Transaction data processing method, device, equipment, medium and program product

Abstract

The invention provides a transaction data processing method which can be applied to the technical field of big data. The transaction data processing method comprises the following steps: extracting a target risk feature corresponding to a to-be-transacted object; based on the target risk feature, reading a plurality of reference transaction information parameters matched with the target risk feature from a pre-constructed total transaction information parameter table; exporting multiple groups of to-be-processed transaction data from the transaction data storage platform; calculating a change amplitude value of each piece of to-be-processed transaction data in a predetermined sliding time window to obtain a plurality of historical change amplitude values; performing data association processing on the plurality of historical change amplitude values and a preset quantile to generate a reference transaction information parameter value; and generating a transaction data processing result corresponding to the to-be-transacted object based on the reference transaction information parameter value. The invention further provides a transaction data processing device and equipment, a medium and a program product.

Description

Technical Field

[0001] The present disclosure relates to the field of big data technology, and more specifically to a transaction data processing method, device, equipment, medium and program product. Background Art

[0002] For various financial products, it is usually necessary to analyze their transaction information. For example, in order to ensure the safety of business, the transaction risks of financial products in different market environments can be analyzed. Related technologies usually analyze the transaction risks of financial products in different market environments based on different parameters.

[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 art. In the related art, on the one hand, parameter values ​​are mostly fixed values ​​set manually, and the changing patterns of transaction data are not taken into consideration, resulting in low reference value of parameter values ​​and low accuracy of transaction information analysis results; on the other hand, in the related art, the required parameters are usually queried directly from the source databases of multiple data providers, and the data types between different database systems may not be fully compatible; in addition, the database structure is relatively complex, which may lead to data redundancy, which is not conducive to maintaining data integrity and consistency, and the data retrieval efficiency is low. Summary of the invention

[0004] In view of the above problems, the present disclosure provides a transaction data processing method, apparatus, device, medium and program product.

[0005] According to a first aspect of the present disclosure, a transaction data processing method is provided, including: extracting a target risk feature corresponding to an object to be traded; based on the target risk feature, reading a plurality of reference transaction information parameters matching the target risk feature from a pre-constructed full transaction information parameter table, wherein the reference transaction information parameters are obtained by performing data conversion processing on the original transaction information parameters; exporting a plurality of groups of transaction data to be processed within a predetermined historical time interval, which correspond one-to-one to the plurality of reference transaction information parameters, from a transaction data storage platform; for each group of transaction data to be processed, calculating a change amplitude value of each transaction data to be processed within a predetermined sliding time window, and obtaining a plurality of historical change amplitude values; performing data association processing on the plurality of historical change amplitude values ​​and preset percentile values, and generating reference transaction information parameter values; and generating a transaction data processing result corresponding to the object to be traded based on the reference transaction information parameter values.

[0006] According to an embodiment of the present disclosure, the above-mentioned transaction data processing method also includes: in response to a data reading instruction, reading multiple sets of original transaction information parameters from multiple source databases; calling a data conversion component to perform data conversion processing on the multiple sets of original transaction information parameters to obtain multiple sets of standard transaction information parameters; based on the multiple sets of standard transaction information parameters, generating a full transaction information parameter table.

[0007] According to an embodiment of the present disclosure, multiple groups of standard transaction information parameters are stored in a multi-level tree-like risk structure, and the multi-level tree-like risk structure includes a root node and child nodes, wherein the root node stores transaction risk category data, and the child nodes store transaction risk subcategory data; based on the multiple groups of standard transaction information parameters, generating a full transaction information parameter table includes: for each group of standard transaction information parameters, classifying and processing the standard transaction information parameters based on multiple predetermined risk categories to obtain an initial classification result, wherein the initial classification result includes multiple initial parameter sets corresponding one-to-one to the multiple predetermined risk categories; for each initial parameter set, classifying and processing the initial parameter set based on the predetermined risk subcategories to obtain a target classification result, wherein the target classification result includes multiple target parameter sets corresponding one-to-one to the multiple predetermined risk subcategories; mapping the target classification result to the multi-level tree-like risk structure to obtain a mapping result; based on the mapping result, generating a full transaction information parameter table.

[0008] According to an embodiment of the present disclosure, calling a data conversion component to perform data conversion processing on multiple sets of original transaction information parameters includes: identifying the original data formats corresponding to the multiple sets of original transaction information parameters; determining the target data format associated with the original data format from a pre-built format conversion reference table; based on the target data format, calling the data conversion component to perform format conversion processing on the multiple sets of original transaction information parameters to obtain multiple sets of standard transaction information parameters, wherein the multiple sets of standard transaction information parameters include reference transaction information parameters.

[0009] According to an embodiment of the present disclosure, data association processing is performed on multiple historical change amplitude values ​​and preset percentile values ​​to generate a reference transaction information parameter value, including: sorting the multiple historical change amplitude values ​​to obtain a sorting result; filtering out a target historical change amplitude value corresponding to the preset percentile value from the sorting result; and when the target historical change amplitude value is an integer, using the target historical change amplitude value as the reference transaction information parameter value.

[0010] According to an embodiment of the present disclosure, data association processing is performed on multiple historical change amplitude values ​​and preset percentile values ​​to generate a reference transaction information parameter value, which also includes: when the target historical change amplitude value is a non-integer, linear interpolation processing is performed on the target historical change amplitude value to obtain the reference transaction information parameter value.

[0011] The second aspect of the present disclosure provides a transaction data processing device, including: an extraction module, which is used to extract target risk characteristics corresponding to the object to be traded; a first reading module, which is used to read multiple reference transaction information parameters matching the target risk characteristics from a pre-constructed full transaction information parameter table based on the target risk characteristics, wherein the reference transaction information parameters are obtained by performing data conversion processing on the original transaction information parameters; an export module, which is used to export multiple groups of transaction data to be processed within a predetermined historical time interval, which correspond one-to-one to multiple reference transaction information parameters, from a transaction data storage platform; a calculation module, which is used to calculate the change amplitude value of each transaction data to be processed within a predetermined sliding time window for each group of transaction data to be processed, and obtain multiple historical change amplitude values; a data association module, which is used to perform data association processing on multiple historical change amplitude values ​​and preset percentile values ​​to generate reference transaction information parameter values; a first generation module, which is used to generate a transaction data processing result corresponding to the object to be traded based on the reference transaction information parameter values.

[0012] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0013] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.

[0014] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor.

[0015] According to the embodiments of the present disclosure, by reading multiple reference transaction information parameters that match the target risk characteristics from the pre-built full transaction information parameter table, the risk prediction scenario corresponding to the risk prediction parameter can be accurately determined, thereby improving the accuracy of the transaction data processing results and improving the data query efficiency; the reference transaction information parameter is obtained by data conversion processing of the original transaction information parameter, which can reduce the data table association operation of the subsequent calculation, improve the calculation efficiency, and avoid the problem of incompatibility of the original transaction information parameter, ensure the integrity and consistency of the data, and at the same time avoid the problem of database storage resource waste caused by data redundancy; by performing data association processing based on the historical change amplitude value and the preset quantile value to generate the reference transaction information parameter value, the historical change law of the transaction data to be processed can be fully explored, so that the reference transaction information parameter value is more referenceable. Therefore, at least partially solves the problem of low reference value of the risk prediction parameter, low accuracy of the transaction data processing result, data incompatibility and data redundancy caused by different data formats of the risk prediction parameter, and thus achieves the technical effect of improving the accuracy of the transaction data processing result, ensuring the integrity and consistency of the data, reducing the data table association operation of the subsequent calculation, and improving the calculation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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:

[0017] Figure 1 A diagram schematically illustrates an application scenario of a transaction data processing method, apparatus, device, medium, and program product according to an embodiment of the present disclosure;

[0018] Figure 2 A flowchart of a transaction data processing method according to an embodiment of the present disclosure is schematically shown;

[0019] Figure 3 A system structure diagram schematically shows a transaction data processing method according to an embodiment of the present disclosure;

[0020] Figure 4 A schematic diagram schematically shows a multi-level tree-like risk structure according to an embodiment of the present disclosure;

[0021] Figure 5 A block diagram schematically shows a structure of a transaction data processing device according to an embodiment of the present disclosure; and

[0022] Figure 6 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

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.).

[0027] It should be noted that the transaction data processing method and device disclosed herein can be used in the field of big data technology, and can also be used in any field other than the field of big data technology. The application field of the transaction data processing method and device disclosed herein is not limited.

[0028] It should be noted that in the embodiments of the present disclosure, certain software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present disclosure, but it does not mean that the applicant has or will necessarily use the solution.

[0029] 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 relevant laws, regulations and standards, 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.

[0030] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0031] In order to ensure the safety of business, it is usually necessary to analyze the transaction risks of financial products. For example, the way to analyze the transaction risks of financial products can be to perform stress testing on financial products. Through stress testing, the ability of financial products to cope with risk shocks in an unfavorable market environment can be predicted. By processing transaction data based on different parameter values, the transaction risks of financial products in different market environments can be analyzed. 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 art: (1) The values ​​of relevant parameters are mostly set manually based on experience, and the setting process does not take into account the changing rules of transaction data, resulting in low reference value of parameter values ​​and low accuracy of transaction data processing results. (2) In the related art, the required parameters are usually read directly from the source databases of multiple data providers, and the data types between different database systems may not be fully compatible. (3) After reading the required parameters, the structure of the database used to store the above parameters is relatively complex, which may lead to data redundancy, which is not conducive to maintaining data integrity and consistency, and leads to low data retrieval efficiency.

[0032] In view of this, an embodiment of the present disclosure provides a transaction data processing method, including: extracting a target risk feature corresponding to an object to be traded; based on the target risk feature, reading a plurality of reference transaction information parameters matching the target risk feature from a pre-constructed full transaction information parameter table, wherein the reference transaction information parameters are obtained by performing data conversion processing on the original transaction information parameters; exporting a plurality of groups of transaction data to be processed within a predetermined historical time interval, which correspond one-to-one to a plurality of reference transaction information parameters, from a transaction data storage platform; for each group of transaction data to be processed, calculating a change amplitude value of each transaction data to be processed within a predetermined sliding time window, and obtaining a plurality of historical change amplitude values; performing data association processing on the plurality of historical change amplitude values ​​and preset percentile values, and generating reference transaction information parameter values; based on the reference transaction information parameter values, generating a transaction data processing result corresponding to the object to be traded.

[0033] Figure 1 The application scenario diagram of the transaction data processing method, apparatus, device, medium and program product according to the embodiments of the present disclosure is schematically shown.

[0034] 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 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0035] The user can use 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 can 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 for example).

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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 the implementation requirements.

[0040] The following will be based on Figure 1 The scene described by Figure 2~Figure 4 The transaction data processing method of the disclosed embodiment is described in detail.

[0041] Figure 2 The flowchart of the transaction data processing method according to the embodiment of the present disclosure is schematically shown.

[0042] like Figure 2 As shown, the transaction data processing method of this embodiment includes operations S210 to S260.

[0043] In operation S210, target risk features corresponding to the transaction object are extracted.

[0044] In operation S220, based on the target risk characteristics, a plurality of reference transaction information parameters matching the target risk characteristics are read from a pre-constructed full transaction information parameter table, wherein the reference transaction information parameters are obtained by performing data conversion processing on the original transaction information parameters.

[0045] In operation S230, multiple groups of to-be-processed transaction data corresponding one-to-one to multiple reference transaction information parameters within a predetermined historical time interval are exported from the transaction data storage platform.

[0046] In operation S240, for each group of transaction data to be processed, a change amplitude value of each transaction data to be processed within a predetermined sliding time window is calculated to obtain a plurality of historical change amplitude values.

[0047] In operation S250, data association processing is performed on a plurality of historical change amplitude values ​​and preset percentile values ​​to generate a reference transaction information parameter value.

[0048] In operation S260, a transaction data processing result corresponding to the transaction object is generated based on the reference transaction information parameter value.

[0049] According to an embodiment of the present disclosure, in operation S210, the object to be traded may be a financial product whose transaction information needs to be analyzed, for example, a financial product whose transaction risk needs to be analyzed. For example, the object to be traded may be a financial product of a financial institution. The target risk characteristic may be, for example, the type of the object to be traded, for example, it may include debt-type objects to be traded, stock-type objects to be traded, fund-type objects to be traded, etc. Specifically, the underlying assets corresponding to the object to be traded may be obtained to accurately determine the type of the object to be traded.

[0050] According to an embodiment of the present disclosure, in operation S220, different types of transaction objects may correspond to different transaction information analysis scenarios, and accordingly, the corresponding transaction information parameters for transaction information analysis may also be different, for example, the transaction risk categories to which the parameters belong may be different. For example: in the case of analyzing the transaction risks of financial products under different market environments, when analyzing the transaction risks of stock-type transaction objects, it is usually necessary to consider the impact of market risks such as exchange rate risk, derivative transaction risk, and interest rate risk, so it is necessary to match transaction information parameters of the market risk category. When analyzing the transaction risks of non-standard debt-type transaction objects such as credit assets, it is usually necessary to consider the impact of credit risks such as the credit status of the creditor, so it is necessary to match transaction information parameters of the credit risk category. The full transaction information parameter table stores standard transaction information parameters of uniform data types, and stores the transaction risk categories to which the standard transaction information parameters belong, and the transaction risk categories include, for example, credit risk categories, market risk categories, etc. Standard transaction information parameters matching the target risk characteristics can be read from the full transaction information parameter table to obtain reference transaction information parameters. For example, the target transaction risk category matching the target risk characteristics can be determined, and the standard transaction information parameters corresponding to the target transaction risk category can be read from the full transaction information parameter table, and the above standard transaction information parameters corresponding to the target transaction risk category can be used as reference transaction information parameters.

[0051] When analyzing the transaction risk of the transaction object, by reading multiple reference transaction information parameters that match the target risk characteristics from the pre-built full transaction information parameter table, rather than manually configuring the required parameters based on experience, the transaction information analysis scenario corresponding to the reference transaction information parameters can be accurately determined, thereby improving the accuracy of the transaction data processing results. In addition, directly querying the reference transaction information parameters from the pre-built full transaction information parameter table can improve data query efficiency.

[0052] According to the embodiments of the present disclosure, the transaction information of the transaction object can be analyzed through the risk trading platform of the financial institution. Before analyzing the transaction information, the original transaction information parameters can be directly read from the source database of the data provider, or the original transaction data can be read from the source database of the data provider, and then the transaction data characteristics of the above original transaction data are identified to obtain the original transaction information parameters. Among them, the above original transaction data can include, for example, position information, product fundraising information, valuation information, and asset performance information (for example, it can include stock indexes, bond yields, futures main indexes, fund income indexes, etc.), and can also include the investment proportion and market value information of overseas investment portfolios in different countries and regions.

[0053] The data provider may be, for example, a third-party data provider other than the financial institution that needs to perform transaction information analysis. Different data providers may provide different original transaction information parameters, or they may provide the same original transaction information parameters. Different data providers may also provide different original transaction data, or the same original transaction data, and then identify the transaction data features of the original transaction data to obtain the original transaction information parameters.

[0054] Furthermore, the data types corresponding to the source databases of different data providers may be different, which will increase the data table association operations in subsequent calculations. In addition, since the data types corresponding to the source databases of different data providers may not be completely compatible, if the original transaction information parameters are directly stored in the target database of the financial institution, the integrity and consistency of the data may not be guaranteed. In addition, since the same original transaction information parameters may be read from the source databases of different data providers, data redundancy may occur.

[0055] Therefore, the original transaction information parameters can be processed for data conversion to unify the data types of the original transaction information parameters, obtain standard transaction information parameters, and then store the standard transaction information parameters in the full transaction information parameter table, and store the full transaction information parameter table in the target database. Therefore, when performing risk prediction in the future, the standard transaction information parameters with unified data types can be directly calculated and analyzed, thereby reducing the data table association operations of subsequent calculations and improving calculation efficiency; on the other hand, through data conversion processing, the same original transaction information parameters can be avoided from being stored multiple times in the target database, thereby avoiding problems such as waste of database storage resources caused by data redundancy. In addition, after converting the original transaction information parameters into standard transaction information parameters with unified data types, the standard transaction information parameters are stored in the target database, which can avoid the problem of incompatibility of the original transaction information parameters and ensure the integrity and consistency of the data.

[0056] According to the embodiments of the present disclosure, different types of objects to be traded may correspond to the same standard transaction information parameters, or may correspond to different standard transaction information parameters, namely, characteristic standard transaction information parameters. For objects to be traded, the characteristic standard transaction information parameters corresponding to the objects to be traded may be stored in the form of a wide table, thereby improving data query efficiency through data redundancy.

[0057] According to an embodiment of the present disclosure, in operation S230, in order to accurately determine the reference transaction information parameter value, multiple groups of pending transaction data within a predetermined historical time interval and corresponding to multiple reference transaction information parameters respectively may be obtained, and the reference transaction information parameter value may be determined based on the historical change pattern of the pending transaction data. Specifically, the historical start date and the historical end date may be determined, and the predetermined historical interval may be determined based on the historical start date and the historical end date. Multiple pending transaction data may be stored in the transaction data storage platform, and multiple groups of pending transaction data within a predetermined historical time interval and corresponding to multiple reference transaction information parameters respectively may be exported from the transaction data storage platform.

[0058] For example, the history start date may be January 1, 20XX, and the history end date may be March 31, 20XX, then the predetermined history interval may be January 1, 20XX to March 31, 20XX. The reference transaction information parameter may include, for example, an exchange rate depreciation parameter. The pending transaction data corresponding to the exchange rate depreciation parameter with a generation time between January 1, 20XX and March 31, 20XX may be exported from the transaction data storage platform, for example, a certain exchange rate value on January 1, 20XX and a certain exchange rate value on January 1, 20XX may be exported.

[0059] According to an embodiment of the present disclosure, in operation S240, the calculation of the change amplitude value of each pending transaction data within a predetermined sliding time window can be: based on the predetermined sliding time window, determine the increase or decrease of the pending transaction data to be processed, and obtain the historical change amplitude value. For example: the predetermined sliding time window is 90 days. For a pending transaction data generated on January 1, 20XX, its increase or decrease compared with 90 days ago can be calculated; for a pending transaction data generated on January 2, 20XX, its increase or decrease compared with 90 days ago can be calculated; for a pending transaction data generated on March 31, 20XX, its increase or decrease compared with 90 days ago can be calculated... By calculating the change amplitude value of each pending transaction data within the predetermined sliding time window, multiple historical change amplitude values ​​can be obtained.

[0060] According to an embodiment of the present disclosure, in operation S250, a historical change amplitude value corresponding to a preset percentile value may be determined from a plurality of historical change amplitude values ​​to obtain a reference transaction information parameter value.

[0061] According to an embodiment of the present disclosure, in operation S260, the transaction data processing result can be used to characterize the transaction risk corresponding to the object to be traded. Based on the reference transaction information parameter value, generating the transaction data processing result corresponding to the object to be traded can be: determining the transaction information analysis scenario based on the reference transaction information parameter value, and determining the transaction data processing result of the object to be traded under the transaction information analysis scenario, wherein the transaction data processing result can be the return value of the object to be traded under the risk prediction scenario.

[0062] According to an embodiment of the present disclosure, by reading multiple reference transaction information parameters that match the target risk characteristics from a pre-constructed full transaction information parameter table, the transaction information analysis scenario corresponding to the reference transaction information parameters can be accurately determined, thereby improving the accuracy of the transaction data processing results and improving the data query efficiency; since the reference transaction information parameters are obtained by data conversion processing of the original transaction information parameters, the data table association operations of subsequent calculations can be reduced, the calculation efficiency can be improved, and the problem of incompatibility of the original transaction information parameters can be avoided, the integrity and consistency of the data can be ensured, and the problem of waste of database storage resources caused by data redundancy can be avoided; by calculating the change amplitude value of the transaction data to be processed within a predetermined sliding time window, and performing data association processing based on the historical change amplitude value and the preset percentile value to generate the reference transaction information parameter value, the historical change law of the transaction data to be processed can be fully explored, so that the reference transaction information parameter value is more referenceable, thereby improving the accuracy of the transaction data processing results.

[0063] According to an embodiment of the present disclosure, the above-mentioned transaction data processing method also includes: in response to a data reading instruction, reading multiple sets of original transaction information parameters from multiple source databases; calling a data conversion component to perform data conversion processing on the multiple sets of original transaction information parameters to obtain multiple sets of standard transaction information parameters; based on the multiple sets of standard transaction information parameters, generating a full transaction information parameter table.

[0064] According to an embodiment of the present disclosure, it is possible to interact with database management systems of different data providers through a database interface to read original transaction information parameters or original transaction data. A data conversion component can be called to perform data conversion processing on multiple groups of original transaction information parameters to unify the data types of the original transaction information parameters and obtain multiple groups of standard transaction information parameters. Multiple groups of standard transaction information parameters can be classified, and a full transaction information parameter table can be generated based on the classification results.

[0065] Figure 3 The system structure diagram of the transaction data processing method according to the embodiment of the present disclosure is schematically shown.

[0066] like Figure 3 As shown, the source database may be a database of a data provider. The same or different original transaction information parameters may be read from different source databases. Since the data types corresponding to different source databases may be different, the original transaction information parameters may be converted based on the data conversion component to obtain standard transaction information parameters. The standard transaction information parameters may be stored in a full transaction information parameter table, and the full transaction information parameter table may be stored in a target database. When determining the reference transaction information parameter value, multiple reference transaction information parameters matching the target risk characteristics may be read from the target database, and the transaction data to be processed may be exported from the transaction data storage platform to determine the reference transaction information parameter value.

[0067] According to an embodiment of the present disclosure, after determining the reference transaction information parameter value, the transaction information platform may generate a transaction data processing result based on the reference transaction information parameter value.

[0068] According to the embodiments of the present disclosure, through the information instruction interaction between multiple systems such as the source database, the target database, the transaction data storage platform, and the transaction data processing system, each link of the risk prediction can be distributed to multiple different application systems for orderly execution, thereby realizing the computer's automatic execution of the transaction data processing process, and the risk prediction process can also be processed synchronously and in parallel by multiple computers, thereby reducing the pressure of data processing in the main system, saving overall computing time, and improving computer efficiency. In addition, through the interaction between multiple systems such as the source database, the target database transaction data storage platform, and the transaction information analysis platform, the flexibility of the transaction data processing system layout can be improved, making it easier to install and deploy.

[0069] According to an embodiment of the present disclosure, specifically, generating a full transaction information parameter table based on multiple groups of standard transaction information parameters includes operations 11 to 14.

[0070] In operation 11, for each group of standard transaction information parameters, the standard transaction information parameters are classified based on multiple predetermined risk categories to obtain an initial classification result, wherein the initial classification result includes multiple initial parameter sets corresponding to the multiple predetermined risk categories.

[0071] In operation 12, for each initial parameter set, the initial parameter set is classified based on the predetermined risk subcategories to obtain a target classification result, wherein the target classification result includes a plurality of target parameter sets corresponding one-to-one to a plurality of predetermined risk subcategories.

[0072] In operation 13, the target classification result is mapped to a multi-level tree-like risk structure to obtain a mapping result.

[0073] In operation 14, based on the mapping results, a full transaction information parameter table is generated.

[0074] According to an embodiment of the present disclosure, multiple sets of standard transaction information parameters can be stored in a multi-level tree risk structure in the full transaction information parameter table. The multi-level tree risk structure includes a root node and child nodes, the root node stores transaction risk category data, and the child node stores transaction risk subcategory data.

[0075] According to an embodiment of the present disclosure, in the above-mentioned multi-level tree-like risk structure, the subnodes include first-level subnodes and second-level subnodes. The root node includes at least one first-level subnode, and each first-level subnode includes at least one second-level subnode. The transaction risk subcategory data includes first-level transaction risk subcategory data and second-level transaction risk subcategory data. The first-level subnode stores the first-level transaction risk subcategory data, and the second-level subnode stores the second-level transaction risk subcategory data.

[0076] Specifically, the primary transaction risk sub-category data includes, for example, market risk, credit risk, operational risk, etc. Each primary transaction risk category may correspond to multiple secondary transaction risk sub-category data. For example, market risk may include multiple secondary market risk sub-categories, and secondary market risk sub-categories may include, for example, interest rate risk, exchange rate risk, derivative risk, etc.; credit risk may include multiple secondary credit risk sub-categories, and secondary credit risk sub-categories may include, for example, industry risk, individual risk, etc.

[0077] Figure 4 The diagram schematically shows a multi-level tree-like risk structure according to an embodiment of the present disclosure.

[0078] like Figure 4As shown, the first-level sub-node stores the first-level transaction risk sub-category data, which may include market risk data and credit risk data; the first-level sub-node may correspond to multiple second-level sub-nodes, which may store the second-level transaction risk sub-category data, such as interest rate risk data, exchange rate risk data, derivative risk data, etc.

[0079] According to an embodiment of the present disclosure, in operation 11, the predetermined risk category may include: market risk category, credit risk category, and operational risk category. The standard transaction information parameters are classified based on multiple predetermined risk categories to determine the risk category to which the standard transaction information parameters belong. The initial parameter set includes, for example: a market risk parameter set, a credit risk parameter set, and an operational risk parameter set.

[0080] According to an embodiment of the present disclosure, in operation 12, each predetermined risk category includes at least one predetermined risk subcategory. In the case where the predetermined risk category is a market risk category, the predetermined risk subcategory includes an interest rate risk category, an exchange rate risk category, a derivative risk category, etc. In the case where the predetermined risk category is a credit risk category, the predetermined risk subcategory includes an individual risk category, an industry risk category, etc. By classifying and processing each initial parameter set based on the predetermined risk subcategory, it is possible to further confirm the risk subcategory to which the standard transaction information parameter belongs, thereby finely dividing the standard transaction information parameter. The target parameter set includes an interest rate risk parameter set, an exchange rate risk parameter set, a derivative risk parameter set, an individual risk parameter set, an industry risk parameter set, etc.

[0081] According to an embodiment of the present disclosure, in operations 14-15, after determining each target parameter set, the standard transaction information parameters in the target parameter set can be mapped to the corresponding nodes of the multi-level tree risk structure to obtain a mapping result, and based on the mapping result, a full transaction information parameter table is generated. An example of the full transaction information parameter table is shown in Table 1 below.

[0082] Table 1

[0083]

[0084] According to the embodiments of the present disclosure, storing standard transaction information parameters in a multi-level tree-like risk structure can improve data storage efficiency, reduce system complexity, and help ensure data consistency and accuracy. In addition, the hierarchical structure of the multi-level tree-like risk structure can be dynamically adjusted according to actual risk prediction needs, as well as the data stored in the child nodes, to achieve dynamic scalability of data storage, increase the scope of application, and reduce development costs.

[0085] According to an embodiment of the present disclosure, specifically, calling a data conversion component to perform data conversion processing on multiple groups of original transaction information parameters includes: identifying the original data format corresponding to the multiple groups of original transaction information parameters; determining the target data format associated with the original data format from a pre-built format conversion reference table; based on the target data format, calling the data conversion component to perform format conversion processing on the multiple groups of original transaction information parameters to obtain multiple groups of standard transaction information parameters, wherein the multiple groups of standard transaction information parameters include reference transaction information parameters.

[0086] According to an embodiment of the present disclosure, the data conversion component may be a data conversion device based on a perl script. Specifically, the data conversion device based on a perl script may batch process the original transaction information parameters and perform format conversion processing on multiple groups of original transaction information parameters.

[0087] According to an embodiment of the present disclosure, the original data format may be a data format of the original data format, and the target data format may be a data format of the standard transaction information parameter. A format conversion reference table may be pre-constructed, and the format conversion reference table may store the correspondence between the original data format and the target data format.

[0088] According to an embodiment of the present disclosure, based on the target data format, calling the data conversion component to perform format conversion processing on multiple sets of original transaction information parameters can be: calling the data conversion component to convert the original data format of multiple sets of original transaction information parameters into the target data format to obtain multiple sets of standard transaction information parameters. For example: when the original transaction information parameters are in the format of value points, they can be uniformly converted into the format of yield.

[0089] According to the embodiments of the present disclosure, by determining the target data format associated with the original data format based on a pre-built format conversion reference table, data processing efficiency can be improved; by calling the data conversion component to perform format conversion processing on multiple groups of original transaction information parameters, the same original transaction information parameters can be avoided from being stored multiple times in the target database, thereby avoiding the problem of waste of database storage resources caused by data redundancy and ensuring data integrity and consistency.

[0090] According to an embodiment of the present disclosure, data association processing is performed on multiple historical change amplitude values ​​and preset percentile values ​​to generate a reference transaction information parameter value, including: sorting the multiple historical change amplitude values ​​to obtain a sorting result; filtering out a target historical change amplitude value corresponding to the preset percentile value from the sorting result; and when the target historical change amplitude value is an integer, using the target historical change amplitude value as the reference transaction information parameter value.

[0091] In the related art, the required parameter values ​​are mostly fixed values ​​determined based on manual experience. For example, for a reference transaction information parameter, the light value is manually set to 1, indicating that the reference transaction information parameter falls by 1% within the time interval set in the stress test scenario. However, due to the large amount of transaction data to be processed and the long time span, the fixed value determined based on manual experience is less reliable, and it is difficult to quickly select representative reference transaction information parameter values ​​based on manual experience.

[0092] According to an embodiment of the present disclosure, in order to improve the referenceability of the reference transaction information parameter value and to configure the reference transaction information parameter value flexibly, dynamically, quickly and accurately, a plurality of historical change amplitude values ​​may be sorted to obtain a sorting result, and a target historical change amplitude value corresponding to a preset percentile value may be screened out from the sorting result to determine the reference transaction information parameter value. The sorting process may, for example, include sorting a plurality of historical change amplitude values ​​from large to small, or sorting a plurality of historical change amplitude values ​​from small to large. Screening out a target historical change amplitude value corresponding to a preset percentile value from the sorting result may be: matching the sorting result with the preset percentile value to determine the historical change amplitude value corresponding to the preset percentile value.

[0093] For example: for a certain reference transaction information parameter mentioned above, when the predetermined sliding time window is 90 days and the preset percentile value is 60: for each pending transaction data corresponding to the predetermined sliding time window, calculate the decline of each pending transaction data compared to 90 days, and obtain multiple historical change amplitude values; sort the multiple historical change amplitude values ​​from large to small, and when the historical change amplitude value of the 60th percentile value is an integer, take the historical change amplitude value of the 60th percentile value as the reference transaction information parameter value.

[0094] According to an embodiment of the present disclosure, further, the preset quantile value may include a first preset quantile value, a second preset quantile value, and a third preset quantile value. Among them, the first preset quantile value is less than the second preset quantile value, and the second preset quantile value is less than the third preset quantile value. By matching the sorting result with the first preset quantile value, the first target historical change amplitude value can be obtained; when the first target historical change amplitude value is an integer, the first target historical change amplitude value is used as the first reference transaction information parameter value. Correspondingly, by matching the sorting result with the second preset quantile value, the second target historical change amplitude value can be obtained; when the second target historical change amplitude value is an integer, the second target historical change amplitude value is used as the second reference transaction information parameter value; by matching the sorting result with the third preset quantile value, the third target historical change amplitude value can be obtained; when the third target historical change amplitude value is an integer, the third target historical change amplitude value is used as the third reference transaction information parameter value.

[0095] According to an embodiment of the present disclosure, specifically, when analyzing the transaction information of the object to be traded, the transaction information analysis scenario is usually determined based on the reference transaction information parameter value. For example: when analyzing transaction risks, it is necessary to determine the transaction risk analysis scenario based on the reference transaction information parameter value, and determine the transaction data processing result of the object to be traded in the scenario, and the transaction data processing results of the object to be traded in different scenarios are different. For example: in the case where the reference transaction information parameter is an exchange rate depreciation parameter, a first reference transaction information parameter value, a second reference transaction information parameter value, and a third reference transaction information parameter value can be determined, wherein the first reference transaction information parameter value is less than the second reference transaction information parameter value, and the second reference transaction information parameter value is less than the third reference transaction information parameter value. Correspondingly, the first reference transaction information parameter value, the second reference transaction information parameter value, and the third reference transaction information parameter value correspond to the first scenario, the second scenario, and the third scenario, respectively. The first scenario can be a mild stress test scenario, the second scenario can be a moderate stress test scenario, and the third scenario can be a severe stress test scenario. The exchange rate depreciation degree in the first scenario is less than the exchange rate depreciation degree in the second scenario, and the exchange rate depreciation degree in the second scenario is less than the exchange rate depreciation degree in the third scenario. When analyzing transaction risks based on the first reference transaction information parameter value, the second reference transaction information parameter value, and the third reference transaction information parameter value, the transaction risks of the transaction object under different exchange rate depreciation degrees can be analyzed. Further, for each reference transaction information parameter, the first reference transaction information parameter value, the second reference transaction information parameter value, and the third reference transaction information parameter value corresponding to the reference transaction information parameter can be summarized to generate a reference transaction information parameter value summary table. An example of the reference transaction information parameter value summary table is shown in Table 2.

[0096] Table 2

[0097]

[0098] It should be noted that in the above Table 2, the specific values ​​of the first reference transaction information parameter value, the second reference transaction information parameter value, and the third reference transaction information parameter value are only for illustrative purposes, and the embodiments of the present disclosure do not limit the specific values ​​of the first reference transaction information parameter value, the second reference transaction information parameter value, and the third reference transaction information parameter value.

[0099] According to an embodiment of the present disclosure, data association processing is performed on multiple historical change amplitude values ​​and preset percentile values ​​to generate a reference transaction information parameter value, which also includes: when the target historical change amplitude value is a non-integer, linear interpolation processing is performed on the target historical change amplitude value to obtain the reference transaction information parameter value.

[0100] According to an embodiment of the present disclosure, linear interpolation processing may be to assume that there is a straight line between two historical change amplitude values, calculate the value of the midpoint between the two historical change amplitude values ​​by the straight line equation, and use the value of the midpoint as the reference transaction information parameter value.

[0101] According to an embodiment of the present disclosure, when the target historical change amplitude value is a non-integer, linear interpolation processing is performed on the target historical change amplitude value to determine the reference transaction information parameter value, which can improve the referenceability of the transaction information parameter value and thereby improve the accuracy of the transaction data processing results.

[0102] According to an embodiment of the present disclosure, after generating the transaction data processing result, a transaction information analysis report can be generated. Specifically, the transaction information analysis report can be generated according to a customized chart. The transaction information analysis report may include the name of the object to be traded, the current unit net value of the object to be traded, and the yield and net value of the object to be traded under the first scenario, the second scenario, and the third scenario. Among them, the first scenario, the second scenario, and the third scenario can be mild, moderate, and severe stress test scenarios, respectively.

[0103] Table 3

[0104]

[0105] It should be noted that in the above Table 3, the specific values ​​of the current unit net worth, rate of return, and unit net worth are only for illustrative purposes, and the embodiments of the present disclosure do not limit the specific values ​​of the current unit net worth, rate of return, and unit net worth.

[0106] Furthermore, in addition to the name of the transaction object, the current unit net value of the transaction object, and the rate of return and net value of the transaction object in different scenarios, the transaction information analysis report may also include the current price, the number of positions, the market value of positions and other underlying holding information, as well as one or more of the scenario price and scenario market value in different scenarios. The different scenarios may include, for example, the first scenario, the second scenario, and the third scenario.

[0107] Table 4

[0108]

[0109] It should be noted that in the above Table 4, the specific values ​​of the current price, the first scenario price, the second scenario market value, and the third scenario price are only for illustrative purposes, and the embodiments of the present disclosure do not limit the specific values ​​of the current unit net worth, rate of return, and unit net worth.

[0110] According to the embodiments of the present disclosure, the above transaction information analysis process can be implemented through microservice technology. The transaction information analysis request initiated by the user can be received, and the user interaction on the service side can be implemented based on the microservice. The above risk prediction process is implemented through microservice technology, which facilitates the maintenance and expansion of the system and improves the availability and scalability of the system.

[0111] According to the embodiments of the present disclosure, for bond-type trading objects, stock-type trading objects, fund-type trading objects, derivative-type trading objects and exchange rate-type trading objects, they usually correspond to trading information parameters of the market risk category. When analyzing the trading risk of bond-type trading objects, the yield of bond-type trading objects can be calculated based on formula (1).

[0112] (1)

[0113] In the above formula (1), r s is the estimated bond yield on day t. is the bond yield under the predetermined scenario. D is the duration and C is the convexity.

[0114] When analyzing the trading risks of stock-type and fund-type trading objects, the rate of return can be calculated based on formula (2).

[0115] (2)

[0116] In the above formula (2), r s is the estimated rate of return of the stock / fund on day t. is the price return under the predetermined scenario, and β is the correlation between the stock / fund and the market index.

[0117] When analyzing the transaction information of bond-type tradable objects, stock-type tradable objects, fund-type tradable objects, derivative-type tradable objects, and exchange rate-type tradable objects, the return can be calculated based on formula (3).

[0118] (3)

[0119] Among them, r s is the estimated rate of return corresponding to each type of transaction object, P s is the estimated return of each type of transaction object on day t, P t is the market value of each type of transaction object.

[0120] According to the embodiments of the present disclosure, for bond-type trading objects excluding interest-bearing bonds and foreign exchange bonds and non-standard trading objects, they usually correspond to credit risk-type transaction information parameters.

[0121] When analyzing the transaction information of interest-bearing bonds and Huijin's bond-type trading objects and non-standard trading objects, the returns can be calculated based on formula (4).

[0122] 4)

[0123] Among them, P s It is the income of interest-bearing bonds and Huijin's bond-type trading objects and non-standard trading objects. s is the probability of default, LGD s is the default loss rate, P t The market value of base bonds / non-standard assets.

[0124] For short-term financing transactions, the returns can be calculated based on formula (5).

[0125] (5)

[0126] Where P s The income of the transaction object of short-term financing. s is the loss ratio, P t It is the market value of the transaction object of short-term financing.

[0127] According to the embodiment of the present disclosure, after the yield and income corresponding to the object to be traded are calculated based on the above formulas (1) to (5), the region corresponding to the object to be traded when the transaction is generated can be obtained to determine the corresponding pricing currency when the object to be traded generates the transaction, and obtain the target currency, and obtain the currency used by the object to be traded when raising funds, and obtain the original currency. It can be judged whether there is a difference between the original currency and the target currency. The absence of a difference between the original currency and the target currency can indicate that the object to be traded is not affected by exchange rate risk. In the case that there is a difference between the original currency and the target currency, the first middle price of the original currency against the reference currency can be obtained, and the second middle price of the target currency against the reference currency can be obtained. The first middle price is aligned with the second middle price and divided to obtain the daily cross exchange rate corresponding to the original currency and the target currency. For example: the target currency is currency A, the original currency is currency B, and the preset reference currency is currency C. The first middle price of currency A against currency C can be calculated, and the second middle price of currency B against currency C can be obtained, and the first middle price is aligned with the second middle price and divided to obtain the daily cross exchange rate corresponding to currency A and currency B.

[0128] According to the embodiments of the present disclosure, by identifying the region and currency corresponding to the transaction generated by the transaction object, and based on the first middle price of the original currency against the reference currency, and the target currency against the reference, the cross exchange rates of various currency pairs can be calculated in batches, thereby technically reducing the delay of real-time calculation and improving calculation efficiency.

[0129] Furthermore, for the transaction objects involving foreign currency assets, the regional holding distribution of the corresponding fund can be obtained from the external table and mapped to the regional corresponding asset valuation currency, and the exchange rate can be calculated based on the holding ratio.

[0130] Based on the above transaction data processing method, the present disclosure also provides a transaction data processing device. Figure 5 The device is described in detail.

[0131] Figure 5 The structural block diagram of the transaction data processing device according to the embodiment of the present disclosure is schematically shown.

[0132] like Figure 5 As shown, the transaction data processing device 500 of this embodiment includes an extraction module 510, a first reading module 520, a derivation module 530, a calculation module 540, a data association module 550 and a first generation module 560.

[0133] Extraction module, used to extract target risk features corresponding to the object to be traded Module 510 is used to extract target risk features corresponding to the object to be traded. In one embodiment, the extraction module 510 can be used to perform the operation S210 described above, which will not be described in detail here.

[0134] The first reading module 520 is used to read multiple reference transaction information parameters matching the target risk characteristics from a pre-constructed full transaction information parameter table based on the target risk characteristics, wherein the reference transaction information parameters are obtained by performing data conversion processing on the original transaction information parameters. In one embodiment, the first reading module 520 can be used to perform the operation S220 described above, which will not be described in detail here.

[0135] The export module 530 is used to export multiple groups of to-be-processed transaction data corresponding to multiple reference transaction information parameters within a predetermined historical time interval from the transaction data storage platform. In one embodiment, the export module 530 can be used to perform the operation S230 described above, which will not be described in detail here.

[0136] The calculation module 540 is used to calculate the change amplitude value of each group of pending transaction data within a predetermined sliding time window to obtain multiple historical change amplitude values. In one embodiment, the calculation module 540 can be used to perform the operation S240 described above, which will not be repeated here.

[0137] The data association module 550 is used to perform data association processing on multiple historical change amplitude values ​​and preset percentile values ​​to generate reference transaction information parameter values. In one embodiment, the data association module 550 can be used to perform the operation S250 described above, which will not be repeated here.

[0138] The first generating module 560 is used to generate a transaction data processing result corresponding to the transaction object based on the reference transaction information parameter value. In one embodiment, the first generating module 560 can be used to perform the operation S260 described above, which will not be described in detail here.

[0139] According to an embodiment of the present disclosure, the transaction data processing device also includes a second reading module, a data conversion module and a second generating module.

[0140] The second reading module is used to respond to the data reading instruction and read multiple sets of original transaction information parameters from multiple source databases; the data conversion module is used to call the data conversion component to perform data conversion processing on the multiple sets of original transaction information parameters to obtain multiple sets of standard transaction information parameters; the second generation module is used to generate a full transaction information parameter table based on the multiple sets of standard transaction information parameters.

[0141] According to an embodiment of the present disclosure, the second generating module includes a first classification submodule, a second classification submodule, a mapping submodule and a generating submodule.

[0142] The first classification submodule includes classifying the standard transaction information parameters for each group of standard transaction information parameters based on multiple predetermined risk categories to obtain an initial classification result, wherein the initial classification result includes multiple initial parameter sets corresponding one-to-one to the multiple predetermined risk categories; the second classification submodule includes classifying the initial parameter sets for each initial parameter set based on the predetermined risk subcategories to obtain a target classification result, wherein the target classification result includes multiple target parameter sets corresponding one-to-one to the multiple predetermined risk subcategories; the mapping submodule includes mapping the target classification result to a multi-level tree-like risk structure to obtain a mapping result; the generation submodule includes generating a full transaction information parameter table based on the mapping result.

[0143] According to an embodiment of the present disclosure, the data conversion module includes an identification submodule, a first determination submodule and a calling submodule.

[0144] The identification submodule is used to identify the original data format corresponding to multiple groups of original transaction information parameters; the determination submodule is used to determine the target data format associated with the original data format from a pre-built format conversion reference table; the calling submodule is used to call the data conversion component to perform format conversion processing on multiple groups of original transaction information parameters based on the target data format, and obtain multiple groups of standard transaction information parameters, wherein the multiple groups of standard transaction information parameters include reference transaction information parameters.

[0145] According to an embodiment of the present disclosure, the data association module includes a sorting submodule, a screening submodule and a second determining submodule.

[0146] The sorting submodule is used to sort multiple historical change amplitude values ​​to obtain a sorting result; the screening submodule is used to screen out the target historical change amplitude value corresponding to the preset percentile value from the sorting result; the second determination submodule is used to use the target historical change amplitude value as a reference transaction information parameter value when the target historical change amplitude value is an integer.

[0147] According to an embodiment of the present disclosure, the data association module further includes a linear interpolation processing module.

[0148] The linear interpolation processing module is used to perform linear interpolation processing on the target historical change amplitude value when the target historical change amplitude value is a non-integer, so as to obtain the reference transaction information parameter value.

[0149] According to an embodiment of the present disclosure, any multiple modules of the extraction module 510, the first reading module 520, the export module 530, the calculation module 540, the data association module 550 and the first generation module 560 can be combined into 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 extraction module 510, the first reading module 520, the export module 530, the calculation module 540, the data association module 550 and the first generation module 560 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 implemented in any one of the three implementation methods of software, hardware and firmware or in any appropriate combination of any of them. Alternatively, at least one of the extraction module 510, the first reading module 520, the export module 530, the calculation module 540, the data association module 550 and the first generation module 560 can be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function can be performed.

[0150] Figure 6 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.

[0151] like Figure 6As shown, the electronic device 600 according to an embodiment of the present disclosure includes a processor 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. The processor 601 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 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.

[0152] In RAM 603, various programs and data required for the operation of electronic device 600 are stored. Processor 601, ROM 602 and RAM 603 are connected to each other via bus 604. Processor 601 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 602 and / or RAM 603. It should be noted that the program can also be stored in one or more memories other than ROM 602 and RAM 603. Processor 601 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.

[0153] According to an embodiment of the present disclosure, the electronic device 600 may further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 may further include one or more of the following components connected to the input / output (I / O) interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0154] 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.

[0155] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it 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 thereof. 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, the computer-readable storage medium may include the ROM 602 and / or RAM 603 described above and / or one or more memories other than ROM 602 and RAM 603.

[0156] 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.

[0157] 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 601. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0158] 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 609, and / or installed from a removable medium 611. 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.

[0159] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the processor 601, 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, apparatus, module, unit, etc. described above can be implemented by a computer program module.

[0160] 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).

[0161] 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.

[0162] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0163] 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, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. 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, characterized in that: The method comprises: Extract the target risk characteristics corresponding to the transaction object; Based on the target risk characteristics, multiple reference transaction information parameters matching the target risk characteristics are read from a pre-constructed full transaction information parameter table, wherein the reference transaction information parameters are obtained by performing data conversion processing on the original transaction information parameters; Exporting from the transaction data storage platform a plurality of groups of to-be-processed transaction data within a predetermined historical time interval, which correspond one-to-one to the plurality of reference transaction information parameters; For each group of the transaction data to be processed, calculating the change amplitude value of each transaction data to be processed within a predetermined sliding time window to obtain a plurality of historical change amplitude values; Performing data association processing on the multiple historical change amplitude values ​​and the preset percentile values ​​to generate reference transaction information parameter values; Based on the reference transaction information parameter value, a transaction data processing result corresponding to the transaction object is generated.

2. The method according to claim 1, characterized in that The method further comprises: In response to a data reading instruction, reading a plurality of sets of original transaction information parameters from a plurality of source databases; Calling a data conversion component to perform the data conversion process on the multiple groups of original transaction information parameters to obtain multiple groups of standard transaction information parameters; Based on the multiple groups of standard transaction information parameters, the full transaction information parameter table is generated.

3. The method according to claim 2, characterized in that The multiple groups of standard transaction information parameters are stored in a multi-level tree-like risk structure, wherein the multi-level tree-like risk structure includes a root node and child nodes, wherein the root node stores transaction risk category data, and the child nodes store transaction risk subcategory data; The generating the full transaction information parameter table based on the multiple sets of standard transaction information parameters includes: For each group of the standard transaction information parameters, classify the standard transaction information parameters based on a plurality of predetermined risk categories to obtain an initial classification result, wherein the initial classification result includes a plurality of initial parameter sets corresponding to the plurality of predetermined risk categories one by one; For each of the initial parameter sets, classify the initial parameter sets based on the predetermined risk subcategories to obtain a target classification result, wherein the target classification result includes a plurality of target parameter sets corresponding one-to-one to the plurality of predetermined risk subcategories; Mapping the target classification result to the multi-level tree-like risk structure to obtain a mapping result; Based on the mapping result, the full transaction information parameter table is generated.

4. The method according to claim 2, characterized in that: The calling of the data conversion component to perform data conversion processing on the multiple groups of the original transaction information parameters includes: Identifying original data formats corresponding to the plurality of sets of original transaction information parameters; determining a target data format associated with the original data format from a pre-built format conversion reference table; Based on the target data format, the data conversion component is called to perform format conversion processing on the multiple groups of original transaction information parameters to obtain the multiple groups of standard transaction information parameters, wherein the multiple groups of standard transaction information parameters include the reference transaction information parameters.

5. The method according to claim 1, characterized in that The performing data association processing on the multiple historical change amplitude values ​​and the preset percentile values ​​to generate the reference transaction information parameter value comprises: Sorting the multiple historical change amplitude values ​​to obtain a sorting result; Filtering the target historical change amplitude value corresponding to the preset percentile value from the sorting results; When the target historical change amplitude value is an integer, the target historical change amplitude value is used as the reference transaction information parameter value.

6. The method according to claim 5, characterized in that The performing data association processing on the multiple historical change amplitude values ​​and the preset percentile values ​​to generate the reference transaction information parameter value also includes: When the target historical change amplitude value is a non-integer, a linear interpolation process is performed on the target historical change amplitude value to obtain the reference transaction information parameter value.

7. A transaction data processing device, characterized in that: The device comprises: An extraction module, used to extract target risk features corresponding to the transaction object; A first reading module is used to read, based on the target risk feature, a plurality of reference transaction information parameters matching the target risk feature from a pre-constructed full transaction information parameter table, wherein the reference transaction information parameters are obtained by performing data conversion processing on the original transaction information parameters; An export module, used to export multiple groups of to-be-processed transaction data corresponding one-to-one to the multiple reference transaction information parameters within a predetermined historical time interval from a transaction data storage platform; A calculation module, configured to calculate, for each group of the transaction data to be processed, a change amplitude value of each of the transaction data to be processed within a predetermined sliding time window, and obtain a plurality of historical change amplitude values; a data association module, configured to perform data association processing on the plurality of historical change amplitude values ​​and preset percentile values ​​to generate a reference transaction information parameter value; and The first generating module is used to generate a transaction data processing result corresponding to the transaction object based on the reference transaction information parameter value.

8. An electronic device comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images