Financial core data exception monitoring method and device, equipment and storage medium

Abstract

The invention relates to the technical field of data management, discloses a financial core data anomaly monitoring method, device and equipment and a medium, and aims to solve the problem of low accuracy of automatic data analysis of financial core data anomaly monitoring in the prior art. The target data set comprises a data pair, the data pair comprises an index identifier and an index value of a target index, and the index value is a first calculation factor index value or a second calculation factor index value; on the basis of a preset back test model, according to calculation of the first calculation factor index value and consistency judgment of the first calculation factor index value and the second calculation factor index value, whether the financial core data in the target transaction scene is abnormal or not is judged, so that implicit indexes causing financial core data abnormity are mined from a large amount of complex financial core data; the automatic data analysis accuracy of financial core data anomaly monitoring can be improved, and the method can be applied to the financial field including but not limited to the financial field.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data governance and financial technology, and particularly relates to a financial core data anomaly monitoring method, device, equipment and medium. BACKGROUND

[0002] Financial core data refers to data owned by a financial institution, which is of vital value to the survival, operation, decision-making and competitiveness of the financial institution, and is the most core and valuable asset of the financial institution. The financial core data usually includes financial business data and financial financial data. The financial business data refers to data generated in financial service activities by front-end business transactions, which is derived from various core business processes and different transaction systems of the financial institution, including but not limited to when a vehicle loan is issued to which vehicle customer, loan contract number, amount, interest rate, term, and repayment schedule. The financial financial data refers to data formed by confirming, measuring, recording and summarizing the financial business data according to the enterprise accounting standards and financial regulatory requirements, which is used to reflect the financial position, operating results and cash flow of the enterprise in a specific accounting period, and is used for external reporting and internal management, including but not limited to the total assets, total liabilities and net assets as of the end of the reporting period, and the total amount of vehicle loans and advances.

[0003] As a financial institution, for example, an automobile financial institution, it needs to regularly report operating data, i.e. related financial financial data, to multiple regulatory agencies. The accuracy of the reported data is an absolute requirement for compliance. For example, the accuracy of the loan balance, which is the core cornerstone of regulatory reporting, directly determines the calculation quality of various risk indicators, compliance criteria and policy thresholds, and is related to the overall company compliance. Therefore, ensuring the absolute accuracy of the loan balance data is the primary prerequisite for ensuring the overall data quality of the reported data.

[0004] However, since the financial business data and the financial financial data belong to different stages of data governance and generally belong to different business departments or even systems, for financial core data that exists in multiple sub-transaction scenarios (sub-transaction scenarios are specific manifestations of transaction scenarios at a finer granularity) and needs to interact and integrate between different systems, any abnormal factor can cause the final financial financial data to be abnormal, thereby affecting the accuracy of the reported data. The misalignment of the reported data can have serious consequences. For example, the calculation of the loan balance involves multiple sub-transaction scenarios such as lending, repayment, contract cancellation, repayment cancellation, red correction, excess repayment, early repayment and bad debt cancellation. Each sub-transaction scenario can individually affect the loan balance, and the transactions are not concentrated in one system but interact between multiple systems. As a result, the loan balance inspection logic is abnormally complex, making it difficult to ensure the data quality and accuracy of the loan balance.

[0005] In the prior art, for repayment, loan and other sub-transaction scenarios, there are generally corresponding data risk automatic monitoring based on automatic data analysis, such as automatic monitoring of loan amount anomalies based on corresponding automatic data analysis, automatic monitoring of data anomalies such as a certain account with settled / unallocated external amount, DAAS early settlement state anomaly, DD certain backboard suspected repeated account entry, and the like based on corresponding automatic data analysis. These existing automatic data analysis can effectively monitor data anomalies in the corresponding sub-transaction scenario. Moreover, the reporting frequency of data based on the above data risk automatic monitoring and related financial and financial data such as loan balance is mostly monthly, quarterly, semi-annually, annually, etc. Related personnel responsible for reporting data generally start checking related financial and financial data after running the monthly batch out data. Once it is found that there is a problem with the related financial and financial data, it is generally necessary to call on the relevant personnel of different business departments such as IT, retail credit management, retail customer relationship management, collection litigation, inventory credit management, etc. to intervene in the investigation, and manually investigate the reasons for the loan balance inequality and related financial and financial data anomalies.

[0006] However, the inventors have found that due to the limitations of automatic data analysis of sub-transaction scenarios on the complex data correlation corresponding to the transaction scenario, data anomaly automatic monitoring based on sub-transaction scenarios requires human analysis to identify real anomalies, otherwise false alarms may occur. Therefore, in various sub-transaction scenarios, if accurate and effective automatic data analysis for a certain sub-transaction scenario is missing, the corresponding data anomalies cannot be discovered, which leads to anomalies in the reporting data of related financial and financial data.

[0007] At the same time, the automatic data analysis of financial and financial data lacks overall audit relationship, i.e. the automatic data analysis of comprehensive, closed-loop, and full-link data anomaly monitoring for multiple sub-transaction scenarios. If the effective monitoring of a certain sub-transaction scenario is missing, it cannot further implement corresponding data anomaly monitoring through overall automatic data analysis of the transaction scenario in a timely, rapid and effective manner, and cannot further ensure the accuracy of the global related financial and financial data in the transaction scenario, which leads to inaccurate related reporting data. Moreover, if the related financial and financial data reported has anomalies, it needs to be urgently repaired before the reporting deadline required by the regulator. In this case, manual investigation is time-consuming and labor-intensive, and the efficiency is low.

[0008] In summary, due to the low accuracy of automatic data analysis of financial core data anomaly monitoring, the efficiency and intelligence level of data risk automatic monitoring of financial core data are reduced.

[0009] Therefore, how to improve the accuracy of automatic data analysis of financial core data anomaly monitoring has become a technical problem urgently to be solved in the field of data risk automatic monitoring, data governance and financial technology. SUMMARY

[0010] The application provides a financial core data anomaly monitoring method and device, a computer device and a medium, to solve the problem of low accuracy of automatic data analysis in traditional financial core data anomaly monitoring.

[0011] In a first aspect, a financial core data anomaly monitoring method is provided, which comprises: in response to a task start instruction for financial core data anomaly monitoring in a target transaction scenario, determining a corresponding target data set based on a preset enterprise data analysis platform and according to the target transaction scenario, the target data set comprising data pairs, each data pair comprising an index identifier and an index value corresponding to a target index, the index value being a first calculation factor index value or a second calculation factor index value; determining a preset back testing model corresponding to the target transaction scenario; calculating all the first calculation factor index values based on the preset back testing model, and determining whether the first calculation value obtained by calculation is consistent with the second calculation factor index value; and determining that the financial core data corresponding to the target transaction scenario is abnormal in the case that the first calculation value is not consistent with the second calculation factor index value.

[0012] In a second aspect, a financial core data anomaly monitoring device is provided, which comprises: a first determination module configured to determine a corresponding target data set based on a preset enterprise data analysis platform and according to a target transaction scenario in response to a task start instruction for financial core data anomaly monitoring in the target transaction scenario, the target data set comprising data pairs, each data pair comprising an index identifier and an index value corresponding to a target index, the index value being a first calculation factor index value or a second calculation factor index value; a second determination module configured to determine a preset back testing model corresponding to the target transaction scenario; a first judgment module configured to calculate all the first calculation factor index values based on the preset back testing model, and determine whether the first calculation value obtained by calculation is consistent with the second calculation factor index value; and a first determination module configured to determine that the financial core data corresponding to the target transaction scenario is abnormal in the case that the first calculation value is not consistent with the second calculation factor index value.

[0013] In a third aspect, a computer device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above method when executing the computer program.

[0014] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0015] The scheme realized by the financial core data anomaly monitoring method, device, computer device and storage medium provided by the above-mentioned scheme comprises the following steps: determining a target index and an index value corresponding to the target index according to a target transaction scenario, and performing automatic data analysis according to the index value and a back testing model corresponding to the index value. The target transaction scenario corresponding to the financial core data can be monitored in time, so that the transaction scenario is taken as a process calculation factor of an influence result. On the basis of automatic data analysis of sub-transaction scenario data anomaly monitoring, the complex, deep and implicit correlation between different sub-transaction scenarios contained in the financial core data is fully mined, and automatic data analysis is realized from the perspective of overall inspection relationship of the transaction scenario by means of the correlation, so that the automatic data analysis of the sub-transaction scenario and the automatic data analysis of the overall inspection relationship of the transaction scenario are combined to mine the implicit index leading to the anomaly of the financial core data from a large amount of complex financial core data. More comprehensive, complete and accurate automatic data analysis is realized, the accuracy of automatic data analysis and the quality of data analysis of the financial core data anomaly monitoring are improved, and the accuracy and efficiency of the financial core data anomaly monitoring are improved, so that the financial system can more effectively maintain the accuracy and integrity of the data. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1 The flowchart of the financial core data anomaly monitoring method provided by the embodiments of the present application is shown in the figure. Figure 2 The first sub-flowchart of the financial core data anomaly monitoring method provided by the embodiments of the present application is shown in the figure. Figure 3 The second sub-flowchart of the financial core data anomaly monitoring method provided by the embodiments of the present application is shown in the figure. Figure 4 The schematic block diagram of the financial core data anomaly monitoring device provided by the embodiments of the present application is shown in the figure. Figure 5 The structure diagram of the computer device in an embodiment of the present application is shown in the figure. Figure 6 The structure diagram of the computer device in another embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0018] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0019] It should be understood that, when used in the specification and the appended claims, the terms "comprise" and "include" indicate the presence of described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or sets thereof.

[0020] The embodiments of the present application provide a financial core data anomaly monitoring method, which can be applied to computer devices including but not limited to smart phones, tablet computers, desktop computers, servers, cloud platforms, etc., and adopted when performing financial core data anomaly monitoring in fields including but not limited to data risk automatic monitoring, data governance and financial technology, for example, when performing financial core data anomaly monitoring in financial institutions such as automobile financial institutions and banks.

[0021] In the face of the technical problem of low accuracy of automatic data analysis of financial core data anomaly monitoring in the prior art, the inventors propose the financial core data anomaly monitoring method of the embodiments of the present application, and the core idea of the embodiments of the present application is that: taking a transaction scenario as a process calculation factor affecting a result, and based on the transaction scenario and a specific business process thereof, according to historical data of an unbalanced transaction scenario, clarifying calculation factor indexes and cause factor indexes affecting the result, and according to the calculation factor indexes and the cause factor indexes, constructing a backtest model, based on the backtest model, performing automatic data analysis of financial core data anomaly monitoring, when the backtest model is unbalanced, determining a corresponding pair of cause factor indexes according to a difference value of the backtest model, so as to fully mine complex, deep and implicit correlation relationships between different sub-transaction scenarios contained in the financial core data, thereby mining out implicit indexes causing the financial core data anomaly from complex data, and according to a data blood relation graph corresponding to the cause factor indexes, determining target data causing the anomaly on a dependency relationship path of an upper system, from model imbalance to alarm and simultaneously prompting the anomaly cause, improving the accuracy and data analysis quality of automatic data analysis of financial core data anomaly monitoring, so as to improve the accuracy and efficiency of financial core data anomaly monitoring.

[0022] Some embodiments of the present application will be described in detail with reference to the drawings. In the case of no conflict, the embodiments described below and the features in the embodiments can be combined with each other. It should be noted that the related terms involved in the embodiments of the present application, even if not specifically explained and described, within the scope of understanding, refer to the meanings and contents related to the financial business, for example, the term "transaction scenario" involved in the embodiments of the present application, although not distinguished by "financial business", but as a person skilled in the art can understand, "transaction scenario" refers to the transaction scenario of financial business, other terms in the embodiments of the present application are similar, and will not be repeated.

[0023] Please refer to Figure 1 , Figure 1 The flowchart of the financial core data anomaly monitoring method provided by the embodiments of the present application is shown. The method is applied to an enterprise data analysis platform including but not limited to a data warehouse, a modern data stack, a data lake, a lake-warehouse integration, etc., as shown in Figure 1 The method includes but is not limited to the following steps S11-S15: S11, in response to the task start instruction of the financial core data anomaly monitoring in the target transaction scenario, based on the preset enterprise data analysis platform, and according to the target transaction scenario, determine the corresponding target data set, the target data set contains data pairs, each data pair contains the index identifier and the index value corresponding to the target index, the index value is the first calculation factor index value or the second calculation factor index value.

[0024] Explanatorily, the enterprise data analysis platform is set in advance, that is, the preset enterprise data analysis platform, the preset enterprise data analysis platform represents a unified and integrated technical ecosystem, which aims to collect, store, process, analyze and obtain insights from a large amount of data of an enterprise to support data-driven decision-making. The enterprise data analysis platform can be built based on including but not limited to data warehouse, modern data stack, data lake, lake-warehouse integration, the preset enterprise data analysis platform generally obtains data from multiple heterogeneous data sources, converts the obtained data into a format suitable for analysis according to a predefined data model, loads the converted data into a central data storage, and provides an access interface to the data in the central data storage to support the generation of analysis queries and reports and other data-driven decisions. Exemplarily, in an automobile financial institution, the preset enterprise data analysis platform can interface the financial business data of the retail business line and the inventory business line respectively, for example, based on the data warehouse of the preset enterprise data analysis platform, the data sources can include but are not limited to Ascent core system, WCS collection system, and all financial business data is unified and integrated, based on this, financial financial data is generated, and based on the financial financial data, operation data can be submitted to multiple regulatory agencies.

[0025] According to the above concept and setting, when performing financial core data anomaly monitoring, the financial core data anomaly monitoring is performed in the transaction scenario as a monitoring unit. Based on the business association and business commonality of the transaction scenario and other scene properties of the transaction scenario, as described above, the transaction scenario can be divided into, but not limited to, retail business line transaction scenarios and inventory business line transaction scenarios, and the transaction scenario can be further divided into more coarse-grained or more fine-grained on the basis of the retail business line transaction scenarios and the inventory business line transaction scenarios, which are not limited by the embodiments of the present application. Therefore, the retail business line transaction scenario is taken as a target transaction scenario, or the inventory business line transaction scenario is taken as a target transaction scenario, the target transaction scenario represents an independent monitoring unit of the financial core data anomaly monitoring, and other target transaction scenarios are taken as target transaction scenarios. In response to the task start instruction of the financial core data anomaly monitoring in the target transaction scenario, a corresponding target data set is determined based on the preset enterprise data analysis platform and according to the target transaction scenario, mainly according to the data of the target sub-transaction scenario included in the target transaction scenario. The target data set contains data pairs, each data pair contains an index identifier and an index value corresponding to a target index, and the index value is one of a first calculation factor index value, a second calculation factor index value, and a reason factor index value. It should be noted that the first calculation factor index value, the second calculation factor index value, and the reason factor index value are distinguished according to the purpose of the index value, and are not used to limit the index value. According to the above distinction, the target index can also be distinguished as a first calculation factor index, a second calculation factor index, and a reason factor index. The first calculation factor index and the second calculation factor index represent indexes as calculation factors, and the reason factor index represents a factor index as a reason for the financial core data anomaly. The specific determination of the first calculation factor index, the second calculation factor index, and the reason factor index is derived from the practice application of the target transaction scenario in the current system version and the full-amount historical financial core data, to find out unbalanced transaction cases corresponding to the financial core data anomaly, to judge one by one whether it is a normal transaction business. If not, that is, if it is not a normal transaction business, it means that it is a real anomaly, which meets the monitoring requirements and needs to be alarmed. Then the case characteristics are set as the identified abnormal calculation factor as a reason for monitoring anomaly. If yes, that is, if it is a normal transaction business, it means that it is not an anomaly, and the case characteristics need to be identified as a normal calculation factor and expanded to the backtest model. Then the expanded backtest model is repeatedly practiced in the current data and the historical data until all normal transaction characteristics are identified. Through repeated practice, the backtest model meeting the financial core data monitoring in the target transaction scenario is obtained, so as to establish the backtest model corresponding to each of the retail business line transaction scenario and the inventory business line transaction scenario according to the business logic, data characteristics, and transaction scenario of the financial core data.

[0026] Exemplarily, please refer to Table 1, as shown in Table 1 below, in the retail business line transaction scenario, the data pair represents the (ID value, index value) composed of the existing second column value and the corresponding first column value that can be directly obtained from the preset enterprise data analysis platform data table, the indexes participating in the operation of the index "9" are the first calculation factor indexes, the index "10" participating in the operation of the index "11" is the second calculation factor index, "5a, 7a, 8a, 8b" are the reason factor indexes, and the index "9" is the calculation index.

[0027] Table 1

[0028] Similarly, please refer to Table 2, as shown in Table 2 below, in the inventory business line transaction scenario, the data pair represents the (ID value, index value) composed of the existing second column value and the corresponding first column value that can be directly obtained from the preset enterprise data analysis platform data table, the indexes participating in the operation of the index "6" are the first calculation factor indexes, the index "7" participating in the operation of the index "8" is the second calculation factor index, "2a, 2b, 2c, 4a, 4b, 4c" are the reason factor indexes, and the index "6" is the calculation index.

[0029] Table 2

[0030] S12, according to the target transaction scenario, determine the corresponding preset backtest model.

[0031] Explanatorily, for each transaction scenario, a corresponding backtest model, i.e. a preset backtest model, is set in advance, based on which the transaction scenario and the preset backtest model are matched and adapted, i.e. a mapping relationship, thus, according to the target transaction scenario, the corresponding preset backtest model is determined.

[0032] The preset back testing model represents a model based on back testing. Back testing refers to using historical data to verify how a corresponding model performs in the past and applying the model to subsequent business. In the embodiments of the present application, the preset back testing model refers to finding out the unbalanced transaction scenario cases corresponding to the abnormal historical financial core data for each transaction scenario, judging whether it is normal transaction business one by one, and constructing a corresponding model according to the practical application of the current system version and the full amount of historical financial core data, obtaining the back testing model, and then verifying the back testing model with the historical financial core data to test the performance of the back testing model under the current system version and the current transaction scenario. In the case that the back testing model performs well under the historical financial core data, the back testing model is used to monitor the abnormality of the subsequent financial core data under the current system version and the current transaction scenario, and a balance monitoring is performed on the corresponding financial core data flow. Abnormalities such as system function errors or manual operation errors are discovered in time to ensure normal financial core data transaction and normal system data flow. Please continue to refer to Table 1 and Table 2. In the examples corresponding to Table 1 and Table 2, the preset back testing model corresponding to Table 1 is constructed based on two formulas of indicators “9” and “11”. The formula corresponding to indicator “11” can also be called a back testing formula. The preset back testing model corresponding to Table 2 is constructed based on two formulas of indicators “6” and “8”. The formula corresponding to indicator “8” can also be called a back testing formula. The same applies to other indicators, which will not be described here.

[0033] S13, calculating all the first calculation factor indicator values based on the preset back testing model, and judging whether the first calculation value obtained by calculation is consistent with the second calculation factor indicator value; S14, in the case that the first calculation value is not consistent with the second calculation factor indicator value, determining that the financial core data corresponding to the target transaction scenario is abnormal; S15, in the case that the first calculation value is consistent with the second calculation factor indicator value, determining that the financial core data corresponding to the target transaction scenario is normal.

[0034] Explanatorily, as described above, all the first calculation factor indicator values are calculated based on the preset back testing model, and it is judged whether the first calculation value obtained by calculation is consistent with the second calculation factor indicator value. In the case that the first calculation value is not consistent with the second calculation factor indicator value, it is determined that the financial core data corresponding to the target transaction scenario is abnormal. In the case that the first calculation value is consistent with the second calculation factor indicator value, it is determined that the financial core data corresponding to the target transaction scenario is normal.

[0035] Exemplarily, please continue to refer to Table 1 and Table 2. As described in the example of Table 1, first, the formula corresponding to the index "9" is calculated to obtain a first calculation value, and then the formula corresponding to the index "11" is calculated. In the case that the calculation result of the formula corresponding to the index "11" is not "0", it is determined that the first calculation value is inconsistent with the second calculation factor index value, and then it is determined that the financial core data corresponding to the target transaction scenario is abnormal. In the case that the calculation result of the formula corresponding to the index "11" is "0", it is determined that the first calculation value is consistent with the second calculation factor index value, and then it is determined that the financial core data corresponding to the target transaction scenario is normal. Similarly, as described in the example of Table 2, first, the formula corresponding to the index "6" is calculated to obtain a first calculation value, and then the formula corresponding to the index "8" is calculated. In the case that the calculation result of the formula corresponding to the index "8" is not "0", it is determined that the first calculation value is inconsistent with the second calculation factor index value, and then it is determined that the financial core data corresponding to the target transaction scenario is abnormal. In the case that the calculation result of the formula corresponding to the index "8" is "0", it is determined that the first calculation value is consistent with the second calculation factor index value, and then it is determined that the financial core data corresponding to the target transaction scenario is normal. Thus, based on the backtest idea, according to the transaction scenario and the historical financial core data corresponding thereto, a corresponding backtest model is constructed, and the backtest model is verified, and then the backtest model is used to monitor the subsequent financial core data in the corresponding system version and the corresponding transaction scenario, so as to realize the abnormal monitoring of the subsequent financial core data based on the historical conditions and the historical data.

[0036] In the embodiment of the present application, by determining the corresponding target index and the index value corresponding thereto according to the target transaction scenario, and performing automatic data analysis according to the index value and the backtest model corresponding thereto, the financial core data corresponding to the target transaction scenario can be monitored in time, so as to take the transaction scenario as a process calculation factor affecting the result, on the basis of automatic data analysis of the sub-transaction scenario data abnormal monitoring, the deep and implicit correlation between different sub-transaction scenarios contained in the financial core data is fully mined, and automatic data analysis is realized from the whole transaction scenario inspection relationship by means of the correlation, so as to combine the automatic data analysis of the sub-transaction scenario and the automatic data analysis of the whole transaction scenario inspection relationship, and more comprehensively, completely and accurately perform automatic data analysis, improve the accuracy of automatic data analysis and data analysis quality of the financial core data abnormal monitoring, and improve the accuracy and efficiency of the financial core data abnormal monitoring, so that the financial system can more effectively maintain the accuracy and integrity of the data.

[0037] In an embodiment, based on the preset backtest model, all the first calculation factor index values are calculated, and it is determined whether the first calculation value obtained by calculation is consistent with the second calculation factor index value, comprising: The first calculation value is obtained by calculating all the first calculation factor index values based on a preset first calculation formula. The second calculation value is obtained by calculating the first calculation value and the second calculation factor index value based on a preset second calculation formula. It is determined whether the second calculation value is zero. In the case where the second calculation value is not zero, it is determined that the first calculation value and the second calculation factor index value are inconsistent. In the case where the second calculation value is zero, it is determined that the first calculation value and the second calculation factor index value are consistent.

[0038] Explanatorily, as described above, the first calculation value is obtained by calculating all the first calculation factor index values based on a preset first calculation formula, and the second calculation value is obtained by calculating the first calculation value and the second calculation factor index value based on a preset second calculation formula. Since the second calculation value should be zero under normal circumstances, in the case where the second calculation value is not zero, it is determined that the first calculation value and the second calculation factor index value are inconsistent, and in the case where the second calculation value is zero, it is determined that the first calculation value and the second calculation factor index value are consistent.

[0039] Further, before determining whether the first calculation value calculated based on the preset back testing model is consistent with the second calculation factor index value, at least one of the following is included: The preset first calculation formula is edited based on a preset first formula editing interface in response to a first editing operation of a user. The preset second calculation formula is edited based on a preset second formula editing interface in response to a second editing operation of a user.

[0040] Specifically, with the updating of the version of the automatic data analysis system corresponding to the financial core data anomaly monitoring, the new development and change of the business scenario, and the continuous identification of new anomalies, it is necessary to continuously update and expand the preset back testing model, and continuously improve the applicability and practicality of the preset back testing model. Therefore, the formula editing interface is preset to edit the corresponding formula of the preset back testing model. Thus, the preset first calculation formula is edited based on a preset first formula editing interface in response to a first editing operation of a user, and the preset second calculation formula is edited based on a preset second formula editing interface in response to a second editing operation of a user. The preset first formula editing interface and the preset second formula editing interface can be the same or different, which can improve the flexibility and convenience of updating the preset back testing model, and the target index of the target data set corresponding to the preset back testing model can also be updated accordingly when necessary.

[0041] According to the embodiments of the present application, the automatic data analysis is performed according to the index value and the back test model corresponding to the index value, the financial core data corresponding to the target transaction scenario is monitored in time, the automatic data analysis of the sub-transaction scenario is combined with the automatic data analysis of the relationship between the transaction scenario and the overall inspection, the automatic data analysis is more comprehensive, complete and accurate, and the accuracy of the automatic data analysis of the financial core data abnormal monitoring and the data analysis quality are improved.

[0042] In an embodiment, please refer to Figure 2 , Figure 2 The first sub-process schematic diagram of the financial core data abnormal monitoring method provided by the embodiments of the present application is shown in FIG. 1. As shown in FIG. 1, the index value is also a cause factor index value; after determining that the first calculation value is inconsistent with the second calculation factor index value, the method further includes: Figure 2 S21, determining the value relationship between the second calculation value and the cause factor index value; S22, determining the target cause factor index value according to the value relationship; S23, determining the index identifier corresponding to the target cause factor index value as a target index identifier; S24, determining the target index corresponding to the target index identifier as an abnormal index causing the abnormality of the financial core data.

[0043] ​Explanatorily, a value relationship between the second calculation value and the cause factor index value is determined; according to the value relationship, a target cause factor index value is determined; an index identifier corresponding to the target cause factor index value is determined as a target index identifier; and a target index corresponding to the target index identifier is determined as an abnormal index causing the financial core data abnormality. Please continue to refer to the examples corresponding to Table 1. As shown in Table 1, in the case of normal general transaction, the difference value GAP is 0, and the terms in the formula with ID 9 are all explicit influence factors (i.e., first calculation factor indexes, i.e., normal indexes in the sub-transaction scenario, positive influence factors), which are factors that have been identified to directly have a positive influence on the calculation of the backtest formula in the case of normal transaction, and are factor indexes that have been subjected to automatic monitoring of data abnormality in the sub-transaction scenario and identified as normal data. Based on this, when the difference value GAP is not 0, it is determined whether the GAP is equal to an identified implicit influence factor (i.e., a cause factor index, i.e., a reason index determined to cause abnormality according to the true abnormality of historical financial core data, a reverse influence factor, a negative influence factor). If the difference value GAP is equal to the 5a value, it can be quickly located that the abnormal transaction scenario is cancellation, and the difference is caused by the fact that the cancellation has been submitted but not completed normally. If the difference value GAP is equal to the 7a value, it can be quickly located that the abnormal transaction scenario is interest overpayment, and the difference is caused by the fact that the interest is overpaid, and the system automatically offsets part of the principal payment. If the difference value GAP is equal to the 8a value, it can be quickly located that the abnormal transaction scenario is entry, and the difference is caused by the fact that the customer remits the repayment to the public account of the company, but the manual entry is abnormal. If the difference value GAP is equal to the 8b value, it can be quickly located that the abnormal transaction scenario is allocation, and the difference is caused by the fact that the system automatically allocates the principal, interest, and penalty interest and other fee details, which are inconsistent with the display of the repayment schedule. Therefore, by the inequality of the backtest formula, the difference value GAP is equal to a certain influence calculation factor, which can quickly identify which transaction scenario has an abnormality. Once the abnormality is monitored, IT monitoring alarm can be triggered to quickly notify the relevant parties by email for processing.

[0044] Further, please refer to Figure 3 , Figure 3 The second sub-process schematic diagram of the financial core data abnormality monitoring method provided by the embodiment of the present application is shown in FIG. 4. Figure 3 As shown in FIG. 4, in this embodiment, the value relationship between the second calculation value and the cause factor index value is determined, which includes: S31, determining whether the second calculation value is equal to a single cause factor index value; S32, in the case where the second calculation value is equal to a single cause factor index value, determining the single cause factor index value as a target cause factor index value; S33, in the case that the second calculation value is not equal to a single cause factor indicator value, sequentially judging whether the second calculation value is equal to the sum of n cause factor indicator values, 2≤n≤m, m and n are natural numbers, and m is the number of all cause factor indicator values; S34, in the case that the second calculation value is equal to the sum of n cause factor indicator values, determining the n cause factor indicator values as target cause factor indicator values; S35, in the case that the second calculation value is not equal to the sum of n cause factor indicator values, issuing an alarm of “unknown factor of the financial core data abnormality”.

[0045] Specifically, judging whether the second calculation value is equal to a single cause factor indicator value, in the case that the second calculation value is equal to a single cause factor indicator value, determining the single cause factor indicator value as a target cause factor indicator value, as shown in Table 1 above, if the difference value GAP is equal to the 5a value, the abnormal transaction scenario of the abnormal transaction can be quickly located as cancellation, and the cause of the difference is that the cancellation has been submitted but has not been normally cancelled; if the difference value GAP is equal to the 7a value, the abnormal transaction scenario of the abnormal transaction can be quickly located as interest overpayment; if the difference value GAP is equal to the 8a value, the abnormal transaction scenario of the abnormal transaction can be quickly located as account abnormality; if the difference value GAP is equal to the 8b value, the abnormal transaction scenario of the abnormal transaction can be quickly located as distribution abnormality.

[0046] Further, when none of the single abnormalities meets the comparison, it is checked whether multiple abnormalities occur simultaneously, i.e., whether a composite abnormality scenario occurs, thereby, in the case that the second calculation value is not equal to a single cause factor indicator value, sequentially judging whether the second calculation value is equal to the sum of n cause factor indicator values, 2≤n≤m, m and n are natural numbers, and m is the number of all cause factor indicator values; in the case that the second calculation value is equal to the sum of n cause factor indicator values, determining the n cause factor indicator values as target cause factor indicator values, as shown in Table 1 above, if the difference value GAP is equal to the sum of the 5a value and the 7a value, the abnormal transaction scenario of the abnormal transaction can be quickly located as the simultaneous occurrence of cancellation and interest overpayment, and in the case that the second calculation value is not equal to the sum of n cause factor indicator values, it is indicated that the cause of the financial core data abnormality is not in the identified cause factor indicators, an alarm of “unknown factor of the financial core data abnormality” is issued, manual intervention is required for re-identification, and the corresponding abnormality cannot be identified through the current automatic data analysis, which can timely discover the corresponding abnormality such as system function error or manual operation error. The cause factor indicator represents an identified and determined abnormal error, including but not limited to an uncompleted transaction process, inconsistent data, data loss, data duplication, data tampering, and other identified abnormalities; an unidentified and undetermined abnormal error is prompted as unknown.

[0047] Further, after determining the target indicator corresponding to the target indicator identified by the target indicator as an abnormal indicator causing the financial core data anomaly, the method further comprises: determining a data bloodline graph corresponding to the abnormal indicator; determining a data path and original data corresponding to the abnormal indicator according to the data bloodline graph; determining an original transaction scenario and a transaction subject according to the data path and the original data; performing an alarm of the financial core data anomaly according to the original transaction scenario and the transaction subject.

[0048] Specifically, a data bloodline graph of a cause factor indicator is constructed in advance, which is generally constructed in a data warehouse, a modern data stack, a data lake, a lake-warehouse integrated enterprise data analysis platform, and the like. As shown in Table 1, a data bloodline graph of indicator 5a and a data bloodline graph of indicator 7a are constructed in advance. The data bloodline graph is a “family tree” or a “traceability map” of the cause factor indicator, which clearly shows the source path of the cause factor indicator in a visual graphical manner, answers the question of “where does the cause factor indicator come from, what processing has it undergone, and where does it go”, and enables traceability of the cause factor indicator.

[0049] According to the above concept and setting, after determining the target indicator corresponding to the target indicator identified by the target indicator as an abnormal indicator causing the financial core data anomaly, a data bloodline graph corresponding to the abnormal indicator is determined; a data path and original data corresponding to the abnormal indicator are determined according to the data bloodline graph; an original transaction scenario and a transaction subject are determined according to the data path and the original data; and an alarm of the financial core data anomaly is performed according to the original transaction scenario and the transaction subject, so as to quickly notify the relevant parties for processing.

[0050] The embodiment of the present application compares the second calculation value with the value corresponding to the reason factor index clarified in advance, and then determines the abnormal index causing the abnormality of the financial core data, so as to fully mine the complex, deep and implicit correlation between different sub-transaction scenarios contained in the financial core data, thereby mining the implicit index causing the abnormality of the financial core data from the complex data, and automatically deriving the reason for the abnormality of the financial core data through automatic data analysis, thereby improving the checking efficiency of the reason for the abnormality of the financial core data, especially in combination with the automatic data analysis frequency of the financial core data abnormality monitoring including but not limited to the daily time period, compared with the traditional technology in which the balance data is checked by each financial business department after the monthly settlement, the real and specific transaction scenario at the time of the abnormality of the financial core data can be tracked and restored in time, so as to maintain the financial core data in time, thereby repairing the data in time before the monthly settlement business uses the data, avoiding further expansion of the influence of the abnormality of the financial core data, and more effectively maintaining the accuracy and integrity of the financial core data, thereby improving the efficiency and reliability of the entire system of the financial institution, and improving the automatic monitoring of the data risk of the financial core data, the accuracy, efficiency and intelligent level of automatic data analysis in the field of data governance and financial technology.

[0051] In an embodiment, before the task starting instruction in response to the financial core data abnormality monitoring in the target transaction scenario, further comprising: Based on the user configuration, a time trigger condition and an associated task starting instruction are received and stored, and the task starting instruction is used to start the financial core data abnormality monitoring task in the target transaction scenario; Monitoring system time; In response to the system time meeting the time trigger condition, the task starting instruction is automatically triggered.

[0052] Explanatorily, a timer is set, a time trigger condition and an associated task starting instruction are received and stored according to the timer and based on the user configuration, the task starting instruction is used to start the financial core data abnormality monitoring task in the target transaction scenario; the system time is monitored; in response to the system time meeting the time trigger condition, the task starting instruction is automatically triggered, and the financial core data abnormality monitoring task in the target transaction scenario is automatically executed, which can realize the automatic data analysis of the financial core data abnormality including but not limited to the daily settlement batch monitoring, wherein the daily settlement batch refers to automatically executing the batch processing of the financial core data abnormality monitoring task (batch running) by the computer system at the end of each day (daily settlement) to complete the financial core data abnormality monitoring of the day, which can realize the high frequency and high efficiency of the financial core data abnormality monitoring, and maintain the accuracy of the financial core data in time.

[0053] The embodiment of the present application can configure the time of the financial core data anomaly monitoring according to the needs of the user, improve the time flexibility of the financial core data anomaly monitoring, and can timely perform the automatic data analysis of the financial core data anomaly monitoring compared with the traditional technology that each financial business department only checks the balance data after the monthly settlement, so as to timely maintain the financial core data, repair the data before the monthly settlement business uses the data, avoid further expansion of the influence of the financial core data anomaly, more effectively maintain the accuracy and integrity of the financial core data, and improve the efficiency and reliability of the entire system of the financial institution, so as to improve the automatic monitoring of the data risk of the financial core data, the accuracy of the automatic data analysis, the data analysis efficiency and the intelligent level in the field of data governance and financial technology.

[0054] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0055] In an embodiment, a financial core data anomaly monitoring device is provided, which corresponds to the financial core data anomaly monitoring method in the above embodiment. Please refer to Figure 4 , Figure 4 The financial core data anomaly monitoring device provided by the embodiment of the present application is shown in the schematic block diagram. As Figure 4 shown, the financial core data anomaly monitoring device 40 includes a first determination module 41, a second determination module 42, a first judgment module 43 and a first determination module 44, and the functions of each module are described as follows: The first determination module 41 is configured to respond to the task start instruction of the financial core data anomaly monitoring in the target transaction scenario, determine the corresponding target data set based on the preset enterprise data analysis platform and according to the target transaction scenario, the target data set includes data pairs, each data pair includes the index identifier and the index value corresponding to the target index, and the index value is the first calculation factor index value or the second calculation factor index value; The second determination module 42 is configured to determine the corresponding preset back testing model according to the target transaction scenario; The first judgment module 43 is configured to calculate all the first calculation factor index values based on the preset back testing model, and judge whether the first calculation value obtained by calculation is consistent with the second calculation factor index value; The first determination module 44 is configured to determine that the financial core data corresponding to the target transaction scenario is abnormal in the case that the first calculation value is inconsistent with the second calculation factor index value.

[0056] In an embodiment, the first judging module 43 comprises: a first calculating sub-module, configured to calculate all the first calculating factor index values based on a preset first calculating formula to obtain a first calculating value; a second calculating sub-module, configured to calculate the first calculating value and the second calculating factor index value based on a preset second calculating formula to obtain a second calculating value; a first judging sub-module, configured to judge whether the second calculating value is zero; a first determining sub-module, configured to determine that the first calculating value and the second calculating factor index value are inconsistent in a case where the second calculating value is not zero; a second determining sub-module, configured to determine that the first calculating value and the second calculating factor index value are consistent in a case where the second calculating value is zero.

[0057] In an embodiment, the financial core data anomaly monitoring apparatus 40 further comprises at least one of the following: a first editing module, configured to edit the preset first calculating formula based on a preset first formula editing interface in response to a first editing operation of a user; a second editing module, configured to edit the preset second calculating formula based on a preset second formula editing interface in response to a second editing operation of a user.

[0058] In an embodiment, the index value is also a reason factor index value; the financial core data anomaly monitoring apparatus 40 further comprises: a third determining module, configured to determine a value relationship between the second calculating value and the reason factor index value; a fourth determining module, configured to determine a target reason factor index value according to the value relationship; a fifth determining module, configured to determine an index identifier corresponding to the target reason factor index value as a target index identifier; a sixth determining module, configured to determine a target index corresponding to the target index identifier as an anomaly index causing the financial core data anomaly.

[0059] In an embodiment, the third determining module comprises: a second judging sub-module, configured to judge whether the second calculating value is equal to a single reason factor index value; a first determining sub-module, configured to determine the single reason factor index value as a target reason factor index value in a case where the second calculating value is equal to the single reason factor index value; a third judging submodule, configured to, in a case where the second calculation value is not equal to a single cause factor index value, judge in sequence whether the second calculation value is equal to a sum of n cause factor index values, 2<=n<=m, m and n are natural numbers, and m is a number of all the cause factor index values; a second determining submodule, configured to, in a case where the second calculation value is equal to the sum of the n cause factor index values, determine the n cause factor index values as target cause factor index values; a first issuing submodule, configured to, in a case where the second calculation value is not equal to the sum of the n cause factor index values, issue an alarm of "unknown factors of the financial core data abnormality".

[0060] In an embodiment, the financial core data abnormality monitoring apparatus 40 further includes: a seventh determining module, configured to determine a data bloodline graph corresponding to the abnormal index; an eighth determining module, configured to determine, according to the data bloodline graph, a data path and original data corresponding to the abnormal index; a ninth determining module, configured to determine, according to the data path and the original data, an original transaction scenario and a transaction subject; an alarm module, configured to perform an alarm of the financial core data abnormality according to the original transaction scenario and the transaction subject.

[0061] In an embodiment, the financial core data abnormality monitoring apparatus 40 further includes: a first receiving module, configured to receive and store, based on user configuration, a time trigger condition and an associated task starting instruction, the task starting instruction being used to start a financial core data abnormality monitoring task in a target transaction scenario; a first monitoring module, configured to monitor a system time; a first triggering module, configured to, in response to the system time satisfying the time trigger condition, automatically trigger the task starting instruction.

[0062] Embodiments of the present application provide a financial core data abnormality monitoring apparatus, which can timely monitor the financial core data corresponding to a target transaction scenario by determining corresponding target indexes and index values corresponding to the target indexes according to the target transaction scenario and performing automatic data analysis according to the index values and backtesting models corresponding to the index values, thereby improving the accuracy and efficiency of the financial core data abnormality monitoring, and improving the automatic data analysis accuracy, data analysis efficiency and intelligent level in the field of data risk automatic monitoring of financial core data, data governance and financial technology.

[0063] The specific definitions of the financial core data anomaly monitoring device can refer to the definitions of the financial core data anomaly monitoring method described above, and will not be repeated here. Each module in the above financial core data anomaly monitoring device can be realized by software, hardware and their combination. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor calls and executes the operations corresponding to each module.

[0064] In one embodiment, a computer device is provided, which can be a server, and its internal structure diagram can be as shown in Figure 5 The computer device includes a processor, a memory, a network interface and a database connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the external client through the network connection. The computer program is executed by the processor to implement the functions or steps of the financial core data anomaly monitoring method server side.

[0065] In one embodiment, a computer device is provided, which can be a client, and its internal structure diagram can be as shown in Figure 6 The computer device includes a processor, a memory, a network interface, a display screen and an input device connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the external server through the network connection. The computer program is executed by the processor to implement the functions or steps of the financial core data anomaly monitoring method client side.

[0066] In one embodiment, a computer device is provided, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the steps of the financial core data anomaly monitoring method described in the above embodiments.

[0067] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by the processor to implement the steps of the financial core data anomaly monitoring method described in the above embodiments.

[0068] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiments of each method. Any reference to memory, storage, database or other medium used in each embodiment of the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0069] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0070] The non-company software tools or components appearing in the embodiments of the present application are only exemplarily introduced and do not represent actual use.

[0071] The related data collection in the embodiments of the present application meets the requirements of relevant laws and regulations, such as the Personal Information Protection Law of China, the GDPR (General Data Protection Regulation of the European Union) or other national and regional information security standards.

[0072] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A financial core data anomaly monitoring method, characterized in that, The method comprises the following steps: in response to a task starting instruction for monitoring financial core data abnormity under a target transaction scenario, determining a corresponding target data set based on a preset enterprise data analysis platform and according to the target transaction scenario, the target data set containing data pairs, each data pair containing an index identifier and an index value corresponding to a target index, the index value being a first calculation factor index value or a second calculation factor index value; determining a corresponding preset back testing model according to the target transaction scenario; calculating all the first calculation factor index values based on the preset back testing model, and determining whether the first calculation value obtained by calculation is consistent with the second calculation factor index value; in the case where the first calculation value is not consistent with the second calculation factor index value, determining that the financial core data corresponding to the target transaction scenario is abnormal.

2. The financial core data anomaly monitoring method of claim 1, wherein, calculating all the first calculation factor index values based on the preset back testing model, and determining whether the first calculation value obtained by calculation is consistent with the second calculation factor index value, comprising: calculating all the first calculation factor index values based on a preset first calculation formula to obtain a first calculation value; calculating the first calculation value and the second calculation factor index value based on a preset second calculation formula to obtain a second calculation value; determining whether the second calculation value is zero; in the case where the second calculation value is not zero, determining that the first calculation value is not consistent with the second calculation factor index value; in the case where the second calculation value is zero, determining that the first calculation value is consistent with the second calculation factor index value.

3. The financial core data anomaly monitoring method of claim 2, wherein, Before calculating all the first calculation factor index values based on the preset back testing model, and determining whether the first calculation value obtained by calculation is consistent with the second calculation factor index value, the method further comprises at least one of the following steps: editing the preset first calculation formula based on a preset first formula editing interface in response to a first editing operation of a user; editing the preset second calculation formula based on a preset second formula editing interface in response to a second editing operation of a user.

4. The financial core data abnormality monitoring method according to claim 2 or 3, characterized by, The index value is also a reason factor index value; After determining that the first calculation value is not consistent with the second calculation factor index value, the method further comprises the following steps: determining a value relationship between the second calculation value and the reason factor index value; determining a target reason factor index value according to the value relationship; determining a target index identifier corresponding to the target reason factor index value as the target index identifier; determining a target index corresponding to the target index identifier as an abnormal index causing the financial core data abnormity.

5. The financial core data abnormality monitoring method of claim 4, wherein, Determining a value relationship between the second calculation value and the reason factor index value, comprising: determining whether the second calculation value is equal to a single reason factor index value; in the case where the second calculation value is equal to a single reason factor index value, determining the single reason factor index value as the target reason factor index value; in the case that the second calculated value is not equal to a single cause factor indicator value, judging in turn whether the second calculated value is equal to a sum of n cause factor indicator values, 2≤n≤m, m and n are natural numbers, and m is the number of all cause factor indicator values; in the case that the second calculated value is equal to a sum of n cause factor indicator values, determining the n cause factor indicator values as target cause factor indicator values; in the case that the second calculated value is not equal to a sum of n cause factor indicator values, issuing an alarm of "unknown factor of the financial core data abnormality".

6. The financial core data abnormality monitoring method of claim 4, wherein, after determining the abnormal indicator as the target indicator corresponding to the target indicator identifier, the method further comprises: determining a data bloodline graph corresponding to the abnormal indicator; determining a data path and original data corresponding to the abnormal indicator according to the data bloodline graph; determining an original transaction scenario and a transaction subject according to the data path and the original data; performing an alarm of the financial core data abnormality according to the original transaction scenario and the transaction subject.

7. The financial core data anomaly monitoring method of claim 1, wherein, before responding to a task start instruction of the financial core data abnormality monitoring in the target transaction scenario, the method further comprises: based on user configuration, receiving and storing a time trigger condition and an associated task start instruction, the task start instruction being used to start the task of the financial core data abnormality monitoring in the target transaction scenario; monitoring system time; in response to the system time satisfying the time trigger condition, automatically triggering the task start instruction.

8. A financial core data abnormality monitoring apparatus characterized by comprising: the method comprises: a first determination module, configured to respond to a task start instruction of the financial core data abnormality monitoring in a target transaction scenario, determine a corresponding target data set based on a preset enterprise data analysis platform and according to the target transaction scenario, the target data set containing data pairs, each data pair containing an indicator identifier and an indicator value corresponding to a target indicator, the indicator value being a first calculated factor indicator value or a second calculated factor indicator value; a second determination module, configured to determine a preset back testing model corresponding to the target transaction scenario; a first judgment module, configured to calculate all the first calculated factor indicator values based on the preset back testing model, and judge whether a first calculated value obtained by the calculation is consistent with the second calculated factor indicator value; a first determination module, configured to determine that the financial core data corresponding to the target transaction scenario is abnormal in the case that the first calculated value is not consistent with the second calculated factor indicator value.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, the processor executes the computer program to realize the steps of the financial core data abnormality monitoring method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1-9. the computer program is executed by the processor to realize the steps of the financial core data abnormality monitoring method according to any one of claims 1 to 7.

Images