Data processing method and device, equipment, storage medium and program product

Abstract

The application provides a data processing method, device, equipment, storage medium and program product. The method comprises the following steps: an electronic device inputs first attribute information of a target bond into a first model, obtains output first transaction information of the target bond, checks the first transaction information and second transaction information, generates a first checking result, if the first checking result indicates that the first transaction information is consistent with the second transaction information, inputs the first attribute information, the first transaction information and holiday information into a second model, obtains output first time information of the target bond, checks the first time information and second time information, and generates a second checking result. The technical scheme can determine whether the time information in the bank system has a problem, so that the problem can be corrected in time, thereby improving the accuracy of the time information in the system.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a data processing method, apparatus, device, storage medium, and program product. Background Technology

[0002] With the deepening of financial market reforms, financial transactions, especially bond transactions, have grown rapidly. How to process bond data quickly and accurately is an important problem that the industry urgently needs to solve.

[0003] Currently, the banking system needs to maintain the attribute information of bonds based on the bond issuance documents or the bond definitions published by custodian institutions in the market. Then, it extracts and calculates the attribute information according to a preset strategy to generate bond transaction information. Finally, it generates the bond's time information based on the attribute and transaction information. The attribute information refers to bond information that can be found in the public market. The transaction information is generated by further processing the attribute information, such as whether interest accrual is adjusted, whether interest payment is adjusted, the interest payment interval, the interest payment adjustment method, and the reset date. The time information mainly includes time-related bond information such as when yield calculation begins and when interest is paid in each period.

[0004] However, the accuracy of time information in existing banking systems is low. Summary of the Invention

[0005] This application provides a data processing method, apparatus, device, storage medium, and program product to solve the problem of low accuracy of time information in existing banking systems.

[0006] In a first aspect, embodiments of this application provide a data processing method, including:

[0007] The first attribute information of the target bond is input into the first model to obtain the first transaction information of the target bond. The first attribute information is the information published when the target bond is issued. The first transaction information is used to determine the method of calculating the return of the target bond. The first model is obtained by pre-training the model on the attribute information and transaction information of the sample bond.

[0008] The first transaction information is compared with the second transaction information to generate a first comparison result. The second transaction information is pre-generated by the bank system based on the first attribute information of the target bond. The first comparison result is used to indicate whether the first transaction information and the second transaction information are consistent.

[0009] If the first verification result indicates that the first transaction information is consistent with the second transaction information, then the first attribute information, the first transaction information and the holiday information are input into the second model to obtain the first time information of the target bond. The first time information is used to determine the time for calculating the return of the target bond. The second model is obtained by pre-training the model on the attribute information, transaction information, holiday information and time information of the sample bond.

[0010] The first time information is compared with the second time information to generate a second comparison result. The second time information is pre-generated by the bank system based on the first attribute information of the target bond and the second transaction information. The second comparison result is used to determine whether the first time information and the second time information are consistent.

[0011] In one possible design of the first aspect, before inputting the first attribute information of the target bond into the first model, the method further includes:

[0012] Obtain the first attribute information of the target bond;

[0013] The first attribute information and the second attribute information are compared to generate a third comparison result. The second attribute information is the attribute information of the target bond that is pre-stored in the banking system. The third comparison result is used to determine whether the first attribute information and the second attribute information are consistent.

[0014] Optionally, the step of verifying the first attribute information and the second attribute information to generate a third verification result includes:

[0015] Based on the field mapping relationship and the dictionary mapping relationship, the first attribute information and the second attribute information are aligned. The field mapping relationship is the correspondence between the fields in the first attribute information and the fields in the second attribute information, and the dictionary mapping relationship is the correspondence between the attribute values ​​in the first attribute information and the attribute values ​​in the second attribute information.

[0016] The aligned first attribute information and the aligned second attribute information are checked to generate the third check result.

[0017] Optionally, the method further includes:

[0018] If the third verification result indicates that the first attribute information and the second attribute information are inconsistent, then the third verification result is output;

[0019] If the third verification result indicates that the first attribute information and the second attribute information are consistent, then the first attribute information is input into the first model.

[0020] In another possible design of the first aspect, after verifying the first transaction information with the second transaction information to generate a first verification result, the method further includes:

[0021] If the first verification result indicates that the first transaction information and the second transaction information are inconsistent, then the first verification result is output.

[0022] In another possible design of the first aspect, after verifying the first time information with the second time information to generate a second verification result, the method further includes:

[0023] If the second verification result indicates that the first time information and the second time information are inconsistent, then the second verification result is output.

[0024] In another possible design of the first aspect, before inputting the first attribute information of the target bond into the first model and obtaining the output first transaction information of the target bond, the method further includes:

[0025] Obtain a first training set, which includes the attribute information and transaction information of the sample bonds;

[0026] The model is trained based on the first training set to generate the first model.

[0027] In another possible design of the first aspect, before inputting the first attribute information of the target bond into the first model and obtaining the output first transaction information of the target bond, the method further includes:

[0028] Obtain a second training set, which includes the attribute information, transaction information, holiday information, and time information of the sample bonds;

[0029] The model is trained based on the second training set to generate the second model.

[0030] Secondly, embodiments of this application provide a data processing apparatus, including:

[0031] The input module is used to input the first attribute information of the target bond into the first model and obtain the first transaction information of the target bond. The first attribute information is the information published when the target bond is issued. The first transaction information is used to determine the method of calculating the return of the target bond. The first model is obtained by pre-training the model on the attribute information and transaction information of the sample bond.

[0032] The verification module is used to verify the first transaction information and the second transaction information to generate a first verification result. The second transaction information is pre-generated by the bank system based on the first attribute information of the target bond. The first verification result is used to indicate whether the first transaction information and the second transaction information are consistent.

[0033] The input module is further configured to input the first attribute information, the first transaction information, and the holiday information into the second model if the first verification result indicates that the first transaction information is consistent with the second transaction information, and to obtain the first time information of the target bond output. The first time information is used to determine the time for calculating the return of the target bond. The second model is obtained by pre-training the model on the attribute information, transaction information, holiday information, and time information of the sample bond.

[0034] The verification module is further configured to verify the first time information and the second time information to generate a second verification result. The second time information is pre-generated by the bank system based on the first attribute information of the target bond and the second transaction information. The second verification result is used to determine whether the first time information and the second time information are consistent.

[0035] In one possible design of the second aspect, the device further includes:

[0036] The acquisition module is used to acquire the first attribute information of the target bond;

[0037] The verification module is further configured to verify the first attribute information and the second attribute information to generate a third verification result. The second attribute information is the attribute information of the target bond that is pre-stored in the banking system. The third verification result is used to determine whether the first attribute information and the second attribute information are consistent.

[0038] Optionally, the verification module is specifically used for:

[0039] Based on the field mapping relationship and the dictionary mapping relationship, the first attribute information and the second attribute information are aligned. The field mapping relationship is the correspondence between the fields in the first attribute information and the fields in the second attribute information, and the dictionary mapping relationship is the correspondence between the attribute values ​​in the first attribute information and the attribute values ​​in the second attribute information.

[0040] The aligned first attribute information and the aligned second attribute information are checked to generate the third check result.

[0041] Optionally, the device further includes:

[0042] The input module is configured to output the third verification result if the third verification result indicates that the first attribute information and the second attribute information are inconsistent.

[0043] The input module is further configured to input the first attribute information into the first model if the third verification result indicates that the first attribute information and the second attribute information are consistent.

[0044] In another possible design of the second aspect, after verifying the first transaction information with the second transaction information to generate a first verification result, the device further includes:

[0045] The output module is configured to output the first verification result if the first verification result indicates that the first transaction information and the second transaction information are inconsistent.

[0046] In another possible design of the second aspect, after verifying the first time information and the second time information to generate a second verification result, the output module is further configured to:

[0047] If the second verification result indicates that the first time information and the second time information are inconsistent, then the second verification result is output.

[0048] In another possible design of the second aspect, before inputting the first attribute information of the target bond into the first model and obtaining the output first transaction information of the target bond, the apparatus further includes:

[0049] The acquisition module is further configured to acquire a first training set, the first training set including the attribute information and transaction information of the sample bonds;

[0050] The training module is used to train the model based on the first training set and generate the first model.

[0051] In another possible design of the second aspect, before inputting the first attribute information of the target bond into the first model and obtaining the first transaction information of the target bond, the acquisition module is further used to acquire a second training set, the second training set including the attribute information, transaction information, holiday information and time information of the sample bond;

[0052] The training module is also used to train the model based on the second training set to generate the second model.

[0053] Thirdly, embodiments of this application provide an electronic device, including: a processor, a memory, and computer program instructions stored in the memory and executable on the processor, wherein the processor executes the computer program instructions to implement the methods provided in the first aspect and various possible designs.

[0054] Fourthly, embodiments of this application may provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the first aspect and various possible designs.

[0055] Fifthly, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, is used to implement the methods provided in the first aspect and various possible designs.

[0056] The data processing method, apparatus, device, storage medium, and program product provided in this application embodiment involve an electronic device that inputs first attribute information of a target bond into a first model, obtains the output first transaction information of the target bond, compares the first transaction information with second transaction information, and generates a first comparison result. If the first comparison result indicates that the first transaction information and the second transaction information are consistent, the first attribute information, the first transaction information, and holiday information are input into a second model to obtain the output first time information of the target bond. The first time information is then compared with the second time information to generate a second comparison result. In this technical solution, the first transaction information and the first time information of the target bond can be obtained through the first model and the second model respectively, and the first transaction information and the first time information can be compared with the corresponding second transaction information and the second time information, thereby determining whether there are any problems with the time information in the banking system, so that they can be corrected in a timely manner when problems exist, thereby improving the accuracy of the time information in the system. Attached Figure Description

[0057] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0058] Figure 1 A flowchart illustrating an embodiment of the data processing method provided in this application;

[0059] Figure 2 A flowchart illustrating Embodiment 2 of the data processing method provided in this application;

[0060] Figure 3 A flowchart illustrating Embodiment 3 of the data processing method provided in this application;

[0061] Figure 4 This is a schematic diagram of the structure of the data processing apparatus provided in the embodiments of this application;

[0062] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0063] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0064] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0065] It should be understood that the data processing methods, apparatus, devices, storage media, and program products provided in the embodiments of this application can be used in the financial field, or in any field other than the financial field. The embodiments of this application do not specifically limit the application fields of the data processing methods, apparatus, devices, storage media, and program products.

[0066] Before introducing the embodiments of this application, the application background of the embodiments of this application will be explained first:

[0067] Currently, bond data processing primarily involves banking systems generating bond transaction information based on bond attributes and pre-configured strategies, and then determining the bond's timing information based on these attributes and transaction data. However, the accuracy of bond transaction information determined by existing technology is low, resulting in low accuracy of the timing information determined based on this transaction information. The low accuracy of bond transaction information is mainly due to the following factors:

[0068] 1. If the banking system does not have a strategy that matches the bond, the transaction information for the bond generated based on the existing strategies of the banking system will be inaccurate.

[0069] 2. If the interest rates of floating-rate bonds in the market have changed, but the interest rates in the banking system have not been updated in a timely manner, the transaction information determined based on the interest rates in the banking system may be inaccurate.

[0070] Based on the above-mentioned technical problems, the technical concept of this application is as follows:

[0071] A first model and a second model can be pre-acquired. The first model is pre-trained and can retrieve transaction information based on bond attribute information. The second model is pre-trained and can retrieve time information based on bond attribute information, transaction information, and holiday information. Both models have self-learning capabilities, and their processing is unaffected by the bank system's strategies and interest rates. This allows the determination of the target bond's transaction and time information based on the first and second models, which can then be compared with the corresponding transaction and time information in the bank system. This enables timely correction of any discrepancies in the bank system's transaction and time information, thereby improving the accuracy of the time information in the bank system.

[0072] The technical solution of this application will now be described in detail through specific embodiments.

[0073] It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0074] Figure 1 This is a flowchart illustrating an embodiment of the data processing method provided in this application. Figure 1 As shown, this data processing method is applied to an electronic device, which can be a terminal device or a server. The data processing method may include the following steps:

[0075] S101. Input the first attribute information of the target bond into the first model and obtain the first transaction information of the target bond.

[0076] In this embodiment of the application, since the time information of the bond is calculated based on the transaction information of the bond, in order to solve the problem of low information accuracy in the banking system in the prior art, the transaction information and time information of the bond can be obtained by means of the first model and the second model, and then checked against the pre-calculated transaction information and time information in the banking system, so as to determine whether there is an error in the time information in the banking system, so as to correct it in time when there is an error.

[0077] In this step, the first attribute information of the target bond can be input into the first model to obtain the first transaction information output by the first model. Since the first model has self-learning ability, it can process the first attribute information to obtain the correct first transaction information. In this way, the second transaction information calculated by the bank system can be verified based on the first transaction information.

[0078] The first attribute information is the information published when the target bond is issued, which is the information that can be found in the public market. For example, the bond type, interest calculation type, interest calculation basis, interest payment frequency, issuance price, issuance date, interest accrual date, bond term, face value, whether it is a floating interest rate or a fixed interest rate, etc.

[0079] It should be understood that the embodiments of this application do not specifically limit the content of the first attribute information, which can be determined according to the actual situation.

[0080] The first transaction information is used to determine the method for calculating the target bond yield (i.e., interest). This first transaction information may not be available in the public market. For example, it may include information such as: calendar reset (which country's calendar is used for resetting if it is a floating-rate bond), reset adjustment method (how to handle the reset date if it falls on a holiday, whether to move it forward, backward, or in another way), whether interest calculation is adjusted (how to handle it if the interest calculation deadline falls on a holiday), whether interest payment is adjusted (how to handle it if the interest payment date falls on a holiday), interest payment adjustment method (how to handle it if the interest payment date falls on a holiday), and the interest payment date interval (the relationship with the interest calculation deadline).

[0081] It should be understood that the embodiments of this application do not specifically limit the content of the first transaction information, which can be determined according to the actual situation.

[0082] The first model is obtained by pre-training the model based on the attribute information and transaction information of the sample bonds.

[0083] It should be understood that the training process of the first model can be specifically described through the following embodiments, and will not be repeated here.

[0084] S102. Verify the first transaction information with the second transaction information to generate the first verification result.

[0085] In this step, the second transaction information is pre-generated by the bank system based on the first attribute information of the target bond. After obtaining the first transaction information, it can be determined whether the first transaction information is consistent with the second transaction information pre-generated in the bank system, thereby generating a first verification result. This first verification result is used to indicate whether the first transaction information and the second transaction information are consistent.

[0086] In one possible implementation, the first verification result can be generated by comparing the values ​​of each sub-transaction information in the first transaction information with the corresponding values ​​in the second transaction information. For example, suppose the reset adjustment method (sub-transaction information) in the first transaction information is "adjust forward (value)," and the reset adjustment method in the second transaction information is "adjust forward." The two are compared to determine if they are consistent. This process is repeated for all sub-transaction information to generate the first verification result.

[0087] Optionally, if the first verification result indicates that the first transaction information and the second transaction information are inconsistent, the first verification result is output. Optionally, a first reminder message can also be output, which is used to remind business personnel that the first transaction information and the second transaction information are inconsistent. For example, the first reminder message can be "XXX bond XXX field is inaccurate".

[0088] S103. If the first verification result indicates that the first transaction information is consistent with the second transaction information, then the first attribute information, the first transaction information and the holiday information are input into the second model to obtain the first time information of the target bond.

[0089] In this step, when the first transaction information matches the second transaction information, it is necessary to further verify the time information in the bank system. First, the correct time information needs to be generated through the second model.

[0090] The first-time information is used to determine when to calculate the target bond yield (i.e., interest). For example, the first-time information can be when to start calculating interest and when to pay interest in each period (which can be a historical period or a future period).

[0091] For example, first-time information can be represented by Table 1.

[0092] Table 1

[0093]

[0094]

[0095] It should be understood that the leftmost column in Table 1 above represents the sub-time information in the first time information, and each subsequent column represents the value of the sub-time information in one cycle. The above values ​​are only one example, and other values ​​can also be used to represent them, without any specific limitation. It should be understood that the first time information may also contain other sub-time information, which can be limited according to the actual situation. This application embodiment does not impose any specific limitation in this regard.

[0096] The second model was obtained by pre-training the model based on the attribute information, transaction information, holiday information, and time information of the sample bonds.

[0097] It should be understood that the training process of the second model can be specifically described through the following embodiments, and will not be repeated here.

[0098] S104. Verify the first time information with the second time information to generate a second verification result.

[0099] In this step, after generating the first time information, the first time information can be compared with the second time information pre-generated in the bank system to determine whether the second time information in the bank system is correct.

[0100] The second time information is pre-generated by the banking system based on the first attribute information and the second transaction information of the target bond, and the second verification result is used to determine whether the first time information and the second time information are consistent.

[0101] Optionally, the second time information can also be information maintained by relevant staff in the banking system based on the first attribute information and the second transaction information of the target bond.

[0102] Optionally, if the second verification result indicates that the first time information and the second time information are inconsistent, then the second verification result is output. Optionally, a second reminder message can also be output, which is used to remind business personnel that the first time information and the second time information are inconsistent. For example, the second verification result can be "The time information that the interest accrual start date of XXX bond is XXX and the interest accrual end date is XXX is inaccurate".

[0103] The data processing method provided in this application involves an electronic device inputting the first attribute information of a target bond into a first model to obtain the output first transaction information of the target bond. The first transaction information is then compared with second transaction information to generate a first verification result. If the first verification result indicates that the first transaction information and the second transaction information are consistent, the first attribute information, the first transaction information, and holiday information are input into a second model to obtain the output first time information of the target bond. The first time information is then compared with the second time information to generate a second verification result. In this technical solution, the first transaction information and the first time information of the target bond can be obtained through the first model and the second model respectively, and the first transaction information and the first time information can be compared with the corresponding second transaction information and second time information to determine whether there are any problems with the time information in the banking system. This allows for timely correction when problems exist, thereby improving the accuracy of the time information in the system.

[0104] Compared to existing manual verification processes, which require staff to perform calculations based on publicly available market information and then verify, process, and judge the transaction and time information calculated in the banking system, manual processing lacks accurate measurement and cannot guarantee rigor, leading to inaccurate accounting, high error rates, and low efficiency. This application's embodiment generates correct transaction and time information using a first and second model, thereby replacing manual calculation and evaluation to verify transaction and time information in the banking system, improving accuracy and efficiency, and avoiding accounting discrepancies.

[0105] Optionally, if the above verification information indicates an inconsistency between two pieces of information, the corresponding information in the system will be corrected based on the information output by the model. For example, if the first verification result indicates that the first transaction information and the second transaction information are inconsistent, the second transaction information will be modified to reflect the first transaction information; if the second verification result indicates that the first time information and the second time information are inconsistent, the second time information will be modified to reflect the first time information, in order to improve the accuracy of the data in the system.

[0106] Optionally, since bond transaction and timing information are derived from attribute information, discrepancies can arise when the attribute information in the banking system differs from the bond issuance documents or the bond definition published by the custodian in the market. Consequently, the transaction and timing information determined based on this attribute information will also be problematic. Therefore, before verifying the second transaction and timing information of the target bond in the banking system, the second attribute information of the target bond can be pre-verified. This allows for timely correction of any issues with the second attribute information, avoiding redundant subsequent verification of transaction and timing information and improving processing efficiency.

[0107] Figure 2 This is a flowchart illustrating a second embodiment of the data processing method provided in this application. Figure 2 As shown, before inputting the first attribute information of the target bond into the first model, the data processing method may further include the following steps:

[0108] S201. Obtain the first attribute information of the target bond.

[0109] In this step, the first attribute information of the target bond published by the custodian institution (such as China Central Depository & Clearing Co., Ltd. or Shanghai Clearing House) can be obtained so that the second attribute information stored in the bank system can be verified based on the first attribute information.

[0110] In one possible implementation, the primary attribute information of the target bond can be imported into a temporary table. Specifically, the electronic device contains components that can be pre-configured to support the import of files of different formats into the temporary table.

[0111] S202. Verify the first attribute information and the second attribute information to generate a third verification result.

[0112] In this step, after obtaining the first attribute information, the first attribute information can be checked against the second attribute information in the system so that if there are any problems with the second attribute information, it can be corrected in time to avoid affecting the subsequent calculation time information.

[0113] The second attribute information is the attribute information of the target bond that is pre-stored in the banking system.

[0114] In one possible implementation, S202 can be achieved through steps (1) and (2):

[0115] Step (1): Align the first attribute information and the second attribute information according to the field mapping relationship and the dictionary mapping relationship.

[0116] When different data sources express the same meaning through data, the data may be expressed in different forms. For example, Monday might be represented by "X" in the first attribute information and by "x" in the second attribute information. Before verifying the first and second attribute information, it is necessary to align them and convert them to the same expression form to avoid verification errors caused by different expression forms.

[0117] Among them, the field mapping relationship is the correspondence between the fields in the first attribute information and the fields in the second attribute information, and the dictionary mapping relationship is the correspondence between the attribute values ​​in the first attribute information and the attribute values ​​in the second attribute information.

[0118] For example, the field mapping relationship can be represented by Table 2.

[0119] Table 2

[0120] External data source Field (First attribute information) Field (Second attribute information) Dictionary mapping relationship Data source 1 Table A, field 'a' Table B, field b Relationship 1 Data source 2 Table C, field C Table D, field d Relationship 2 Data source 3 Table E, field e Table F, field f Relationship 3

[0121] Referring to Table 2, the external data source is the data source for obtaining the first attribute information of the target bond. It should be understood that the field mapping relationship in Table 2 may also include other content and forms, which can be limited according to the actual situation. This application embodiment does not limit this.

[0122] For example, the dictionary mapping relationships in Table 2 can be represented by Table 3.

[0123] Table 3

[0124] Relationship Number Attribute value (first attribute information) Attribute value (secondary attribute information) Relationship 1 G g Relationship 2 H h Relationship 3 I i

[0125] It should be understood that dictionary mapping relationships may also include other content and forms, which can be limited according to the actual situation. This application embodiment does not limit this.

[0126] Step (2): Verify the aligned first attribute information and the aligned second attribute information to generate a third verification result.

[0127] After aligning the first attribute information and the second attribute information, the aligned first attribute information and the aligned second attribute information are compared to determine whether they are consistent, thereby generating a third verification result. The third verification result is used to determine whether the first attribute information and the second attribute information are consistent.

[0128] Furthermore, if the third verification result indicates a discrepancy between the first and second attribute information, then the third verification result is output. Optionally, a third reminder message can also be output to alert business personnel to the inconsistency between the first and second attribute information. For example, this third reminder message could be "XXX bond XXX field is inaccurate".

[0129] Optionally, if the third verification result indicates that the first attribute information and the second attribute information are inconsistent, the second attribute information can be modified to the first attribute information.

[0130] If the third verification result indicates that the first attribute information and the second attribute information are consistent, then the first attribute information is input into the first model.

[0131] In the above embodiments, before inputting the first attribute information of the target bond into the first model, the second attribute information in the banking system can be checked to ensure timely correction of any issues with the second attribute information, thus avoiding impact on subsequent processing. Furthermore, if issues arise with the second transaction information in the banking system, the third verification result can be used to analyze whether the problem is caused by the second attribute information, facilitating subsequent correction of the problem.

[0132] Furthermore, based on any of the above embodiments, before verifying the second transaction information and the second time information of the target bond in the banking system, model training is also required to obtain the first model and the second model.

[0133] It should be understood that the electronic device used for model training and the electronic device used for executing the above data processing method can be the same device or different devices, and can be limited according to the actual situation. This application embodiment does not make specific limitations in this regard.

[0134] First Model

[0135] Obtain the first training set and train the model based on the first training set to generate the first model.

[0136] The first training set includes attribute information and transaction information of sample bonds. The sample bonds can be existing bonds in the banking system, and the transaction information of the sample bonds can be correct transaction information obtained from the historical processing data of the sample bonds according to the Artificial Intelligence (AI) algorithm and confirmed by humans.

[0137] It should be understood that the embodiments of this application do not limit the method of obtaining the first training set or the type of the first model.

[0138] Second Model

[0139] Obtain a second training set and train the model based on the second training set to generate a second model.

[0140] The second training set includes attribute information, transaction information, holiday information, and time information of the sample bonds. Optionally, holiday information can be represented by a calendar, and the time information of the sample bonds can be accurate time information obtained from the historical processing data of the sample bonds by the AI ​​algorithm and verified manually.

[0141] The data processing method based on any of the above embodiments will be described below with a specific example.

[0142] Figure 3 This is a flowchart illustrating Embodiment 3 of the data processing method provided in this application. Figure 3 As shown, this data processing method includes two modes: Mode 1 and Mode 2. Mode 1 verifies the second attribute information in the banking system, while Mode 2 verifies the second transaction information and the second time information in the banking system. This data processing method may include the following steps:

[0143] Step 1: Determine the enabled mode.

[0144] The enabled mode can be determined based on the data to be verified. When enabling mode one, steps 11 to 14 are executed; when enabling mode two, steps 21 to 26 are executed.

[0145] Mode 1:

[0146] Step 11: Obtain the first attribute information of the target bond.

[0147] Step 12: Align the first attribute information and the second attribute information according to the field mapping relationship and the dictionary mapping relationship.

[0148] Step 13: Check the aligned first attribute information and the aligned second attribute information. If they match, end the processing flow; otherwise, proceed to step 14.

[0149] Step 14: Output the third reminder message and end the processing flow.

[0150] Mode 2:

[0151] Step 21: Input the first attribute information of the target bond into the first model and obtain the first transaction information of the target bond.

[0152] Step 22: Compare the first transaction information with the second transaction information. If they do not match, proceed to step 23. If they match, proceed to step 24.

[0153] Step 23: Output the first reminder message and end the processing flow.

[0154] Step 24: Input the first attribute information, the first transaction information, and the holiday information into the second model to obtain the first time information of the target bond.

[0155] Step 25: Compare the first time information with the second time information. If they match, end the processing flow. If they do not match, proceed to step 26.

[0156] Step 26: Output the second reminder message and end the processing flow.

[0157] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0158] Figure 4 This is a schematic diagram of the structure of the data processing apparatus provided in an embodiment of this application. Figure 4 As shown, the data processing device 400 includes:

[0159] The input module 401 is used to input the first attribute information of the target bond into the first model and obtain the first transaction information of the target bond. The first attribute information is the information published when the target bond is issued. The first transaction information is used to determine the method of calculating the return of the target bond. The first model is obtained by pre-training the model on the attribute information and transaction information of the sample bond.

[0160] The verification module 402 is used to verify the first transaction information and the second transaction information to generate a first verification result. The second transaction information is pre-generated by the bank system based on the first attribute information of the target bond. The first verification result is used to indicate whether the first transaction information and the second transaction information are consistent.

[0161] The input module 401 is also used to input the first attribute information, the first transaction information and the holiday information into the second model if the first verification result indicates that the first transaction information and the second transaction information are consistent, and to obtain the first time information of the target bond output. The first time information is used to determine the time for calculating the return of the target bond. The second model is obtained by pre-training the model on the attribute information, transaction information, holiday information and time information of the sample bond.

[0162] The verification module 402 is also used to verify the first time information with the second time information and generate a second verification result. The second time information is pre-generated by the bank system based on the first attribute information and the second transaction information of the target bond. The second verification result is used to determine whether the first time information and the second time information are consistent.

[0163] In one possible design of this application embodiment, the data processing device 400 further includes:

[0164] The acquisition module is used to acquire the first attribute information of the target bond;

[0165] The verification module 402 is also used to verify the first attribute information and the second attribute information to generate a third verification result. The second attribute information is the attribute information of the target bond that is pre-stored in the banking system. The third verification result is used to determine whether the first attribute information and the second attribute information are consistent.

[0166] Optional, verification module 402, specifically used for:

[0167] Based on the field mapping relationship and the dictionary mapping relationship, the first attribute information and the second attribute information are aligned. The field mapping relationship is the correspondence between the fields in the first attribute information and the fields in the second attribute information, and the dictionary mapping relationship is the correspondence between the attribute values ​​in the first attribute information and the attribute values ​​in the second attribute information.

[0168] The aligned first attribute information and the aligned second attribute information are checked together to generate a third check result.

[0169] Optionally, the data processing device 400 also includes:

[0170] Input module 401 is used to output the third verification result if the third verification result indicates that the first attribute information and the second attribute information are inconsistent;

[0171] The input module 401 is also used to input the first attribute information into the first model if the third verification result indicates that the first attribute information and the second attribute information are consistent.

[0172] In another possible design of this application embodiment, after verifying the first transaction information and the second transaction information to generate a first verification result, the data processing device 400 further includes:

[0173] The output module is used to output the first verification result if the first verification result indicates that the first transaction information and the second transaction information are inconsistent.

[0174] In another possible design of this application embodiment, after verifying the first time information and the second time information to generate a second verification result, the output module is further configured to:

[0175] If the second verification result indicates that the first time information and the second time information are inconsistent, then the second verification result is output.

[0176] In another possible design of this application embodiment, before inputting the first attribute information of the target bond into the first model and obtaining the output first transaction information of the target bond, the data processing device 400 further includes:

[0177] The acquisition module is also used to acquire the first training set, which includes the attribute information and transaction information of the sample bonds;

[0178] The training module is used to train the model based on the first training set and generate the first model.

[0179] In another possible design of this application embodiment, before inputting the first attribute information of the target bond into the first model and obtaining the first transaction information of the target bond, the acquisition module is further used to acquire a second training set, which includes the attribute information, transaction information, holiday information and time information of the sample bonds.

[0180] The training module is also used to train the model based on the second training set to generate a second model.

[0181] The data processing apparatus provided in this application embodiment can be used to execute the data processing method in any of the above embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0182] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. Additionally, these modules can be fully or partially integrated together, or implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through the integrated logic circuits in the hardware of the processor element or through software instructions.

[0183] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device may include: a processor 501, a memory 502, and computer program instructions stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program instructions, it implements the data processing method provided in any of the foregoing embodiments.

[0184] Optionally, the various components of the electronic device can be connected via a system bus.

[0185] The memory 502 can be a separate memory unit or a memory unit integrated into the processor. The number of processors can be one or more.

[0186] Optionally, the electronic device may also include an interface for interacting with other devices.

[0187] It should be understood that the processor 501 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0188] The system bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. Memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0189] All or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable memory. When the program is executed, it performs the steps of the above method embodiments; and the aforementioned memory (storage medium) includes: read-only memory (ROM), RAM, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof.

[0190] The electronic device provided in this application embodiment can be used to execute the data processing method provided in any of the above method embodiments. Its implementation principle and technical effect are similar, and will not be described again here.

[0191] This application provides a computer-readable storage medium storing computer-executable instructions. When these instructions are executed on a computer, the computer performs the aforementioned data processing method.

[0192] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0193] Optionally, a readable storage medium can be coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Alternatively, the readable storage medium can be an integral part of the processor. Both the processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components within the device.

[0194] This application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and the at least one processor can implement the above-described data processing method when executing the computer program.

[0195] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A data processing method, characterized in that, include: The first attribute information of the target bond is input into the first model to obtain the first transaction information of the target bond. The first attribute information is the information published when the target bond is issued. The first transaction information is used to determine the method of calculating the return of the target bond. The first model is obtained by pre-training the model on the attribute information and transaction information of the sample bond. The first transaction information is compared with the second transaction information to generate a first comparison result. The second transaction information is pre-generated by the bank system based on the first attribute information of the target bond. The first comparison result is used to indicate whether the first transaction information and the second transaction information are consistent. If the first comparison result indicates that the first transaction information and the second transaction information are inconsistent, the second transaction information is modified to the first transaction information. If the first verification result indicates that the first transaction information is consistent with the second transaction information, then the first attribute information, the first transaction information and the holiday information are input into the second model to obtain the first time information of the target bond. The first time information is used to determine the time for calculating the return of the target bond. The second model is obtained by pre-training the model on the attribute information, transaction information, holiday information and time information of the sample bond. The first time information is compared with the second time information to generate a second comparison result. The second time information is pre-generated by the bank system based on the first attribute information of the target bond and the second transaction information. The second comparison result is used to determine whether the first time information and the second time information are consistent. If the second comparison result indicates that the first time information and the second time information are inconsistent, the second time information is modified to the first time information.

2. The method according to claim 1, characterized in that, Before inputting the first attribute information of the target bond into the first model, the method further includes: Obtain the first attribute information of the target bond; The first attribute information and the second attribute information are compared to generate a third comparison result. The second attribute information is the attribute information of the target bond that is pre-stored in the banking system. The third comparison result is used to determine whether the first attribute information and the second attribute information are consistent.

3. The method according to claim 2, characterized in that, The step of verifying the first attribute information and the second attribute information to generate a third verification result includes: Based on the field mapping relationship and the dictionary mapping relationship, the first attribute information and the second attribute information are aligned. The field mapping relationship is the correspondence between the fields in the first attribute information and the fields in the second attribute information, and the dictionary mapping relationship is the correspondence between the attribute values ​​in the first attribute information and the attribute values ​​in the second attribute information. The aligned first attribute information and the aligned second attribute information are checked to generate the third check result.

4. The method according to claim 2 or 3, characterized in that, The method further includes: If the third verification result indicates that the first attribute information and the second attribute information are inconsistent, then the third verification result is output; If the third verification result indicates that the first attribute information and the second attribute information are consistent, then the first attribute information is input into the first model.

5. The method according to any one of claims 1 to 3, characterized in that, After verifying the first transaction information with the second transaction information to generate a first verification result, the method further includes: If the first verification result indicates that the first transaction information and the second transaction information are inconsistent, then the first verification result is output.

6. The method according to any one of claims 1 to 3, characterized in that, After verifying the first time information with the second time information to generate a second verification result, the method further includes: If the second verification result indicates that the first time information and the second time information are inconsistent, then the second verification result is output.

7. The method according to any one of claims 1 to 3, characterized in that, Before inputting the first attribute information of the target bond into the first model and obtaining the output first transaction information of the target bond, the method further includes: Obtain a first training set, which includes the attribute information and transaction information of the sample bonds; The model is trained based on the first training set to generate the first model.

8. The method according to any one of claims 1 to 3, characterized in that, Before inputting the first attribute information of the target bond into the first model and obtaining the output first transaction information of the target bond, the method further includes: Obtain a second training set, which includes the attribute information, transaction information, holiday information, and time information of the sample bonds; The model is trained based on the second training set to generate the second model.

9. A data processing apparatus, characterized in that, include: The input module is used to input the first attribute information of the target bond into the first model and obtain the first transaction information of the target bond output. The first attribute information is the information published when the target bond is issued. The first transaction information is used to determine the method of calculating the return of the target bond. The first model is obtained by pre-training the model on the attribute information and transaction information of the sample bond. The verification module is used to verify the first transaction information and the second transaction information to generate a first verification result. The second transaction information is pre-generated by the bank system based on the first attribute information of the target bond. The first verification result is used to indicate whether the first transaction information and the second transaction information are consistent. If the first verification result indicates that the first transaction information and the second transaction information are inconsistent, the second transaction information is modified to the first transaction information. The input module is further configured to input the first attribute information, the first transaction information, and the holiday information into the second model if the first verification result indicates that the first transaction information is consistent with the second transaction information, and to obtain the first time information of the target bond output. The first time information is used to determine the time for calculating the return of the target bond. The second model is obtained by pre-training the model on the attribute information, transaction information, holiday information, and time information of the sample bond. The verification module is further configured to verify the first time information and the second time information to generate a second verification result. The second time information is pre-generated by the bank system based on the first attribute information of the target bond and the second transaction information. The second verification result is used to determine whether the first time information and the second time information are consistent. If the second verification result indicates that the first time information and the second time information are inconsistent, the second time information is modified to the first time information.

10. An electronic device, comprising: A processor, a memory, and computer program instructions stored in the memory and executable on the processor, characterized in that the processor executes the computer program instructions to implement the data processing method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the data processing method as described in any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it is used to implement the data processing method as described in any one of claims 1 to 8.

Images