0036] Optionally, according to the completeness of the customer information of each implementing institution in the implementing institution result set corresponding to the suspicious transaction report to be screened, determine the target implementing institution corresponding to the suspicious transaction report to be screened, including:

[0037] Determine whether the first executing agency can perform the screening task according to the completeness of the customer information of the first executing agency;

[0038] If so, determine the first executing agency as the target executing agency;

[0039] If not, determine the target executing agency according to the relationship between the first executing agency and the account-opening agency and the relationship between the first executing agency and the second executing agency.

[0040] Optionally, determining the target executing agency according to the relationship between the first executing agency and the account-opening agency and the relationship between the first executing agency and the second executing agency includes:

[0041] Judge whether the first executing agency is the account-opening agency;

[0042] If so, determine the first executing agency as the target executing agency;

[0043] If not, determine the target executing agency according to the relationship between the first executing agency and the second executing agency.

[0044] Optionally, determining the target executing agency according to the relationship between the first executing agency and the second executing agency includes:

[0045] Judge whether the first executing agency and the second executing agency are the same agency;

[0046] If so, submit the screening task of the suspicious transaction report to be screened to the superior agency of the first executing agency;

[0047] If not, determine the target executing agency according to the completeness of the customer information of the second executing agency.

[0048] Optionally, determining the target executing agency according to the completeness of the customer information of the second executing agency includes:

[0049] Judge whether the customer information of the second executing agency is complete;

[0050] If so, determine the second executing agency as the target executing agency;

[0051] If not, submit the screening task of the suspicious transaction report to be screened to the superior agency of the second executing agency.

[0052] In a second aspect, an embodiment of the present invention further provides a suspicious transaction report screening task allocation device, including:

[0053] An acquisition module, configured to acquire suspicious transaction data;

[0054] A result set determination module, configured to determine, based on suspicious transaction data, the executing institutions of the suspicious transaction reports to be screened according to the set allocation rules and machine learning models respectively, and form a result set of the executing institutions corresponding to the suspicious transaction reports to be screened;

[0055] A target executing institution determination module, configured to determine the target executing institution corresponding to the suspicious transaction report to be screened according to the integrity of the customer information of the executing institutions in the result set of the executing institutions corresponding to the suspicious transaction report to be screened.

[0056] Thirdly, an embodiment of the present invention further provides a device, which includes:

[0057] One or more processors;

[0058] A storage device, configured to store one or more programs;

[0059] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the first aspect.

[0060] Fourthly, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the method as described in the first aspect is implemented.

[0061] Fifthly, an embodiment of the present invention provides a computer program product, which includes computer-executable instructions, and the computer-executable instructions are used to implement the method as described in the first aspect when executed.

[0062] The method, device, equipment and storage medium for screening and assigning suspicious transaction reports provided by the embodiments of the present invention determine the executing institutions of the suspicious transaction reports to be screened based on suspicious transaction data according to the set allocation rules and machine learning models respectively, and form a result set of the executing institutions corresponding to the suspicious transaction reports to be screened, so as to implement determining the executing institutions of the suspicious transaction reports to be screened in two ways, and the two determination methods complement each other to form a result set of the executing institutions corresponding to the suspicious transaction reports to be screened. Then, according to the integrity of the customer information of the executing institutions in the result set of the executing institutions corresponding to the suspicious transaction report to be screened, the target executing institution corresponding to the suspicious transaction report to be screened is determined, which can implement determining the executing institution with the most complete customer information as the target executing institution of the suspicious transaction report to be screened, and further provide an effective basis for the analysis of the screening personnel. The technical solution of this embodiment is beneficial to improving the accuracy of the method for screening and assigning suspicious transaction reports, and can quickly find the target executing institution of the suspicious transaction report, which is beneficial to improving the task flow speed. Description of the Drawings

[0063] Figure 1 is a flowchart of a method for screening and assigning suspicious transaction reports provided by an embodiment of the present invention;

[0064] Figure 2 It is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention;

[0065] Figure 3 It is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention;

[0066] Figure 4 It is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention;

[0067] Figure 5 It is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention;

[0068] Figure 6 It is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention;

[0069] Figure 7 It is a schematic structural diagram of a device for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention;

[0070] Figure 8 It is a schematic structural diagram of a device provided by an embodiment of the present invention. Detailed implementation manners

[0071] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the present invention, rather than limiting the present invention. Additionally, it should be noted that for the sake of description, only parts related to the present invention rather than all structures are shown in the accompanying drawings.

[0072] Figure 1 It is a flowchart of a method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention. This embodiment is applicable to the situation of allocating suspicious transaction report screening tasks. This method can be executed by a device for allocating suspicious transaction report screening tasks, and this device can be implemented in a software and / or hardware manner. This device can be configured in an electronic device, such as a computer device. As Figure 1 shown, this method can specifically include:

[0073] Step 110, obtain suspicious transaction data.

[0074] Among them, a suspicious transaction refers to a transaction screened out through transaction monitoring criteria.

[0075] Suspicious transaction data may include suspicious transaction reports. The suspicious transaction reports in the suspicious transaction data may include to-be-screened suspicious transaction reports and historical suspicious transaction reports. Among them, the to-be-screened suspicious transaction reports can be assigned to the target executing agency for screening through the suspicious transaction report task assignment method of this embodiment. The historical suspicious transaction reports are the suspicious transaction reports that have been assigned and completed. The suspicious transaction data may also include the actual executing agencies corresponding to the historical suspicious transaction reports. The suspicious transaction reports may include at least part of the content specified in the data dictionary of suspicious transaction reports for the banking industry in the interface specification for reporting large-value transactions and suspicious transactions of financial institutions. The suspicious transaction data can be a report obtained by manually analyzing suspicious transactions or a report obtained by analyzing suspicious transactions through existing algorithms. The suspicious transaction data can be stored in the form of electronic documents. When obtaining the suspicious transaction data, after establishing a connection with the storage device storing the suspicious transaction data, the suspicious transaction data can be read.

[0076] Step 120: Based on the suspicious transaction data, determine the executing agencies of the to-be-screened suspicious transaction reports respectively according to the set assignment rules and the machine learning model, and form a result set of the executing agencies corresponding to the to-be-screened suspicious transaction reports.

[0077] Specifically, based on the suspicious transaction data, one executing agency of the to-be-screened suspicious transaction report can be obtained according to the set assignment rules; based on the suspicious transaction data, one executing agency of the to-be-screened suspicious transaction report can be determined according to the machine learning model. Among them, the two executing agencies obtained according to the set assignment rules and the machine learning model may be the same or different. The two determination methods of the set assignment rules and the machine learning model can complement each other. The executing agencies of the to-be-screened suspicious transaction reports determined by the set assignment rules and the machine learning model respectively are used as the result set of the executing agencies of the to-be-screened suspicious transaction reports. The set assignment rules can be set according to the completeness of the customer information and / or the completeness of the counterparty information corresponding to the suspicious transaction report. For example, the set assignment rules may include preferentially determining the executing agency with the highest completeness of the customer information and / or the completeness of the counterparty information as the executing agency of the to-be-screened suspicious transaction report. The machine learning model can be any machine learning model in the prior art, and this embodiment does not make specific limitations here.

[0078] Step 130: Determine the target executing agency corresponding to the to-be-screened suspicious transaction report according to the completeness of the customer information of the executing agency in the result set of the executing agencies corresponding to the to-be-screened suspicious transaction report.

[0079] Specifically, each transaction report to be screened corresponds to a result set of executing institutions. In this step, the target executing institution of the suspicious transaction report to be screened is determined according to the completeness of the customer information of each executing institution in the result set of executing institutions. Optionally, step 130 may include: determining the executing institution with the highest completeness of the customer information of the executing institution in the result set of executing institutions corresponding to the suspicious transaction report to be screened as the target executing institution of the suspicious transaction report to be screened.

[0080] The method for allocating suspicious transaction report screening tasks provided in this embodiment determines the executing institutions of the suspicious transaction reports to be screened based on suspicious transaction data according to the set allocation rules and machine learning models respectively, forming a result set of executing institutions of the suspicious transaction reports to be screened, and realizes determining the executing institutions of the suspicious transaction reports to be screened through two methods. The two determination methods complement each other to form a result set of executing institutions corresponding to the suspicious transaction reports to be screened. Then, according to the completeness of the customer information of the executing institutions in the result set of executing institutions corresponding to the suspicious transaction reports to be screened, the target executing institution corresponding to the suspicious transaction reports to be screened is determined, which can realize determining the executing institution with the most complete customer information as the target executing institution of the suspicious transaction reports to be screened, and further provide an effective basis for the analysis of the screening personnel. The technical solution of this embodiment is beneficial to improving the accuracy of the method for allocating suspicious transaction report screening tasks, and can quickly find the target executing institution of the suspicious transaction report, which is beneficial to improving the task transfer speed.

[0081] Figure 2 is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention. Refer to Figure 2 , and this method for allocating suspicious transaction report screening tasks includes:

[0082] Step 210, obtain suspicious transaction data.

[0083] Optionally, the suspicious transaction data includes historical suspicious transaction data and transaction reports to be screened. The historical suspicious transaction data includes historical suspicious transaction reports and corresponding actual executing institutions.

[0084] Step 220, based on the specific information of the suspicious transaction report to be screened, determine the first executing institution of the suspicious transaction report to be screened according to the set allocation rules.

[0085] Specifically, a suspicious transaction report to be screened can correspond to multiple transactions of a customer, and the specific information of the suspicious transaction report to be screened can include the transaction location and transaction amount of each transaction of the corresponding customer. In this step, the first executing agency is obtained according to the set allocation rule. Optionally, the set allocation rule can include determining the executing agency at the place where the suspicious transaction occurs as the first executing agency of the suspicious transaction report to be screened, where the executing agency at the place where the suspicious transaction occurs is the executing agency with the highest integrity of the counterparty information of the suspicious transaction.

[0086] Step 230: Based on the historical suspicious transaction reports, the corresponding actual executing agencies, and the specific information of the suspicious transaction reports to be screened, determine the second executing agency of the suspicious transaction reports to be screened according to the machine learning model.

[0087] Optionally, this step 220 includes:

[0088] Use the historical suspicious transaction reports as the input of the machine learning model, and use the actual executing agencies corresponding to the historical suspicious transaction reports as the output of the machine learning model to train the machine learning model to obtain a trained machine learning model;

[0089] Input each suspicious transaction report to be screened into the trained machine learning model to determine the second executing agency of the suspicious transaction report to be screened.

[0090] Among them, in this embodiment, the input of the machine learning model can be a large number of historical suspicious transaction reports, and each historical suspicious transaction report corresponds to an actual executing agency. Specifically, the actual executing agency corresponding to the historical suspicious transaction report is the executing agency with the highest integrity of the customer information and / or counterparty information. Using the historical suspicious transaction reports as the input of the machine learning model and the actual executing agencies corresponding to the historical suspicious transaction reports as the output of the machine learning model to train the machine learning model, a trained machine learning model can be obtained, so that after inputting the suspicious transaction report to be screened into the trained machine learning model, the obtained second executing agency is likely to be the executing agency with the highest integrity of the customer information and / or counterparty information.

[0091] Optionally, the machine learning model is a discriminative model, such as K-Nearest Neighbor, neural network, support vector machine. The discriminative model saves computing resources and has a higher learning accuracy. Selecting the machine learning model as a discriminative model can, on the one hand, improve the execution efficiency of the suspicious transaction report screening task allocation method, and on the other hand, improve the accuracy of the trained machine learning model.

[0092] Step 240: Use the first executing agency and the second executing agency corresponding to the suspicious transaction report to be screened as the execution agency result set corresponding to the suspicious transaction report to be screened.

[0093] Specifically, since the first execution institution and the second execution institution are determined in different ways, where the determination of the first execution institution is based on set rules, and the determination of the second execution institution takes into account actual factors (because when training a machine learning model, historical suspicious transaction reports are used as input, and the actual execution institution corresponding to the historical suspicious transaction report is used as the output second execution institution), the determination method of the first execution institution is complementary to the determination method of the second execution institution, making it easier for the formed execution institution result set to include the execution institution with the most complete customer information and / or counterparty information. Furthermore, when determining the target execution institution subsequently, a more reasonable target execution institution can be obtained.

[0094] Step 250: Determine the target execution institution of the suspicious transaction report to be screened according to the completeness of the customer information of the execution institution in the execution institution result set corresponding to the suspicious transaction report to be screened; this step is the same as step 130 in the above embodiment, and is not specifically limited in this embodiment.

[0095] Figure 3 is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention. Refer to Figure 3 and this method for allocating suspicious transaction report screening tasks includes:

[0096] Step 310: Obtain suspicious transaction data.

[0097] Optionally, the suspicious transaction data includes historical suspicious transaction data and the suspicious transaction report to be screened, and the historical suspicious transaction data includes historical suspicious transaction reports and corresponding actual execution institutions.

[0098] Step 320: Based on the specific information of the suspicious transaction report to be screened, determine whether there is a suspicious transaction occurrence location for multiple suspicious transactions corresponding to the suspicious transaction report to be screened.

[0099] Optionally, the specific information of the suspicious transaction report to be screened includes multiple suspicious transactions and the administrative division code of the corresponding counterparty (transaction counterparty) financial institution network point for each suspicious transaction. The above step 320 includes: determining whether there is a suspicious transaction occurrence location for multiple suspicious transactions corresponding to the suspicious transaction report to be screened according to the total amount of all suspicious transactions in the suspicious transaction report to be screened and the total amount of suspicious transactions corresponding to the same administrative division code of the counterparty financial institution network point.

[0100] Specifically, when the ratio of the total amount of suspicious transactions corresponding to the same administrative division code of the counterparty financial institution network point to the total amount of all suspicious transactions in the suspicious transaction report to be screened is greater than or equal to the first set threshold, the administrative region corresponding to the administrative division code of the counterparty financial institution network point can be set as the suspicious transaction occurrence location. Optionally, the first set threshold is greater than 50%, for example, the first set threshold can be equal to 70%.

[0101] Alternatively, step 320 above includes: determining whether there is a suspicious transaction occurrence location for multiple suspicious transactions corresponding to the suspicious transaction report to be screened based on the total number of transaction records of all suspicious transactions in the suspicious transaction report to be screened and the number of suspicious transaction records corresponding to the administrative division code of the same counterparty financial institution branch.

[0102] Specifically, when the ratio of the number of suspicious transaction records corresponding to the administrative division code of the same counterparty financial institution branch to the total number of all suspicious transaction records in the suspicious transaction report to be screened is greater than or equal to a second set threshold, the administrative region corresponding to the administrative division code of this counterparty financial institution branch may be determined as the suspicious transaction occurrence location. Optionally, the second set threshold is greater than 50%, for example, the second set threshold may be equal to 70%.

[0103] If so, execute step 330.

[0104] Step 330: Determine the first executing institution of the suspicious transaction report to be screened as the executing institution at the suspicious transaction occurrence location.

[0105] Specifically, according to step 320 above, the executing institution at the suspicious transaction occurrence location has the most complete counterparty information. Therefore, when there is a suspicious transaction occurrence location for multiple suspicious transactions corresponding to the suspicious transaction report to be screened, determining the first executing institution as the executing institution at the suspicious transaction occurrence location can make the determined first executing institution have the most complete counterparty information.

[0106] If not, execute step 340.

[0107] Step 340: Determine the first executing institution of the suspicious transaction report to be screened as the executing institution at the frequent transaction occurrence location or the account opening institution.

[0108] Specifically, the executing institution at the frequent transaction occurrence location has the most complete customer information, and the account opening institution is most likely to collect more customer information. Therefore, when there is no suspicious transaction occurrence location, determining the executing institution at the frequent transaction occurrence location or the account opening institution as the first executing institution can make the determined first executing institution have the most complete customer information or be most likely to collect more customer information.

[0109] Step 350: Based on the historical suspicious transaction reports and the corresponding actual executing institutions, and the specific information of the suspicious transaction report to be screened, determine the second executing institution of the suspicious transaction report to be screened according to the machine learning model; this step is the same as step 230 in the above embodiment and will not be elaborated here.

[0110] Step 360: Use the first implementing institution and the second implementing institution corresponding to the suspicious transaction report to be screened as the result set of implementing institutions corresponding to the suspicious transaction report to be screened; this step is the same as step 240 in the above embodiment and will not be elaborated here.

[0111] Step 370: Determine the target implementing institution of the suspicious transaction report to be screened according to the completeness of the implementing institution customer information in the result set of implementing institutions corresponding to the suspicious transaction report to be screened; this step is the same as step 250 in the above embodiment and is not specifically limited in this embodiment.

[0112] It should be noted that in the technical solution of this embodiment, steps 320 - 340 and step 350 can be executed in parallel, that is, the determination of the first implementing institution and the second implementing institution can be executed in parallel or sequentially, and this embodiment is not specifically limited here.

[0113] Figure 4 is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention. Refer to Figure 4 , and this method for allocating suspicious transaction report screening tasks includes:

[0114] Step 410: Obtain suspicious transaction data; this step is the same as step 310 in the above embodiment and will not be elaborated here.

[0115] Step 420: Based on the specific information of the suspicious transaction report to be screened, determine whether there is a place where the suspicious transaction occurred for multiple suspicious transactions corresponding to the suspicious transaction report to be screened; this step is the same as step 320 in the above embodiment and will not be elaborated here.

[0116] If so, execute step 430,

[0117] Step 430: Determine the first implementing institution for screening the suspicious transaction report to be screened as the implementing institution where the suspicious transaction occurred; this step is the same as step 340 in the above embodiment and will not be elaborated here.

[0118] If not, execute step 440,

[0119] Step 440: Based on the specific information of the suspicious transaction report to be screened, determine whether there is a place where regular transactions occurred for multiple transactions corresponding to the suspicious transaction report to be screened.

[0120] Optionally, the specific information of the suspicious transaction report to be screened includes multiple transactions and the financial institution branch code corresponding to each transaction. Optionally, the above step 440 includes:

[0121] Judging whether there is a frequent transaction place for multiple transactions corresponding to a suspicious transaction report to be screened according to the total amount of transactions of the set transaction types in the suspicious transaction report to be screened and the total amount of transactions of the set transaction types corresponding to the same financial institution branch code.

[0122] Specifically, when the ratio of the total amount of transactions of the set transaction types corresponding to the same financial institution branch code to the total amount of transactions of all set transaction types in the suspicious transaction report to be screened is greater than or equal to a third set threshold, the administrative region corresponding to the financial institution branch code can be taken as the frequent transaction place. Optionally, the third set threshold is greater than 50%, for example, the third set threshold can be equal to 70%.

[0123] Or, the above step 440 includes:

[0124] Judging whether there is a frequent transaction place for multiple transactions corresponding to a suspicious transaction report to be screened according to the number of transaction records of the set transaction types in the suspicious transaction report to be screened and the number of transaction records of the set transaction types corresponding to the same pair of financial institution branch codes;

[0125] Specifically, when the ratio of the number of transaction records of the set transaction types corresponding to the same financial institution branch code to the number of transaction records of all set transaction types in the suspicious transaction report to be screened is greater than or equal to a fourth set threshold, the administrative region corresponding to the financial institution branch code can be taken as the frequent transaction place. Optionally, the fourth set threshold is greater than 50%, for example, the fourth set threshold can be equal to 70%.

[0126] Wherein, the transactions of the set transaction types are transactions other than exempted transactions.

[0127] If so, that is, when there is a frequent transaction place for the transactions corresponding to the suspicious transaction report to be screened, step 450 is executed.

[0128] Step 450, determining the first executing institution of the suspicious transaction report to be screened as the executing institution at the frequent transaction place.

[0129] Specifically, according to the above steps, the executing institution at the frequent transaction place has the most complete customer information. Therefore, when there is a frequent transaction place for multiple transactions corresponding to the suspicious transaction report to be screened, determining the first executing institution as the executing institution at the frequent transaction place can make the determined first executing institution have the most complete customer information.

[0130] If not, that is, when there is no frequent transaction place for the transactions corresponding to the suspicious transaction report to be screened, step 460 is executed.

[0131] Step 460, determining the first executing institution of the suspicious transaction report to be screened as the account-opening institution.

[0132] Specifically, it is relatively easier for the account-opening institution to obtain more customer information. Therefore, when there is no regular place of transaction for the suspicious transaction report to be screened, determining the account-opening institution as the first executing institution for the suspicious transaction report to be screened can ensure that the first executing institution has more accessible customer information.

[0133] Step 470: Based on the historical suspicious transaction reports, the corresponding actual executing institutions, and the specific information of the suspicious transaction reports to be screened, determine the second executing institution for the suspicious transaction reports to be screened according to the machine learning model; this step is the same as step 230 in the above embodiment and will not be elaborated here.

[0134] Step 480: Use the first executing institution and the second executing institution corresponding to the suspicious transaction report to be screened as the result set of the executing institutions corresponding to the suspicious transaction report to be screened; this step is the same as step 240 in the above embodiment and will not be elaborated here.

[0135] Step 490: Determine the target executing institution for the suspicious transaction report to be screened according to the integrity of the customer information of the executing institutions in the result set of the executing institutions corresponding to the suspicious transaction report to be screened; this step is the same as step 250 in the above embodiment and will not be specifically limited in this embodiment.

[0136] It should be noted that in the technical solution of this embodiment, steps 420 - 460 and step 470 can be executed in parallel, that is, the determination of the first executing institution and the second executing institution can be executed in parallel or sequentially, and this embodiment will not be specifically limited here.

[0137] Figure 5 is a flowchart of another method for allocating suspicious transaction report screening tasks provided by an embodiment of the present invention. This embodiment is based on Figures 2 - 4 the corresponding implementation plan, referring to Figure 5 , taking this embodiment as an example based on Figure 2 the corresponding implementation plan, the method for allocating and screening suspicious transaction report tasks includes:

[0138] Step 510: Obtain suspicious transaction data, which is the same as step 210 in the above embodiment and will not be elaborated here.

[0139] Optionally, the suspicious transaction data includes historical suspicious transaction data and suspicious transaction reports to be screened, and the historical suspicious transaction data includes historical suspicious transaction reports and the corresponding actual executing institutions.

[0140] Step 520: Based on the specific information of the suspicious transaction report to be screened, determine the first executing institution for the suspicious transaction report to be screened according to the set allocation rules; this step is the same as step 220 in the above embodiment and will not be elaborated here.

[0141] Step 530: Based on the historical suspicious transaction reports, the corresponding actual executing institutions, and the specific information of the suspicious transaction reports to be screened, determine the second executing institution of the suspicious transaction reports to be screened according to the machine learning model; this step is the same as step 230 in the above embodiment and will not be elaborated here.

[0142] Step 540: Use the first executing institution and the second executing institution corresponding to the suspicious transaction reports to be screened as the result set of the executing institutions corresponding to the suspicious transaction reports to be screened; this step is the same as step 240 in the above embodiment and will not be elaborated here.

[0143] Step 550: Determine whether the first executing institution can perform the screening task according to the completeness of the customer information of the first executing institution.

[0144] If so, execute step 560.

[0145] Step 560: Determine the first executing institution as the target executing institution.

[0146] Specifically, when determining the first executing institution according to the Figure 3 and Figure 4 corresponding technical solutions, preferably determine the executing institution at the place where the suspicious transaction occurred as the first executing institution, and the transaction counterparty information of the executing institution at the place where the suspicious transaction occurred is the most complete. When there is no place where the suspicious transaction occurred, determine the executing institution at the place where the regular transactions occurred as the first executing institution, and the customer information and transaction situation information of the executing institution at the place where the regular transactions occurred are the most complete. When there is no place where the suspicious transaction occurred and no place where the regular transactions occurred, determine the account-opening institution as the first executing institution, and the account-opening institution is most likely to obtain more customer information. Therefore, when this solution is based on Figure 3 or Figure 4When based on the corresponding technical solution, when the first executing institution is the executing institution at the place where the suspicious transaction occurred, in the subsequent steps, it is determined whether the first executing institution can perform the screening task according to the completeness of the customer information of the first executing institution, which can ensure that when the completeness of the customer information of the first executing institution meets the requirements, the executing institution with the most complete counterparty information and customer information can be determined as the target executing institution. When the first executing institution is the executing institution at the place where the regular transaction occurred, in the subsequent steps, it is determined whether the first executing institution can perform the screening task according to the completeness of the customer information of the first executing institution, which can ensure that when the completeness of the customer information of the first executing institution meets the requirements, the executing institution with the most complete transaction situation information and customer information can be determined as the target executing institution. When the first executing institution is the account-opening institution, in the subsequent steps, it is determined whether the first executing institution can perform the screening task according to the completeness of the customer information of the first executing institution, which can ensure that when the completeness of the customer information of the first executing institution meets the requirements, the executing institution that is most likely to obtain more customer information can be determined as the target executing institution. Therefore, the technical solution of this embodiment is beneficial to ensuring the accuracy of the screening task assignment.

[0147] If not, execute 570.

[0148] Step 570: Determine the target executing institution according to the relationship between the first executing institution and the account-opening institution, and the relationship between the first executing institution and the second executing institution.

[0149] Specifically, through the algorithm design of setting the assignment rules, it is easier to obtain the executing institution with more complete counterparty information and / or customer information. Optionally, the algorithm design for setting the assignment rules can be Figure 3 Steps 320 - 340 in the corresponding technical solution, or Figure 4 Steps 420 - 470 in the corresponding technical solution. Therefore, in this embodiment, first, it is determined whether the first executing institution can perform the screening task according to the completeness of the customer information of the first executing institution. When the completeness of the customer information of the first executing institution meets the requirements, it is determined that the first executing institution can perform the screening task, and the first executing institution is determined as the target executing institution. When the first executing institution cannot perform the task, the second executing institution or other executing institutions are determined as the target executing institutions.

[0150] Optionally, in step 570, determining the target executing institution according to the relationship between the first executing institution and the account-opening institution, and the relationship between the first executing institution and the second executing institution can be determining the target executing institution according to whether the first executing institution is the same as the account-opening institution, and whether the first executing institution is the same as the second executing institution.

[0151] Figure 6 It is the flowchart of another method for assigning suspicious transaction report screening tasks provided by an embodiment of the present invention. This embodiment is based onFigure 5 On the basis of the corresponding technical solution, with reference to Figure 6 , the method for allocating suspicious transaction report screening tasks includes:

[0152] Step 610: Obtain suspicious transaction data. This step is the same as step 510 in the above embodiment and will not be elaborated here.

[0153] Step 620: Based on the specific information of the suspicious transaction report to be screened, determine the first executing agency of the suspicious transaction report to be screened according to the set allocation rules; this step is the same as step 520 in the above embodiment and will not be elaborated here.

[0154] Step 630: Based on the historical suspicious transaction reports and the corresponding actual executing agencies, and the specific information of the suspicious transaction report to be screened, determine the second executing agency of the suspicious transaction report to be screened according to the machine learning model; this step is the same as step 530 in the above embodiment and will not be elaborated here.

[0155] Step 640: Use the first executing agency and the second executing agency corresponding to the suspicious transaction report to be screened as the result set of the executing agency corresponding to the suspicious transaction report to be screened; this step is the same as step 540 in the above embodiment and will not be elaborated here.

[0156] Step 650: Determine whether the first executing agency can perform the screening task according to the completeness of the customer information of the first executing agency; this step is the same as step 550 in the above embodiment and will not be elaborated here.

[0157] If so, execute step 660.

[0158] Step 660: Determine the first executing agency as the target executing agency; this step is the same as step 660 in the above embodiment and will not be elaborated here.

[0159] If not, execute step 670.

[0160] Step 670: Determine whether the first executing agency is the account-opening agency.

[0161] If so, execute step 681.

[0162] Step 681: Determine the first executing agency as the target executing agency.

[0163] Specifically, the account-opening agency can more easily obtain more customer information. Therefore, when the first executing agency is the account-opening agency, the first executing agency can be directly determined as the target executing agency.

[0164] If not, execute step 682.

[0165] Step 682: Determine whether the first executing agency and the second executing agency are the same agency;

[0166] If so, execute Step 691.

[0167] Step 691: Submit the screening task of the suspicious transaction report to be screened to the superior agency of the first executing agency.

[0168] Because when the first executing agency cannot execute the screening task of the suspicious transaction report to be screened, if the second executing agency is the same as the first executing agency, the second executing agency also cannot execute the screening task. At this time, the screening task of the suspicious transaction report to be screened is submitted to the superior agency of the first executing agency, and the superior agency of the first executing agency makes an allocation according to the actual situation.

[0169] If not, execute Step 691.

[0170] Step 692: Determine whether the customer information of the second executing agency is complete;

[0171] If so, execute Step 6921.

[0172] Step 6921: Determine the second executing agency as the target executing agency;

[0173] Specifically, the second executing agency is obtained based on a machine learning model. In the method of this embodiment, when the first executing agency obtained according to the set allocation rule cannot execute the screening task of the suspicious transaction report to be screened, the second executing agency obtained according to the machine learning model can be used as a substitute to ensure that the screening task can be quickly allocated, thereby improving the reliability of the method for allocating the screening task of the suspicious transaction report.

[0174] If not, execute Step 6922.

[0175] Step 6922: Submit the screening task of the suspicious transaction report to be screened to the superior agency of the second executing agency.

[0176] Among the above steps, Steps 682 - 6922 are the process of determining the target executing agency according to the relationship between the first executing agency and the second executing agency, and Steps 692 - 6922 are the process of determining the target executing agency according to the completeness of the customer information of the second executing agency.

[0177] The embodiment of the present invention also provides a device for allocating the screening task of the suspicious transaction report. Figure 7 It is a schematic structural diagram of a device for allocating the screening task of the suspicious transaction report provided by the embodiment of the present invention. This device for allocating the screening task of the suspicious transaction report can be used to execute the method for allocating the screening task of the suspicious transaction report in any of the above embodiments of the present invention. Refer to Figure 7 , this device for allocating the screening task of the suspicious transaction report includes:

[0178] An acquisition module 710, configured to acquire suspicious transaction data;

[0179] A result set determination module 720, configured to determine, based on the suspicious transaction data, the executing institutions of the suspicious transaction reports to be screened according to the set allocation rules and machine learning models respectively, and form a result set of the executing institutions corresponding to the suspicious transaction reports to be screened;

[0180] A target executing institution determination module 730, configured to determine the target executing institution corresponding to the suspicious transaction report to be screened according to the integrity of the customer information of the executing institutions in the result set of the executing institutions corresponding to the suspicious transaction report to be screened.

[0181] The suspicious transaction report screening task allocation device of this embodiment is used to execute the suspicious transaction report screening task allocation method of any of the above embodiments of the present invention, and thus has the same beneficial effects as the suspicious transaction report screening task allocation method, which will not be elaborated here.

[0182] Figure 8 It is a schematic structural diagram of a device provided by an embodiment of the present invention. Figure 8 It shows a block diagram of an exemplary device 412 suitable for implementing the embodiments of the present invention. Figure 8 The shown device 412 is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0183] As Figure 8 shown, the device 412 is presented in the form of a general-purpose device. The components of the device 412 may include but are not limited to: one or more processors 416, a storage device 428, and a bus 418 connecting different system components (including the storage device 428 and the processor 416).

[0184] The bus 418 represents one or more of several types of bus structures, including a storage device bus or a storage device controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the multiple bus structures. For example, these architectures include but are not limited to the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0185] Device 412 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by device 412, including volatile and non-volatile media, removable and non-removable media.

[0186] The storage device 428 can include computer system readable media in the form of volatile memory, such as random access memory (RAM) 431 and / or cache memory 432. Device 412 can further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 434 can be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 8 not shown and typically referred to as a "hard disk drive"). Although Figure 8 not shown in, a disk drive for reading and writing on removable non-volatile disks (such as a "floppy disk") and an optical disk drive for reading and writing on removable non-volatile optical disks, such as a compact disc read-only memory (CD-ROM), a digital video disc read-only memory (DVD-ROM) or other optical media) can be provided. In these cases, each drive can be connected to the bus 418 through one or more data media interfaces. The storage device 428 can include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0187] A program / utility 441 having a set (at least one) of program modules 442 can be stored, for example, in the storage device 428. Such program modules 442 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules 442 generally perform the functions and / or methods in the embodiments described in the present invention.

[0188] Device 412 can also communicate with one or more external devices 414 (such as keyboards, pointing terminals, display 424, etc.), and can also communicate with one or more terminals that enable users to interact with the device 412, and / or communicate with any terminal that enables the device 412 to communicate with one or more other computing terminals (such as network cards, modems, etc.). Such communication can be carried out through the input / output (I / O) interface 422. In addition, the device 412 can also communicate with one or more networks (such as a Local Area Network (LAN), a Wide Area Network (WAN), and / or a public network, such as the Internet) through the network adapter 421. As Figure 8 shown, the network adapter 421 communicates with other modules of the device 412 through the bus 418. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the device 412, including but not limited to: microcode, terminal drivers, redundant processors, external disk drive arrays, Redundant Arrays of Independent Disks (RAID) systems, tape drives, and data backup storage systems, etc.

[0189] The processor 416 executes various functional applications and data processing by running programs stored in the storage device 428. For example, it implements the suspicious transaction report screening task allocation method provided by the embodiments of the present invention. The method includes:

[0190] Obtain suspicious transaction data;

[0191] Based on the suspicious transaction data, respectively determine the execution agencies of the suspicious transaction reports to be screened according to the set allocation rules and machine learning models, and form a result set of execution agencies corresponding to the suspicious transaction reports to be screened;

[0192] According to the integrity of the customer information of the execution agencies in the result set of execution agencies corresponding to the suspicious transaction reports to be screened, determine the target execution agency corresponding to the suspicious transaction reports to be screened.

[0193] The embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the suspicious transaction report screening task allocation method provided by the embodiments of the present invention. The method includes:

[0194] Obtain suspicious transaction data;

[0195] Based on the suspicious transaction data, respectively determine the execution agencies of the suspicious transaction reports to be screened according to the set allocation rules and machine learning models, and form a result set of execution agencies corresponding to the suspicious transaction reports to be screened;

[0196] Determine the target executing institution corresponding to the suspicious transaction report to be screened according to the integrity of the executing institution customer information in the result set of the executing institution corresponding to the suspicious transaction report to be screened.

[0197] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable media may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, 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), an optical fiber, 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 this document, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0198] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0199] The program code contained on the computer-readable medium may be transmitted by any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0200] Computer program code for performing the operations of the present invention may be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0201] An embodiment of the present invention also provides a computer program product, which includes computer-executable instructions that, when executed by a computer processor, are used to perform the suspicious transaction report screening task allocation method in the above method embodiments.

[0202] Of course, for a computer program product provided by an embodiment of the present application, the computer-executable instructions are not limited to the method operations described above, and may also perform related operations in the methods provided by any embodiment of the present application.

[0203] Note that the above is only a preferred embodiment of the present invention and the applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and without departing from the concept of the present invention, more other equivalent embodiments may be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for allocating suspicious transaction report screening tasks, characterized in that, Including: Obtaining suspicious transaction data; Based on the suspicious transaction data, respectively determining the executing institutions of the suspicious transaction reports to be screened according to the set allocation rules and machine learning models, and forming a result set of the executing institutions corresponding to the suspicious transaction reports to be screened; Determining the target executing institution corresponding to the suspicious transaction report to be screened according to the integrity of the customer information of the executing institutions in the result set of the executing institutions corresponding to the suspicious transaction report to be screened; Wherein, the suspicious transaction data includes historical suspicious transaction data and suspicious transaction reports to be screened, and the historical suspicious transaction data includes historical suspicious transaction reports and corresponding actual executing institutions; Wherein, based on the suspicious transaction data, respectively determining the executing institutions of the suspicious transaction reports to be screened according to the set allocation rules and machine learning models to form a result set of the executing institutions corresponding to the suspicious transaction reports to be screened, including: Based on the specific information of the suspicious transaction report to be screened, determining the first executing institution of the suspicious transaction report to be screened according to the set allocation rules; Based on the historical suspicious transaction reports and corresponding actual executing institutions, and the specific information of the suspicious transaction report to be screened, determining the second executing institution of the suspicious transaction report to be screened according to the machine learning model; Taking the first executing institution and the second executing institution corresponding to the suspicious transaction report to be screened as the result set of the executing institutions corresponding to the suspicious transaction report to be screened; Wherein, determining the first executing institution of the suspicious transaction report to be screened according to the set allocation rules based on the specific information of the suspicious transaction report to be screened includes: Based on the specific information of the suspicious transaction report to be screened, judging whether there is a place where the suspicious transaction occurs for multiple suspicious transactions corresponding to the suspicious transaction report to be screened; If so, determining the first executing institution of the suspicious transaction report to be screened as the executing institution at the place where the suspicious transaction occurs; If not, determining the first executing institution of the suspicious transaction report to be screened as the executing institution at the place where the regular transaction occurs or the account-opening institution.

2. The method for allocating suspicious transaction report screening tasks according to claim 1, wherein The specific information of the suspicious transaction report to be screened includes multiple suspicious transactions and the administrative division code of the corresponding other financial institution network points for each suspicious transaction; Judging whether there is a place where the suspicious transaction occurs for multiple suspicious transactions corresponding to the suspicious transaction report to be screened based on the specific information of the suspicious transaction report to be screened includes: Judging whether there is a place where the suspicious transaction occurs for multiple transactions corresponding to the suspicious transaction report to be screened according to the total amount of all suspicious transactions in the suspicious transaction report to be screened and the total amount of suspicious transactions corresponding to the same administrative division code of the other financial institution network points; or Judging whether there is a place where the suspicious transaction occurs for multiple suspicious transactions corresponding to the suspicious transaction report to be screened according to the total number of transaction pens of all suspicious transactions in the suspicious transaction report to be screened and the number of suspicious transaction pens corresponding to the same administrative division code of the other financial institution network points.

3. The method for allocating the suspicious transaction report screening task according to claim 1, wherein Determining that the first executing institution for screening the suspicious transaction report to be screened is the executing institution where the regular transaction occurs or the account-opening institution includes: Based on the specific information of the suspicious transaction report to be screened, determine whether there is a frequent transaction place for the multiple transactions corresponding to the suspicious transaction report to be screened; If so, determine the first implementing agency of the suspicious transaction report to be screened as the implementing agency at the frequent transaction place; If not, determine the first implementing agency of the suspicious transaction report to be screened as the opening agency.

4. The method for allocating suspicious transaction report screening tasks according to claim 3, wherein The specific information of the suspicious transaction report to be screened includes multiple transactions and the financial institution outlet code corresponding to each transaction; Based on the specific information of the suspicious transaction report to be screened, determining whether there is a frequent transaction place for the transactions corresponding to the suspicious transaction report to be screened includes: Judging whether there is a frequent transaction place for the multiple transactions corresponding to the suspicious transaction report to be screened according to the total amount of the transactions of the set transaction type in the suspicious transaction report to be screened and the total amount of the transactions of the set transaction type corresponding to the same financial institution outlet code; or, Judging whether there is a frequent transaction place for the multiple transactions corresponding to the suspicious transaction report to be screened according to the number of transactions of the set transaction type in the suspicious transaction report to be screened and the number of transactions of the set transaction type corresponding to the same pair of financial institution outlet codes; Among them, the transactions of the set transaction type are transactions other than exempted transactions.

5. The method for allocating suspicious transaction report screening tasks according to claim 1, wherein Based on the historical suspicious transaction report and the corresponding actual implementing agency, and the specific information of the suspicious transaction report to be screened, determining the second implementing agency of the suspicious transaction report to be screened according to the machine learning model includes: Taking the historical suspicious transaction report as the input of the machine learning model, and taking the actual implementing agency corresponding to the historical suspicious transaction report as the output of the machine learning model to train the machine learning model, and obtaining a trained machine learning model; Inputting each suspicious transaction report to be screened into the trained machine learning model to determine the second implementing agency of the suspicious transaction report to be screened.

6. The suspicious transaction report screening task allocation method according to claim 5, wherein The machine learning model is a discriminant model.

7. The method for allocating the suspicious transaction report screening task according to any one of claims 1-6, characterized in that, Determining the target implementing agency corresponding to the suspicious transaction report to be screened according to the completeness of the customer information of each implementing agency in the implementing agency result set corresponding to the suspicious transaction report to be screened includes: Determining whether the first implementing agency can perform the screening task according to the completeness of the customer information of the first implementing agency; If so, determining the first implementing agency as the target implementing agency; If not, determining the target implementing agency according to the relationship between the first implementing agency and the opening agency and the relationship between the first implementing agency and the second implementing agency.

8. The method for allocating the suspicious transaction report screening task according to claim 7, wherein, Determining the target implementing agency according to the relationship between the first implementing agency and the opening agency and the relationship between the first implementing agency and the second implementing agency includes: Judging whether the first implementing agency is the opening agency; If so, determining the first implementing agency as the target implementing agency; If not, determining the target implementing agency according to the relationship between the first implementing agency and the second implementing agency.

9. The method for allocating the suspicious transaction report screening task according to claim 8, wherein Determining the target implementing agency according to the relationship between the first implementing agency and the second implementing agency includes: Determine whether the first executing agency and the second executing agency are the same agency; If so, submit the screening task of the suspicious transaction report to be screened to the superior agency of the first executing agency; If not, determine the target executing agency according to the integrity of the customer information of the second executing agency.

10. The method for allocating the suspicious transaction report screening task according to claim 9, wherein The determining the target executing agency according to the integrity of the customer information of the second executing agency includes: Determine whether the customer information of the second executing agency is complete; If so, determine the second executing agency as the target executing agency; If not, submit the screening task of the suspicious transaction report to be screened to the superior agency of the second executing agency.

11. A suspicious transaction report screening task allocation device, characterized in that, including: An acquisition module for acquiring suspicious transaction data; wherein, the suspicious transaction data includes historical suspicious transaction data and suspicious transaction reports to be screened, and the historical suspicious transaction data includes historical suspicious transaction reports and corresponding actual executing agencies; A result set determination module for respectively determining the executing agency corresponding to the suspicious transaction report to be screened based on the suspicious transaction data according to the set allocation rules and the machine learning model, and forming an executing agency result set of the suspicious transaction report to be screened; A target executing agency determination module for determining the target executing agency corresponding to the suspicious transaction report to be screened according to the integrity of the customer information of the executing agency in the executing agency result set corresponding to the suspicious transaction report to be screened; Wherein, the result set determination module is specifically configured to determine the first executing agency of the suspicious transaction report to be screened according to the set allocation rules based on the specific information of the suspicious transaction report to be screened; based on the historical suspicious transaction report and the corresponding actual executing agency, and the specific information of the suspicious transaction report to be screened, determine the second executing agency of the suspicious transaction report to be screened according to the machine learning model; and use the first executing agency and the second executing agency corresponding to the suspicious transaction report to be screened as the executing agency result set corresponding to the suspicious transaction report to be screened; Wherein, the determining the first executing agency of the suspicious transaction report to be screened according to the set allocation rules based on the specific information of the suspicious transaction report to be screened includes: based on the specific information of the suspicious transaction report to be screened, determine whether there is a place where the suspicious transaction occurs in multiple suspicious transactions corresponding to the suspicious transaction report to be screened; if so, determine the first executing agency of the suspicious transaction report to be screened as the executing agency at the place where the suspicious transaction occurs; if not, determine the first executing agency of the suspicious transaction report to be screened as the executing agency at the place where the frequent transaction occurs or the account opening agency.

12. An apparatus, characterized in that, The device includes: 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 implement the method as described in any one of claims 1-10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-10.

14. A computer program product comprising computer-executable instructions that, when executed, are configured to implement the method according to any one of claims 1-10.

Images