Financial data risk early warning system and method based on cloud computing

Abstract

The invention belongs to the technical field of financial data, and particularly relates to a financial data risk early warning system and method based on cloud computing, and the system comprises a data storage module, a data acquisition module, a data monitoring module, a data preprocessing module, a risk assessment system, an early warning assessment decision module, a data risk early warning module and a terminal. The data module comprises a cloud database and a local database, the data acquisition module comprises multi-source heterogeneous financial data and at least one data interface used for data entry, and the data monitoring module is used for monitoring abnormal changes of the financial data. And at least one rule engine and at least one data processing engine for realizing data processing based on the rule engine are arranged in the data preprocessing module. According to the invention, financial data risk early warning for most of different service objects can be realized, and future early warning and analysis of data can be realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of financial data, and in particular relates to a financial data risk early warning system and method based on cloud computing. Background Art

[0002] Utilize cloud computing platforms and technologies to collect, store, process and analyze the financial data of enterprises or individuals. By establishing risk assessment models and early warning mechanisms, potential financial risks can be discovered in a timely manner and early warning signals can be issued so that relevant personnel can take appropriate measures to reduce risks.

[0003] Problems with existing technologies: The hardware cost required for calculating large amounts of financial data is relatively high, so cloud storage is often used. However, in terms of risk control and early warning for financial data on the market, it can only achieve superficial financial data monitoring and early warning. Future warnings generated by financial data are only reflected on the surface and are mostly related to experience. The corresponding computing technology mostly relies on the calculation methods of cloud service providers. Targeted adaptation and adjustment are required for different service objects. Summary of the Invention

[0004] The purpose of the present invention is to provide a financial data risk warning system and method based on cloud computing, which can realize financial data risk warning for most different service objects and can realize future warning and analysis of data.

[0005] The technical solutions adopted by the present invention are as follows: A financial data risk early warning system based on cloud computing, comprising: A data storage module, the data module includes a cloud database and a local database; A data acquisition module, comprising multi-source heterogeneous financial data and at least one data interface for data entry; A data monitoring module, which is used to monitor abnormal changes in financial data; A data preprocessing module, wherein the data preprocessing module is internally provided with at least one rule engine and at least one data processing engine that implements data processing based on the rule engine; A risk assessment system comprising a risk assessment rule construction module and at least one risk warning module corresponding to the risk assessment rule, wherein the risk warning module runs at least one warning trigger module based on the risk assessment rule constructed by the risk assessment rule construction module to output risk warning information; An early warning assessment decision module, which performs a dynamic assessment of the risk information according to the dynamic assessment system based on the risk early warning information output by the risk assessment system, and issues a risk notification for the assessed early warning information according to the multi-level assessment model; A data risk warning module, which outputs risk information exceeding a risk threshold based on risk notification; The terminal includes at least one interactive interface.

[0006] A dedicated communication line is provided between the cloud database and the local database. Both the cloud database and the local database are provided with computing devices for data operations. The computing results of the cloud database and the local database are compared. When data differences are found in the calculation results, the early warning method includes the following steps: Both the cloud database and the local database verify the data output by themselves, and cross-validate the data output by the counterpart; According to the verification results, the verification results are output, and the risk threshold is rated according to the verification results to output corresponding early warning information; The output warning information is stored in the data storage module, and the warning information is distributed to at least three ends, one of which is the necessary warning end.

[0007] The abnormal changes include abnormal changes in flow, abnormal changes in historical data, abnormal changes in structure, abnormal changes in trends, and abnormal changes in associations.

[0008] The data preprocessing module includes an underlying rule based on a data change benchmark threshold, and the numerical risk of the financial value change is determined and evaluated based on the underlying rule.

[0009] The risk assessment system constructs a module based on risk assessment rules according to the financial value change assessment results determined by the acquired data preprocessing engine, realizes data comparison, and realizes risk assessment according to the processing method of the data processing engine.

[0010] According to another aspect of an embodiment of the present invention, a financial data risk early warning method based on cloud computing is provided, comprising the following steps: Obtain static and dynamic financial data; Conduct risk assessment of financial data based on the acquired static financial data to output risk warning information; Based on the risk warning information, obtain the influencing factors that generate the warning information, and use data processing methods to analyze the influencing factor data; Obtain factors affecting abnormal data fluctuations; Further process the factors affecting abnormal data fluctuations based on data processing methods, and obtain the corresponding dynamic elements of the corresponding data in real time; Evaluate the impact of factors on data fluctuations based on real-time data acquisition; To generate dynamic impact changes and correlations; In order to realize dynamic early warning assessment of data, risk determination, risk positioning, and risk level assessment and early warning of the judgment results can be realized based on the assessment results.

[0011] The data processing method of the data processing engine comprises the following steps: Obtain financial data and classify and process the financial data; The classified financial data is partitioned into stepped and fixed partitions, wherein the maximum and minimum values of the stepped and fixed partitions refer to the values calculated from the historical data; Obtaining a difference set from the step-fixed partition and the maximum and minimum values, wherein the difference set is an influencing factor affecting the numerical fluctuation of the step-fixed partition; Compare the correlation factors and corresponding correlation data to obtain the factors affecting abnormal data fluctuations.

[0012] The dynamic evaluation method comprises the following steps: Enter dynamically acquired data into the financial data risk warning system one by one; By analyzing each or each group of newly acquired and entered dynamic data, analyze its impact on the entire data model; Based on the impact, located in the system background, the dynamic data is compared with any group of data in the historical data or any data change after removing a group of data in the data model; Based on the impact of dynamic data on the alarm risk level in the financial data risk alarm system, it is used to judge the impact of one or a group of dynamic data on the financial data risk alarm system; Based on the above impacts, the rule system is entered to generate a cloud analysis model to achieve a comparison of the corresponding risk data changes, as well as the corresponding risk level, risk type and risk positioning.

[0013] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, any one of the aforementioned methods is implemented.

[0014] According to yet another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, any one of the aforementioned methods is implemented.

[0015] The technical effects achieved by the present invention are: The present invention realizes corresponding splitting of corresponding financial risk early warning methods, processes and analyzes the split data, and obtains the future trend of the corresponding data through analysis of the data and data operation trends to specify the corresponding strategy.

[0016] The present invention enables more detailed management and monitoring of financial data, and can also adopt differentiated risk management strategies for data sets with different characteristics, thereby improving the system's sensitivity and response speed, helping to identify and respond to potential risks earlier. At the same time, it provides greater flexibility, allowing enterprises to customize risk assessment models according to their own needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural diagram of the financial data risk early warning system of the present invention; Figure 2 It is a schematic diagram of the relationship between the risk assessment system and the early warning assessment decision module in the present invention; Figure 3 It is a flowchart of the financial data risk early warning method in the present invention; Figure 4 It is a schematic diagram of the data processing method of the present invention; Figure 5 It is a flow chart of the data processing method in the present invention; Figure 6 It is a flow chart of the dynamic evaluation method in the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose and advantages of the present invention more clearly understood, the present invention is described in detail below with reference to the following examples. It should be understood that the following text is only used to describe one or more specific embodiments of the present invention and does not strictly limit the scope of protection of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0020] According to an embodiment of the present invention, a method embodiment of a financial data risk warning method based on cloud computing is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0021] like Figure 1 and Figure 2 As shown, a financial data risk early warning system based on cloud computing includes: Data storage module, the data module includes a cloud database and a local database, wherein both the cloud database and the local database are equipped with a computing and analysis system for data computing and analysis, and the cloud database and the local database are connected via a data dedicated line to achieve data synchronization on both ends; A data acquisition module, which includes multi-source heterogeneous financial data and at least one data interface for data entry. The multi-source heterogeneous financial data includes various financial data related to finance, including but not limited to financial flow, warehousing, and equipment records. The data entry method of the data interface includes uploaded data and data generated by the financial data risk early warning system during data processing. The data monitoring module is used to monitor abnormal changes in financial data. The data monitoring module operates in conjunction with the data preprocessing module, risk assessment system, and early warning assessment and decision-making module. It monitors data changes and data output results during the operation of the preprocessing module, risk assessment system, and early warning assessment and decision-making module, and outputs the data through the terminal. It includes a log generation module and transmits the data information after log generation to the data storage module to enable the call and operation analysis of the data preprocessing module, risk assessment system, and early warning assessment and decision-making module in the subsequent use process; A data preprocessing module, which includes at least one rule engine and at least one data processing engine that implements data processing based on the rule engine. The rule engine is used to generate basic rules for data preprocessing, such as normalizing acquired data or setting benchmark values for data comparison based on data variation intervals. Its data rules rely on the experience of technical personnel such as data analysts, as well as the data information and rules accumulated during the operation of the financial data risk early warning system; A risk assessment system is provided with a risk assessment rule construction module and at least one risk warning module corresponding to the risk assessment rule. The risk warning module runs at least one warning trigger module based on the risk assessment rule constructed by the risk assessment rule construction module to output risk warning information. The construction and operation of the risk assessment rule are the same as those in the rule engine construction and operation process. The difference is that the risk assessment rule construction module is used in the risk assessment phase. It is connected with the risk warning module to output the generated risk warning to generate risk warning information. The early warning assessment decision module performs a dynamic assessment of the risk information according to the dynamic assessment system based on the risk warning information output by the risk assessment system, and issues a risk notification for the assessed early warning information according to the multi-level assessment model; Data risk warning module: The data risk warning module outputs risk information that exceeds the risk threshold based on risk notification; The terminal includes at least one interactive interface.

[0022] As an optional embodiment, a dedicated communication line is set up between the cloud database and the local database. Both the cloud database and the local database are equipped with computing devices for data calculations, and a calculation analysis system for data calculation and analysis is run to achieve a comparison of calculation results between the cloud database and the local database.

[0023] Furthermore, when a data discrepancy is found in the calculation results, the early warning method includes the following steps: S101, the cloud database and the local database both verify the data output by themselves, and cross-validate the data output by the corresponding end; S102: Output the verification result according to the verification result, and rate the risk threshold according to the verification result to output corresponding warning information; S103. The outputted warning information is stored in a data storage module, and the warning information is distributed to at least three terminals, one of which is a necessary warning terminal.

[0024] Optionally, to ensure data security and calculation accuracy, encryption is used between both ends to encrypt the data packet. If the data packet is changed after both ends verify the key, an alert is issued.

[0025] Furthermore, the necessary early warning terminal is the highest level early warning terminal, which is used to store and receive all early warning information, and has the highest early warning authority and control authority when receiving a network attack or network fluctuation. Another early warning terminal among the three ends is a terminal distributed among various technicians, and the other end is a terminal device set up in each central server, which is used to coordinate the terminals of various technicians.

[0026] Furthermore, the data monitoring module is used to monitor abnormal changes in financial data, where abnormal changes include abnormal changes in flow, abnormal changes in historical data, abnormal changes in structure, abnormal changes in trends, and abnormal changes in associations.

[0027] Alternatively, abnormal transaction changes refer to unusual activities in bank accounts or transaction flows; For example, a large inflow or outflow of funds in a short period of time, a significant increase or decrease in the amount compared to usual, frequent but small transfers of funds, discrepancies between purchased items and funds, etc. Such anomalies may indicate potential fraud or operational errors.

[0028] Alternatively, historical data anomalies refer to situations where the currently observed data point does not conform to the historical data pattern; For example, this might include a sudden increase or decrease in data, or a reversal of a long-term trend.

[0029] Alternatively, structural anomalies involve changes in the data structure, where the distribution of categorical variables has changed significantly; For example, in sales data, if the proportion of a certain product's sales to total sales suddenly increases or decreases significantly, this may be a structural anomaly. In addition, changes in the data table structure (such as adding or deleting fields) may also be considered a type of structural anomaly.

[0030] Alternatively, an abnormal trend change is a phenomenon in which the general direction of data development over time deviates; For example, a company's profits have been growing steadily in the past few years, but have stagnated or even declined in recent quarters. This trend change is a trend anomaly.

[0031] Alternatively, a correlation anomaly refers to an unexpected change in the relationship between two or more related variables; For example, there is usually a negative correlation between the price and sales volume of a product (sales volume decreases when the price increases), but if this relationship suddenly reverses (sales volume increases when the price increases), this constitutes an abnormal correlation.

[0032] By analyzing the above-mentioned various abnormal changes, it is possible to analyze the corresponding changes or data anomalies in the financial data and implement risk warning.

[0033] As an optional embodiment, the data preprocessing module includes an underlying rule based on a data change benchmark threshold, and the numerical risk of the financial value change is determined and evaluated based on the underlying rule.

[0034] Optionally, the data preprocessing module can not only clean the data and prepare the original data to facilitate the subsequent analysis and use of the data, but also realize the preliminary evaluation of the data through rules and algorithms, and transmit the data to the risk assessment system through data preprocessing for further evaluation of the data.

[0035] Among them, the data change benchmark threshold is to set one or a group of standard values, which can be a fixed value, a percentage or a dynamic value obtained based on historical data analysis, to measure whether the change in financial data exceeds the normal range. For example, if a company's monthly expenditure usually fluctuates no more than 5%, then 5% can be used as a benchmark threshold. When the actual expenditure changes by more than this ratio, the system will mark it as abnormal. In addition, for the corresponding data, it can use the data acquisition module to specially mark the data that has an impact. Taking the expenditure as an example, if a large amount of marketing, procurement, donations, etc. is incurred this month, the above data will be excluded.

[0036] The underlying rules are specifically applied as follows: The underlying rules are based on the above benchmark thresholds and are mainly used to assess the risk level of changes in financial values. Specifically, they include the following steps: S201. Calculate the rate of change between the financial value and the value of the previous period using the following formula: : in, and Represent the new and old financial values respectively; S202, the calculated Compare with the pre-set baseline threshold. If the threshold is exceeded, the change is considered to have a certain risk and its severity needs to be further assessed; S203. Risks are graded based on the extent to which the rate of change exceeds the baseline threshold. For example, a slight excess is marked as low risk, while a significant excess is marked as high risk. This helps companies prioritize the most urgent issues. S204: After the risk level is determined, corresponding warning information is generated and sent to the corresponding personnel or terminal.

[0037] As an optional embodiment, refer to the attached Figure 2 ,The risk assessment system builds a module based on the ,assessment results of the financial numerical changes determined by the ,data preprocessing engine, and builds a module based on the risk ,assessment of the data comparison, and the data processing engine ,processing method to achieve risk assessment.

[0038] Furthermore, the difference between the risk assessment system and the data preprocessing module is that the data preprocessing method is only applicable to preliminary data warning and data analysis, while the risk assessment system is a deep analysis tool that relies on the data information provided in the preprocessing stage, and combines static data and dynamic data to further realize data analysis, and uses algorithms or models to realize risk assessment.

[0039] Furthermore, the risk assessment rule construction module builds a series of risk assessment rules based on historical data, industry standards, and internal corporate policies. The rules include static or dynamic values. For anomaly detection, the Z-Score formula is used to set thresholds: ; Where X is a specific financial value, and are the sample mean and standard deviation, respectively.

[0040] Based on the above, if the data change rate exceeds the set threshold, an early warning will be triggered.

[0041] Furthermore, based on the above risk assessment rules, when specific conditions are met, the early warning module will generate risk warning information, which involves calculating a comprehensive risk score R, combining the two dimensions of possibility (P) and impact (I): R = P × I.

[0042] In addition, the financial data processing method used in the financial data processing process, in addition to being used for the above-mentioned data processing, can also be used in the branch data or sub-data of the above-mentioned data to assess risks. For example, in the process of evaluating the total financial data, the data processing method can also be used and applied to the expenditure flow, income flow, and sub-data such as expenditure flow or income flow in the total financial data. The above-mentioned processing method is under great computing pressure locally, and the data processing is achieved by uploading the data to the cloud and deploying the computing method in the cloud.

[0043] Please refer to Figure 3 As shown, a financial data risk early warning method based on cloud computing includes the following steps: S1. Obtain static and dynamic financial data; S2. Conduct risk assessment of financial data based on the acquired static financial data to output risk warning information; S3. Based on the risk warning information, obtain the influencing factors that generate the warning information, and use data processing methods to analyze the influencing factor data; S4. Obtain the factors affecting abnormal data fluctuations; S5. Further processing of factors affecting abnormal data fluctuations based on data processing methods, and obtaining corresponding dynamic elements of the corresponding data in real time; S6. Evaluate the impact of factors on data fluctuations based on factors obtained in real time; S7, to generate dynamic impact changes and correlations; S8, to achieve dynamic early warning assessment of data, and based on the assessment results, to achieve risk determination, risk positioning, and risk level assessment and early warning of the judgment results According to step S1, the static financial data includes but is not limited to fixed assets, equipment information, factory information, etc., and the dynamic financial data includes but is not limited to warehouse information, sales data, production data, etc.

[0044] In steps S2 to S4, a benchmark risk assessment database is set up based on the vigilant financial data. For example, if fixed assets suffer losses or abnormal fixed asset transfers due to market changes, natural disasters and other factors, risk information is output, and factors affecting abnormal fluctuations are obtained to further analyze the generated risk information.

[0045] In step S5, during the processing and analysis of the above data, dynamic factors are obtained in real time, and the corresponding influencing factors may include weather reasons, market reasons, raw material price fluctuations, etc., to obtain the dynamic factors of the corresponding data, such as the income and expenditure accounts in the financial data obtained by the above influencing factors, as well as the corresponding data for the same period or previous periods.

[0046] Based on step S6, a dynamic impact association set is generated, a corresponding impact association database is established, and association is established for corresponding data.

[0047] According to step S8, an early warning is issued for the above-mentioned abnormal data, and the early warning information is evaluated. According to the evaluation results and based on the risk assessment, the factors that have the greatest impact on the abnormal data are obtained, thereby realizing the judgment, positioning and risk level of the influencing factors, and outputting the early warning information.

[0048] As an optional embodiment, refer to the attached Figure 4 and Figure 5 , the data processing method of the data processing engine includes the following steps: S11. Obtain financial data and classify the financial data; S12. Perform step-by-step partitioning on the classified financial data, with the maximum and minimum values of the step-by-step partitions referring to values calculated from historical data; S13, obtaining a difference set from the step-fixed partition and the maximum and minimum values, where the difference set is an influencing factor affecting the numerical fluctuation of the step-fixed partition; S14. Compare the correlation factors and the corresponding correlation data to obtain the factors affecting abnormal data fluctuations.

[0049] Please refer to further Figure 4The financial data is first classified and processed, and then the ladder fixed grid partition is applied to each category, and the ladder fixed grid partition is subdivided. As shown in the figure, it is divided into a, b, c, and d partitions. The sum of multiple partitions is 100%. If further analysis is required, the above method can be used to process each partition a, b, c, and d separately to improve the accuracy of data analysis. Through subdivision, more subtle changes in the financial data can be captured, which are ignored in a rougher analysis. Moreover, through further analysis of the a, b, c, and d partitions, the proportion of the impact of each factor in the a, b, c, and d partitions on the financial data can be obtained, thereby obtaining the weight value of each a, b, c, and d partition, expressed as a percentage.

[0050] Furthermore, different risk management strategies can be applied to different sub-partitions according to their characteristics.

[0051] For example, for partitions with greater volatility (such as zone B), a higher alert level can be set; while for relatively stable partitions (such as zone A), a more relaxed monitoring strategy can be adopted, thereby providing more accurate strategies and precise response strategies for financial data management.

[0052] Furthermore, by using stepped partitioning, the ability to use more detailed partitions allows the system to respond to potential risks more quickly, as even small but persistent anomalies can be detected in a timely manner.

[0053] Furthermore, a large interval of ladder fixed partition is further divided into four small partitions a, b, c, and d, each of which has its own specific maximum value. and minimum value (i=a,b,c,d), define the partition function: ; in, Indicates the The labels of each sub-partition, and is the boundary value of each sub-partition; Based on the above, we can analyze the fluctuation factors by difference set: To further identify factors that influence numerical fluctuations, the difference is calculated within each sub-partition: ; Represented as each subpartition A set of data points that are within their normal range.

[0054] When applying risk assessment rules, adjust thresholds or weights based on different sub-partitions; For example, a lower trigger threshold could be set in a high volatility area (e.g., area b), while a higher threshold could be used in a low volatility area (e.g., area a): ; in, is the weight set according to the characteristics of the sub-partition, and are the mean and standard deviation of the samples in the subpartition respectively.

[0055] Based on the above process, more detailed management and monitoring of financial data can be achieved, and differentiated risk management strategies can be adopted for data sets with different characteristics, which improves the sensitivity and response speed of the system, helps to identify and respond to potential risks earlier, and at the same time provides greater flexibility, allowing enterprises to customize risk assessment models according to their own needs.

[0056] As an optional embodiment, refer to the attached Figure 6 ,The dynamic evaluation method includes the following steps: S21. Enter the dynamically acquired data into the financial data risk warning system one by one; S22. Analyze the impact of each or each group of newly acquired and entered dynamic data on the entire data model; S23, based on the impact, located in the system background, by comparing the dynamic data with any group of data in the historical data or any data change after removing a group of data in the data model; S24, based on the impact of the dynamic data on the warning risk level in the financial data risk warning system, used to determine the impact of one or a group of dynamic data on the financial data risk warning system; S25. Based on the above impacts, the rules are entered into the system to generate a cloud analysis model to compare the changes in the corresponding risk data, as well as the corresponding risk levels, risk types, and risk positioning.

[0057] Through the above method, when processing any kind of financial risk warning, the corresponding financial risk warning method can be split accordingly, and the split data can be processed and analyzed. By analyzing the data and the data operation trend, the future trend of the corresponding data can be obtained to specify the corresponding strategy.

[0058] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0059] According to another aspect of an embodiment of the present invention, an electronic device is provided. The electronic device includes a memory and a processor; the memory is used to store programs; and the processor executes the programs to implement any one of the aforementioned methods.

[0060] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The storage medium stores a computer program. When the computer program is executed by a processor, any one of the aforementioned methods is implemented.

[0061] According to yet another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, which implements any of the aforementioned methods when executed by a processor.

[0062] The foregoing is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art may make various improvements and modifications without departing from the principles of the present invention, and such improvements and modifications are also within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained herein shall, unless otherwise specified or limited, be implemented in accordance with conventional means in the art.

Claims

1. A financial data risk early warning system based on cloud computing, characterized in that: include: A data storage module, the data module includes a cloud database and a local database; A data acquisition module, comprising multi-source heterogeneous financial data and at least one data interface for data entry; A data monitoring module, which is used to monitor abnormal changes in financial data; A data preprocessing module, wherein the data preprocessing module is internally provided with at least one rule engine and at least one data processing engine that implements data processing based on the rule engine; A risk assessment system comprising a risk assessment rule construction module and at least one risk warning module corresponding to the risk assessment rule, wherein the risk warning module runs at least one warning trigger module based on the risk assessment rule constructed by the risk assessment rule construction module to output risk warning information; An early warning assessment decision module, which performs a dynamic assessment of the risk information according to the dynamic assessment system based on the risk early warning information output by the risk assessment system, and issues a risk notification for the assessed early warning information according to the multi-level assessment model; A data risk warning module, which outputs risk information exceeding a risk threshold based on risk notification; The terminal includes at least one interactive interface.

2. The cloud computing-based financial data risk early warning system according to claim 1, characterized in that: A dedicated communication line is provided between the cloud database and the local database. Both the cloud database and the local database are provided with computing devices for data operations. The computing results of the cloud database and the local database are compared. When data differences are found in the calculation results, the early warning method includes the following steps: Both the cloud database and the local database verify the data output by themselves, and cross-validate the data output by the counterpart; According to the verification results, the verification results are output, and the risk threshold is rated according to the verification results to output corresponding early warning information; The output warning information is stored in the data storage module, and the warning information is distributed to at least three ends, one of which is the necessary warning end.

3. The cloud computing-based financial data risk early warning system according to claim 1, characterized in that: The abnormal changes include abnormal changes in flow, abnormal changes in historical data, abnormal changes in structure, abnormal changes in trends, and abnormal changes in associations.

4. The cloud computing-based financial data risk early warning system according to claim 1, characterized in that: The data preprocessing module includes an underlying rule based on a data change benchmark threshold, and determines the numerical risk of the financial value change based on the underlying rule for evaluation; 5. The cloud computing-based financial data risk early warning system according to claim 1, characterized in that: The risk assessment system constructs a module based on risk assessment rules according to the financial value change assessment results determined by the acquired data preprocessing engine, realizes data comparison, and realizes risk assessment according to the processing method of the data processing engine.

6. A financial data risk early warning method based on cloud computing, using the financial data risk early warning system according to any one of claims 1 to 5, characterized in that: The steps include: Obtain static and dynamic financial data; Conduct risk assessment of financial data based on the acquired static financial data to output risk warning information; Based on the risk warning information, obtain the influencing factors that generate the warning information, and use data processing methods to analyze the influencing factor data; Obtain factors affecting abnormal data fluctuations; Further process the factors affecting abnormal data fluctuations based on data processing methods, and obtain the corresponding dynamic elements of the corresponding data in real time; Evaluate the impact of factors on data fluctuations based on real-time data acquisition; To generate dynamic impact changes and correlations; In order to realize dynamic early warning assessment of data, risk determination, risk positioning, and risk level assessment and early warning of the judgment results can be realized based on the assessment results.

7. The financial data risk early warning method based on cloud computing according to claim 6, characterized in that: The data processing method of the data processing engine comprises the following steps: Obtain financial data and classify and process the financial data; The classified financial data is partitioned into stepped and fixed partitions, wherein the maximum and minimum values of the stepped and fixed partitions refer to the values calculated from the historical data; Obtaining a difference set from the step-fixed partition and the maximum and minimum values, wherein the difference set is an influencing factor affecting the numerical fluctuation of the step-fixed partition; Compare the correlation factors and corresponding correlation data to obtain the factors affecting abnormal data fluctuations.

8. The financial data risk early warning method based on cloud computing according to claim 1, characterized in that: The dynamic evaluation method comprises the following steps: Enter dynamically acquired data into the financial data risk warning system one by one; By analyzing each or each group of newly acquired and entered dynamic data, analyze its impact on the entire data model; Based on the impact, located in the system background, the dynamic data is compared with any group of data in the historical data or any data change after removing a group of data in the data model; Based on the impact of dynamic data on the alarm risk level in the financial data risk alarm system, it is used to judge the impact of one or a group of dynamic data on the financial data risk alarm system; Based on the above impacts, the rule system is entered to generate a cloud analysis model to achieve a comparison of the corresponding risk data changes, as well as the corresponding risk level, risk type and risk positioning.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 6 to 8 is implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 6 to 8 is implemented.

Images