Data early warning method and device, electronic equipment and computer storage medium

Abstract

The invention provides a data early warning method and device, electronic equipment and a computer storage medium, and can be applied to the technical field of big data and financial science and technology. The method comprises the steps that multiple data groups are determined according to target financial data in a temporary data table, the target financial data comprise multiple pieces of financial data subjected to authenticity inspection, and each data group comprises multiple pieces of financial data of at least one risk factor; according to the historical statistical data, single-day inspection data is determined, and the single-day inspection data represents the probability that qualification inspection of the multiple pieces of financial data in a single day is passed; a first inspection result is determined according to the single-day inspection data and a target number and a time span corresponding to each data group, the target number represents the number of the financial data whose authenticity inspection is passed in the data group, and the time span represents the time span of multiple pieces of financial data in the data group; and generating early warning information for the data packet under the condition that the first inspection result is not passed.

Description

Technical Field

[0001] The present disclosure relates to the field of big data and financial technology, and specifically to a data early warning method, device, electronic device and computer storage medium, device, equipment, medium and program product. Background Art

[0002] With the continuous development of computer technology, the financial data of the banking industry has also increased significantly. Banks can use a variety of models or measurement methods to test a large amount of financial data to determine the authenticity and risk of the data.

[0003] After verifying the financial data, banks can identify which risk factors have a significant impact on their business, thereby developing more targeted risk management strategies. Secondly, by verifying the eligibility of risk factors, banks can ensure the accuracy and effectiveness of the models used internally, thereby improving the overall risk management level.

[0004] At present, banks conduct financial data inspections at fixed times and under the conditions of meeting the risk factor qualification test (RFET). This inspection method can only be used to remedy obvious errors in the regular inspection results. Inspection result problems caused by missing data sources, system or program problems cannot be handled in advance, resulting in low inspection efficiency. Summary of the invention

[0005] In view of the above problems, the present disclosure provides a data early warning method, device, electronic device and computer storage medium.

[0006] According to a first aspect of the present disclosure, a data early warning method is provided, comprising: determining a plurality of data groups according to target financial data in a temporary data table, wherein the target financial data comprises a plurality of financial data that have been verified for authenticity, and each data group comprises a plurality of financial data of at least one risk factor; determining single-day verification data according to historical statistical data, wherein the single-day verification data represents the probability that the qualification test of the plurality of financial data in a single day is passed; determining a first verification result according to the single-day verification data, a target number and a time span corresponding to each data group, wherein the target number represents the number of financial data that have passed the authenticity test in the data group, and the time span represents the time span of the plurality of financial data in the data group; and generating early warning information for the data group when the first verification result is a failure.

[0007] According to an embodiment of the present disclosure, a single-day inspection data is determined based on historical statistical data, including: determining sampling parameters based on historical statistical data; generating a target statistical array based on the sampling parameters, wherein the target statistical array includes a preset number of inspection values, and the ratio of the number of inspection values ​​that pass the authenticity test to the preset number is equal to the sampling parameters; determining a first inspection probability of passing each inspection standard in the qualification test and a second inspection probability of simultaneously passing multiple inspection standards in the qualification test based on the target statistical array; and determining the single-day inspection data based on the multiple first inspection probabilities and the second inspection probabilities.

[0008] According to an embodiment of the present disclosure, the method also includes: when the single-day inspection data is less than or equal to the first threshold, determining the second inspection result as failed and generating early warning information; when the single-day inspection data is greater than the first threshold, determining the second inspection result as passed, and determining the first inspection result based on the single-day inspection data, the target number corresponding to each data group, and the time span.

[0009] According to an embodiment of the present disclosure, determining a first inspection result based on single-day inspection data, a target quantity and a time span corresponding to each data group includes: calculating the standard deviation of the data group and the product between the single-day inspection data and the time span based on the single-day inspection data and the time span; determining a calculated value characterizing the degree of dispersion of multiple financial data within the data group based on the difference between the target quantity and the product, and the standard deviation; and determining the first inspection result based on a comparison result of the calculated value with a second threshold.

[0010] According to an embodiment of the present disclosure, the method also includes: determining a count dispersion value characterizing the data grouping based on sampling parameters, a time span and a target number; determining a third inspection result based on a comparison result between the count dispersion value and a third threshold; and when the third inspection result is passed, determining the first inspection result based on the target number and time span corresponding to each data group based on the single-day inspection data.

[0011] According to an embodiment of the present disclosure, before determining multiple data groups based on the target financial data in the temporary data table, it also includes: calling a program script to load the target financial data from a preset data source to the temporary data table; determining the inspection parameters of the target financial data based on the temporary data table; determining a fourth inspection result of the target financial data based on the inspection parameters; and generating early warning information for the data grouping based on the inspection parameters when the fourth inspection result is failure.

[0012] According to an embodiment of the present disclosure, the inspection parameters include the data volume and / or data acquisition time of the target financial data; determining the fourth inspection result of the target financial data based on the inspection parameters includes: determining the fourth inspection result based on a comparison result between the data volume and the historical data volume, wherein the historical data volume is the average data volume of the financial data acquired each time within a preset time period; and / or determining the fourth inspection result based on a comparison result between the data acquisition time and the current time.

[0013] According to an embodiment of the present disclosure, multiple data groups are determined based on target financial data in a temporary data table, including: obtaining a mapping table between risk factors and data groups from a database; and dividing the target financial data into multiple data groups based on the mapping table.

[0014] A second aspect of the present disclosure provides a data early warning device, characterized in that the device includes: a first determination module, used to determine multiple data groups based on target financial data in a temporary data table, wherein the target financial data includes multiple financial data that have been verified for authenticity, and each data group includes multiple financial data of at least one risk factor; a second determination module, used to determine single-day verification data based on historical statistical data, wherein the single-day verification data represents the probability that the qualification inspection of multiple financial data in a single day is passed; a third determination module, used to determine a first inspection result based on the single-day verification data, a target number and a time span corresponding to each data group, wherein the target number represents the number of financial data that have passed the authenticity inspection in the data group, and the time span represents the time span of multiple financial data in the data group; and an early warning module, used to generate early warning information for the data group when the first inspection result is not passed.

[0015] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0016] The fourth aspect of the present disclosure further provides a computer-readable storage medium having a computer program or instructions stored thereon, which implements the steps of the above method when the above computer program or instructions are executed by a processor.

[0017] The fifth aspect of the present disclosure further provides a computer program product, including a computer program or instructions, which implement the steps of the above method when the above computer program or instructions are executed by a processor.

[0018] In an embodiment of the present disclosure, multiple data groups are determined according to target financial data in a temporary data table, wherein the target financial data includes multiple financial data that have been verified for authenticity, and each data group includes multiple financial data of at least one risk factor; single-day verification data are determined according to historical statistical data, wherein the single-day verification data represents the probability that the qualification inspection of multiple financial data in a single day is passed; a first inspection result is determined according to the single-day verification data, the target number and the time span corresponding to each data group, wherein the target number represents the number of financial data that have passed the authenticity inspection in the data group, and the time span represents the time span of multiple financial data in the data group; and when the first inspection result is not passed, early warning information for the data group is generated. Through the above embodiments, the present disclosure can at least avoid the technical problem of low inspection efficiency caused by only performing procedural verification when an error occurs in the qualification inspection and failing to perform data early warning, and by performing pre-inspection at each stage of data acquisition, procedural problems such as missing data sources, errors or system errors can be detected in advance, thereby achieving the technical effect of improving inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above contents and other purposes, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0020] Figure 1 The application scenario diagram of the data early warning method and device according to the embodiment of the present disclosure is schematically shown;

[0021] Figure 2 A flowchart of a data early warning method according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 3 The flowchart of the method for determining single-day inspection data according to an embodiment of the present disclosure is schematically shown.

[0023] Figure 4 The flowchart of the method for determining the fourth inspection result according to the embodiment of the present disclosure is schematically shown.

[0024] Figure 5 A schematic diagram of a data early warning method scenario according to a specific embodiment of the present disclosure is schematically shown.

[0025] Figure 6 A schematic diagram of a structure of a data early warning device according to an embodiment of the present disclosure is shown; and

[0026] Figure 7 A block diagram of an electronic device suitable for implementing a data early warning method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0028] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0029] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0030] When using expressions such as "at least one of A, B, and C, etc.", they should generally be interpreted according to the meaning of the expression commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0031] It should be noted that the data warning method and device disclosed herein can be used for processing financial data in the field of financial technology, and can also be used for processing financial data in any field other than the field of financial technology. The application field of the data warning method and device disclosed herein is not limited.

[0032] In the technical solution of the present disclosure, the user information (including but not limited to user personal information, user image information, user device information, such as location information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] In the scenario of using personal information for automated decision-making, the methods, devices, and systems provided by the embodiments of the present disclosure provide users with corresponding operation portals for users to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered. The expression "automated decision-making" here refers to the activity of automatically analyzing and evaluating a person's behavioral habits, interests and hobbies, or economic, health, credit status, etc. through computer programs, and making decisions. The expression "expert decision-making" here refers to the activity of making decisions by people who specialize in a certain field, have specialized experience, knowledge and skills, and have reached a certain level of professionalism.

[0034] The risk factor qualification test includes two parts: authenticity test and qualification test. The existing technical process lacks the predictive warning function for authenticity test and qualification test. During the qualification test, when the data source is missing or wrong or there is a problem with the program in the system, resulting in obvious errors in the final qualification test results, it is difficult to conduct relevant procedural monitoring and early warning.

[0035] In order to at least partially solve the above technical problems, the present disclosure provides a data early warning method, including: determining multiple data groups based on target financial data in a temporary data table, wherein the target financial data includes multiple financial data that have been verified for authenticity, and each data group includes multiple financial data of at least one risk factor; determining single-day verification data based on historical statistical data, wherein the single-day verification data represents the probability that the qualification test of multiple financial data in a single day is passed; determining a first inspection result based on the single-day verification data, a target number and a time span corresponding to each data group, wherein the target number represents the number of financial data that have passed the authenticity test in the data group, and the time span represents the time span of multiple financial data in the data group; and generating early warning information for the data group when the first inspection result is failure.

[0036] Figure 1 The application scenario diagram of the data early warning method and device according to the embodiment of the present disclosure is schematically shown.

[0037] like Figure 1 As shown, the application scenario 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or optical fiber cables, etc.

[0038] The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0039] The first terminal device 101, the second terminal device 102, and the third terminal device 103 may be various electronic devices having display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0040] The server 105 may be a server that provides various services, such as a background management server (only as an example) that provides support for websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103. The background management server may analyze and process the received data such as user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal device.

[0041] It should be noted that the data early warning method provided in the embodiment of the present disclosure can generally be executed by the server 105. Accordingly, the data early warning device provided in the embodiment of the present disclosure can generally be set in the server 105. The data early warning method provided in the embodiment of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105. Correspondingly, the data early warning device provided in the embodiment of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the first terminal device 101, the second terminal device 102, the third terminal device 103 and / or the server 105.

[0042] For example, the server 105 can determine multiple data groups based on the target financial data in the temporary data table; determine the single-day inspection data based on the historical statistical data; determine the first inspection result based on the single-day inspection data, the target quantity and time span corresponding to each data group, and generate warning information for the data group when the first inspection result is not passed. Afterwards, the server 105 can send the warning information to one of the first terminal device 101, the second terminal device 102, and the third terminal device 103. The user can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to view the warning information.

[0043] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0044] The following will be based on Figure 1 The scene described by Figure 2~Figure 6 The data early warning method of the disclosed embodiment is described in detail.

[0045] Figure 2 The flowchart of the data early warning method according to the embodiment of the present disclosure is schematically shown. Figure 2 As shown, the data early warning method 200 of this embodiment includes operations S210 to S240.

[0046] In operation S210, a plurality of data groups are determined according to target financial data in the temporary data table.

[0047] According to an embodiment of the present disclosure, a temporary data table is a way of storing data in the current system after obtaining target financial data from a preset data source. Specifically, the target financial data can be obtained from the data source through an interface, and a temporary data table is created in the current system to store the obtained target financial data. For example, the target financial data can be obtained from externally purchased financial market data or a bank's internal data lake.

[0048] According to an embodiment of the present disclosure, the data structure of the temporary data table may be a variety of data structures, such as data structures applicable to relational databases and non-relational databases.

[0049] According to an embodiment of the present disclosure, the target financial data includes a plurality of financial data that have been verified for authenticity. The target financial data obtained from the preset data source may be data that has been verified for authenticity in batches.

[0050] In one embodiment, the authenticity-verified financial data refers to data whose authenticity has been verified, and the verification results include passed and failed.

[0051] According to an embodiment of the present disclosure, after acquiring target financial data, multiple target financial data are grouped to obtain multiple data groups. Each data group includes multiple financial data of at least one risk factor. Risk factors include but are not limited to the expiration date of a financial product, the exercise date of a financial product, the execution price of a financial product, etc.

[0052] For example, financial data can be price data of financial products. If there is a risk factor in the entire data group whose real price can be obtained on a certain day, the real price of the risk factor on that day is recorded as 1; if any risk factor in the entire data group cannot obtain a real price on a certain day, the real price count of the risk factor on that day is 0.

[0053] In operation S220, single-day inspection data is determined based on historical statistical data.

[0054] According to an embodiment of the present disclosure, historical statistical data refers to data obtained by processing historical financial data acquired before target financial data and then performing statistics on the historical financial data. For example, the historical statistical data may be the number of financial data that have passed the authenticity check in the historical financial data, the total amount of historical financial data, or data calculated based on the above data.

[0055] According to an embodiment of the present disclosure, the single-day test data represents the probability of passing the qualification test of multiple financial data in a single day. The qualification test is to predict whether multiple financial data can pass the qualification test in the risk factor qualification test in a single day. The qualification test has a predetermined test standard.

[0056] According to the embodiments of the present disclosure, since the historical statistical data is calculated using historical financial data within a longer historical time span, the single-day inspection data predicted based on the historical statistical data is not easily affected by the fluctuation of the financial data of a certain day or other factors, and the predicted single-day inspection data can be used to perform a single-day qualification inspection subsequently.

[0057] In operation S230, a first inspection result is determined according to the single-day inspection data, the target quantity corresponding to each data group, and the time span.

[0058] According to an embodiment of the present disclosure, the target quantity represents the quantity of financial data that have passed the authenticity check in the data group, and the time span represents the time span of multiple financial data in the data group.

[0059] According to an embodiment of the present disclosure, a calculation method for measuring data fluctuations may be used to determine the first test result based on the single-day test data, target quantity, and time span. For example, the Z-SCORE method may be used to measure the degree of deviation of the financial data of the day.

[0060] In operation S240 , if the first inspection result is a failure, warning information for the data group is generated.

[0061] According to an embodiment of the present disclosure, when the first inspection result is passed, warning information of the data group can be generated. For each data group, relevant personnel can be notified for processing after the warning information of each data group is obtained, or after all data groups are inspected, the warning information of multiple data groups can be batch-notified to relevant personnel for processing.

[0062] According to an embodiment of the present disclosure, the warning information may include the reason for the failure of the first test result. For example, the warning information may be "the first test result of the XX data group on XX date is not passed, the reason is YYY". Alternatively, when the first test results of multiple data groups are all passed, the relevant personnel may also be notified that "the first test results of the XX data group on XX date ~ XY data group are all passed".

[0063] In an embodiment of the present disclosure, multiple data groups are determined according to target financial data in a temporary data table, wherein the target financial data includes multiple financial data that have been verified for authenticity, and each data group includes multiple financial data of at least one risk factor; single-day verification data are determined according to historical statistical data, wherein the single-day verification data represents the probability that the authenticity verification of multiple financial data in a single day is passed; a first inspection result is determined according to the single-day inspection data, the target number and the time span corresponding to each data group, wherein the target number represents the number of financial data that have passed the authenticity verification in the data group, and the time span represents the time span of multiple financial data in the data group; and when the first inspection result is not passed, early warning information for the data group is generated. Through the above embodiments, the present disclosure can at least avoid the technical problem of low inspection efficiency caused by only performing procedural verification when an error occurs in the qualification inspection and failing to perform data early warning, and by performing pre-inspection at each stage of data acquisition, procedural problems such as missing data sources, errors or system errors can be detected in advance, thereby achieving the technical effect of improving inspection efficiency.

[0064] For ease of understanding, the following will be Figure 2~Figure 5 Take as an example to illustrate the data early warning method of the embodiment of the present disclosure.

[0065] Figure 3 The flowchart of the method for determining single-day inspection data according to an embodiment of the present disclosure is schematically shown. Figure 3 As shown, the method 300 for determining single-day inspection data of this embodiment includes operations S321 to S324, which can be used as a specific embodiment of operation S220.

[0066] In operation S321, sampling parameters are determined according to historical statistical data.

[0067] According to the embodiments of the present disclosure, for a certain data group, the result of the authenticity test is either passed or failed. From a probability perspective, the result of the authenticity test can be regarded as a two-point distribution. At the same time, whether the authenticity test of financial data every two days is an independent event. Therefore, for the monthly, quarterly, annual, and all-time situations, it can be regarded as 30, 90, 360, and N independent two-point distributions. The number of times there are real prices in these N tests follows a binomial distribution. Therefore, the single-day inspection data can be estimated by repeated random sampling.

[0068] According to an embodiment of the present disclosure, the historical statistical data may be the number of financial data that passed the authenticity check and the total data volume of the historical financial data.

[0069] For example, sampling parameter = the number of financial data that passed the authenticity test / the total amount of historical financial data, that is, the probability p of passing the daily authenticity test, hereinafter referred to as sampling parameter p.

[0070] In operation S322, a plurality of target statistical arrays are generated according to the sampling parameters, wherein the target statistical arrays include a preset number of test values, and a ratio of the number of test values ​​that pass the authenticity test to the preset number is equal to the sampling parameters.

[0071] According to an embodiment of the present disclosure, the preset number may be the total number of days in a year, such as 360.

[0072] According to an embodiment of the present disclosure, in repeated random sampling, one or more target statistical arrays can be randomly generated, and the target statistical array can be of a preset length, that is, it includes a preset number of test values, such as 360. In the target statistical array, each test value has a probability of p being 1 and a probability of (1-p) being 0, 1 being a test value that passes the authenticity test, and 0 being a test value that fails the authenticity test. Thus, among the 360 ​​test values, there are 360*p test values ​​that pass the authenticity test, and 360*(1-p) test values ​​that fail the authenticity test.

[0073] For example, 10,000 random target statistic arrays may be generated, each target statistic having 360*p test values ​​that pass the authenticity test and 360*(1-p) test values ​​that fail the authenticity test, but with different distributions of 1 and 0 in the target statistic array.

[0074] In operation S323, a first inspection probability of passing each inspection standard in the qualification inspection and a second inspection probability of simultaneously passing a plurality of inspection standards in the qualification inspection are determined based on the plurality of target statistical arrays.

[0075] According to an embodiment of the present disclosure, the inspection standard is a preset inspection standard in the qualification inspection. For example, the inspection standard may include: at least 24 observations can be observed within one year before the inspection time point, and at least 4 observations can be observed within any 90 days at any time point within one year before the inspection time point. At least 100 observations can be observed within 12 months before the inspection time point. The observations here are also financial data that have passed the authenticity inspection, such as the existence of real prices.

[0076] According to an embodiment of the present disclosure, in the case where there are multiple target statistical arrays, for each target statistical array, it is determined whether it meets each inspection standard. If it meets, it is counted as 1, and if it does not meet, it is not counted. Thus, by combining the counts of multiple target statistical arrays meeting each inspection standard and the total number of target statistical arrays, a first inspection probability of passing each inspection standard in the qualification test and a second inspection probability of passing multiple inspection standards in the qualification test at the same time can be obtained.

[0077] For example, the first test probability of passing the first test standard A, P(A) = the number of target statistical arrays that meet the first test standard / the total number of target statistical arrays; the first test probability of passing the second test standard B, P(B) = the number of target statistical arrays that meet the second test standard / the total number of target statistical arrays. The second test probability of passing both test standards in the qualification test at the same time, P(A / \B) = the number of target statistical arrays that meet both test standards at the same time / the total number of target statistical arrays.

[0078] In operation S324, single-day inspection data is determined according to the plurality of first inspection probabilities and second inspection probabilities.

[0079] According to an embodiment of the present disclosure, still taking the above two inspection standards as an example, the value of the single-day inspection data = P(A)+P(B)-P(A / \B).

[0080] According to the embodiments of the present disclosure, when predicting the single-day inspection data, the accuracy of the single-day inspection data (the probability of passing the qualification inspection on a single day / the next day) depends on the number of target statistical arrays, that is, the number of experimental simulations of repeated random sampling. The more experimental simulations, the closer to the true value, but the greater the computational consumption, therefore, the number of target statistical arrays can be determined based on empirical values.

[0081] In the embodiments of the present disclosure, for the probability problem of high complexity such as qualification test, from the perspective of probability model, sampling parameters are determined according to historical statistical data through repeated random sampling; target statistical arrays are generated according to the sampling parameters; the first test probability of passing each test standard in the qualification test and the second test probability of passing multiple test standards in the qualification test at the same time are determined according to the target statistical array; and the single-day test data is determined according to the multiple first test probabilities and second test probabilities. Thus, repeated random sampling can be used to predict whether the financial data of a single day passes the qualification test for recent data grouping, so that early warning can be given from the perspective of a single day through a simple probability model. The implementation method is simple, and there is no need to wait until the data that meets the time span of the qualification test is collected before the qualification test can be performed, thus achieving the technical effect of data early warning.

[0082] According to an embodiment of the present disclosure, the method also includes: when the single-day inspection data is less than or equal to the first threshold, determining the second inspection result as failed and generating early warning information; when the single-day inspection data is greater than the first threshold, determining the second inspection result as passed, and determining the first inspection result based on the daily inspection data, the target number corresponding to each data group, and the time span.

[0083] According to the embodiment of the present disclosure, since the first test result is determined based on the single-day test data, if the single-day test data is wrong, then the subsequent first test result will also be wrong. Therefore, after calculating the single-day test data, the single-day test data can be tested once, such as determining the second test result.

[0084] According to an embodiment of the present disclosure, when the single-day inspection data is less than or equal to the first threshold, the single-day inspection data is too low, and the subsequent first inspection result is also not passed. Therefore, when the second inspection result is not passed, data warning is directly performed to generate warning information.

[0085] In addition, when the second inspection result is failure, the corresponding processing result can be determined according to actual needs, such as determining whether to supplement the upstream data volume for this data group to increase the expected passing probability of the qualification inspection.

[0086] According to an embodiment of the present disclosure, when the single-day inspection data is greater than the first threshold, the second inspection result is determined to be passed, and subsequent first inspection results can continue to be generated, such as determining the first inspection result based on the single-day inspection data, the target number corresponding to each data group, and the time span.

[0087] In the embodiments of the present disclosure, after determining the single-day inspection data, by first determining the second inspection result of the single-day inspection data, it is possible to ensure that when the second inspection result fails, data warning is directly performed, that is, early warning of the data is achieved, and there is no need to perform subsequent determination operations of the first inspection result, thereby reducing the waste of computer resources.

[0088] According to an embodiment of the present disclosure, determining a first inspection result based on single-day inspection data, a target quantity and a time span corresponding to each data group includes: calculating the standard deviation of the data group and the product between the single-day inspection data and the time span based on the single-day inspection data and the time span; determining a calculated value characterizing the degree of dispersion of multiple financial data within the data group based on the difference between the target quantity and the product, and the standard deviation; and determining the first inspection result based on a comparison result of the calculated value with a second threshold.

[0089] According to an embodiment of the present disclosure, the Z-SCORE method may be used to determine the first test result. For example, after calculating the single-day test data based on historical statistical data, it may be assumed that the probability of a certain data group passing the qualification test on a certain day is q, that is, the single-day test data q. In the case of counting whether the data group passes the qualification test under a time span, it may be determined that the time span of passing the qualification test within the time span n is r.

[0090] Abstracting the overall process, for a binomial distribution, the probability of success each time (daily) is q. Assume that within a period of time, the number of observations that pass the qualification test is k. Then use the Z-SCORE method to measure the degree of deviation of the observed value from the probability mean. The process of obtaining the calculated value can be seen in the following formula (1):

[0091] (1)

[0092] Among them, n is the time span of data grouping, q is the single-day test data, and the standard deviation of data grouping is , the product of the single-day inspection data and the time span is nq. According to the time span r of the qualified inspection, the product nq and the standard deviation A calculated value Z1 representing the dispersion degree of the plurality of financial data in the data group is obtained.

[0093] In a specific embodiment, for monthly statistics, the time span n is 30. For quarterly statistics, the time span n is 90, and for annual statistics, the time span n is 360. Meanwhile, r represents the number of days that have passed the qualification test for the assumptions in the past 30 days, the past 90 days, and the past 360 days, respectively.

[0094] According to an embodiment of the present disclosure, after determining the calculated value, the normal distribution probability table corresponding to the value of Z-SCORE can be used to calculate the probability of occurrence of financial data that has passed the authenticity test in the recent period compared with all historical probability levels. In order to simplify the data warning process, it is set that when the absolute value of the calculated value is greater than the second threshold value (such as 2), the first test result is determined to be failed, and a warning message is generated, that is, a warning is issued in the case of an extreme deviation of about 5%. At this time, it is possible to manually check whether the upstream data has changed. When the absolute value of the calculated value is less than or equal to the second threshold value (such as 2), the first test result is determined to be passed.

[0095] In the embodiments of the present disclosure, by adopting the Z-SCORE method, the RFET inspection is improved from the perspective of the probability model, and the probability change of passing the qualification inspection in the future is predicted based on the time span of the current data grouping. Not only is data warning achieved before data measurement, but the warning measures are simple and fast.

[0096] According to an embodiment of the present disclosure, a count dispersion value characterizing a data group is determined based on sampling parameters, a time span and a target number; a third inspection result is determined based on a comparison result between the count dispersion value and a third threshold value; and in a case where the third inspection result is passed, the first inspection result is determined based on the target number and time span corresponding to each data group based on the single-day inspection data.

[0097] According to an embodiment of the present disclosure, similar to the above-mentioned method of determining the second test result, the count dispersion value can be calculated according to the following formula (2):

[0098] (2)

[0099] Among them, n is the time span, p is the sampling parameter, and the standard deviation of the count is , the product of the single-day test data and the time span is np, and k is the observation value that passes the authenticity test in the current data group. According to k, the product np and the standard deviation The count dispersion value Z2 is obtained, which represents the standard deviation deviation of the real price in the recent period compared with the historical situation.

[0100] According to an embodiment of the present disclosure, when the absolute value of the count dispersion value Z2 is greater than the third threshold value (such as 2), the third test result is determined to be unsuccessful, and an early warning message is generated, that is, an early warning is issued in the case of an extreme deviation of about 5%. At this time, it is possible to manually check whether the upstream data has changed. When the absolute value of the count dispersion value is less than or equal to the third threshold value (such as 2), the third test result is determined to be passed.

[0101] In the embodiments of the present disclosure, by adopting the Z-SCORE method, the RFET test is improved from the perspective of the probability model, and the count changes for the authenticity test in the future are predicted based on the time span of the current data grouping. This not only realizes data warning before data measurement, but also makes the warning measures simple and fast.

[0102] Figure 4 The flowchart of the method for determining the fourth inspection result according to the embodiment of the present disclosure is schematically shown. Figure 4 As shown, the method 400 for determining the fourth inspection result includes operations S410 to S440, which may be performed before operation S210.

[0103] In operation S410, a program script is called to load target financial data from a preset data source into a temporary data table.

[0104] In operation S420, verification parameters of the target financial data are determined according to the temporary data table.

[0105] In operation S430, a fourth verification result of the target financial data is determined according to the verification parameter.

[0106] In operation S440, when the fourth inspection result is a failure, warning information for the data group is generated according to the inspection parameters.

[0107] According to an embodiment of the present disclosure, the program script may be a pre-written data acquisition script. When accessing an external preset data source, the financial data is automatically loaded into a temporary data table of the database by calling the program script.

[0108] According to an embodiment of the present disclosure, before acquiring the target financial data, the user's consent or authorization may be obtained. For example, before operation S410, a request to acquire the target financial data may be issued to the user who owns the target financial data. When the user who owns the target financial data agrees or authorizes the acquisition of the target financial data, operation S410 is performed.

[0109] According to an embodiment of the present disclosure, after the target financial data is acquired and stored in the temporary data table in operation S410, data confirmation can be performed to ensure that the failure of the subsequent qualification test is not caused by the lack of data source or data in the data acquisition stage. Therefore, the test parameters can be determined according to the temporary data table in operation S420. The test parameters can be parameters of data dimensions, such as data volume, data acquisition time, etc.

[0110] For operation S430, after obtaining the inspection parameter, the inspection parameter is subjected to data inspection, and a fourth inspection result is determined. If the fourth inspection result is not passed, a warning message for the data group is generated according to the inspection parameter, for example, the warning message may be "the fourth inspection result is not passed because the inspection parameter X has not passed the inspection."

[0111] According to an embodiment of the present disclosure, when the fourth inspection result is passed, the above operation S210 may be performed.

[0112] In the embodiments of the present disclosure, during the data acquisition stage, the inspection parameters of the target financial data are determined according to the temporary data table; according to the inspection parameters, the fourth inspection result of the target financial data is determined, and when the fourth inspection result is a failure, an early warning message is directly generated, thereby realizing an early warning of the data without executing subsequent single-day inspection data calculation and first inspection result calculation operations, thereby reducing the waste of computer resources.

[0113] According to an embodiment of the present disclosure, the inspection parameters include the data volume and / or data acquisition time of the target financial data; determining the fourth inspection result of the target financial data based on the inspection parameters includes: determining the fourth inspection result based on a comparison result between the data volume and the historical data volume, wherein the historical data volume is the average data volume of the financial data acquired each time within a preset time period; and / or determining the fourth inspection result based on a comparison result between the data acquisition time and the current time.

[0114] According to an embodiment of the present disclosure, when the difference between the data volume and the historical data volume is greater than the fourth threshold, the fourth test result is determined to be unsuccessful; when the difference between the data volume and the historical data volume is less than or equal to the fourth threshold, the fourth test result is determined to be passed. For example, the time span of the historical data volume can be the same as the time span of the financial data in the data group.

[0115] It is understandable that if the difference between the data volume and the historical data volume is greater than the fourth threshold, it means that the data volume is significantly different from the historical average value, that is, the data volume fluctuates greatly, and the detection fails. The relevant operation and maintenance personnel can be notified by warning and a request to re-acquire data can be issued to the upstream.

[0116] According to the embodiment of the present disclosure, when the data acquisition time is the same as the current time, the fourth test result is determined to be passed; when the data acquisition time is different from the current time, the fourth test result is determined to be failed. It can be understood that if the data acquisition time (data timestamp) does not match the current time of the system, that is, it is not the latest data, it fails the test, an early warning is issued to notify the relevant operation and maintenance personnel, and a request to re-acquire data is issued to the upstream.

[0117] According to an embodiment of the present disclosure, when the inspection parameters include both data acquisition time and data volume, if the data acquisition time is the same as the current time and the difference between the data volume and the historical data volume is less than or equal to the fourth threshold, the fourth inspection result is determined to be passed; otherwise, it is failed.

[0118] In the embodiments of the present disclosure, by comparing the data volume and / or data acquisition time with the historical data volume and / or the current time, the timestamp and data volume detection can be completed, so that the data acquired from the data source can be detected and warned in advance from these two dimensions, avoiding the failure of subsequent qualification inspection due to missing data source or data error, thereby improving the inspection efficiency.

[0119] According to an embodiment of the present disclosure, for operation S210, multiple data groups are determined based on the target financial data in the temporary data table, including: obtaining a mapping table between risk factors and data groups from a database; and dividing the target financial data into multiple data groups based on the mapping table.

[0120] According to an embodiment of the present disclosure, a mapping table between risk factors and data groups can be pre-established according to the mapping relationship between financial products and risk factors. Thus, after acquiring target financial data, the target financial data can be divided into multiple data groups according to the financial products of the target financial data and the above mapping table.

[0121] In the embodiment of the present disclosure, the target financial data is divided into multiple data groups according to the mapping table, so that the multiple financial data in each data group have actual physical meanings. Therefore, when the risk factor qualification test is performed on the data groups of the same type of financial products, it can be more in line with the actual scenario and the prediction result is more accurate.

[0122] Figure 5 The following schematically shows a data early warning method scenario diagram according to a specific embodiment of the present disclosure. Figure 5 As shown, the embodiment 500 includes operations S501 to S509.

[0123] In operation S501, a verification parameter of the target financial data is determined according to the temporary data table; and a fourth verification result of the target financial data is determined according to the verification parameter.

[0124] In operation S502, the fourth test result is determined whether it passes. If the fourth test result is passed, operation S503 is performed; if the fourth test result is not passed, operation S509 is performed.

[0125] In operation S503, the single-day verification data is determined according to the historical statistical data. After operation S503, the target financial data may be grouped, and a second verification result may be determined for each data group according to the single-day verification data.

[0126] In operation S504, it is determined whether the third test result passes according to the sampling parameters. If the third test result passes, operation S505 is performed; if the third test result does not pass, operation S509 is performed.

[0127] In operation S505, it is determined whether the second inspection result is passed according to the single-day inspection data. If the second inspection result is passed, operation S506 is performed; if the second inspection result is not passed, operation S509 is performed.

[0128] In operation S507 , a first inspection result is determined according to the single-day inspection data, the target quantity corresponding to each data group, and the time span.

[0129] In operation S508, the first test result is determined whether it passes. If the first test result is passed, operation S508 is performed; if the first test result is not passed, operation S509 is performed.

[0130] In operation S508, pass information is generated.

[0131] In operation S509, warning information is generated.

[0132] The disclosed embodiments improve the RFET inspection from the perspective of probability model, covering the inspection of the probability deviation of the counting statistics of recent grouped data, the prediction of the probability of passing the data group, the evaluation of the expected probability of qualification, and the inspection of the probability change of qualification in the future (corresponding to the third inspection result, the second inspection result, the sampling parameter p and the first inspection parameter respectively). By constructing a comprehensive data early warning mechanism before, during and after measurement, the stable operation of the RFET inspection system, the rationality of data collection, and the fit between the output results and business needs are ensured, and the inspection efficiency is maximized.

[0133] Based on the above data early warning method, the present disclosure also provides a data early warning device. Figure 6 The device is described in detail.

[0134] Figure 6 The structural block diagram of the data early warning device according to the embodiment of the present disclosure is schematically shown.

[0135] like Figure 6 As shown, the data warning device 600 of this embodiment includes: a first determination module 610 , a second determination module 620 , a third determination module 630 and a warning module 640 .

[0136] The first determination module 610 is used to determine multiple data groups according to the target financial data in the temporary data table, wherein the target financial data includes multiple financial data that have been verified for authenticity, and each data group includes multiple financial data of at least one risk factor. In one embodiment, the first determination module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0137] The second determination module 620 is used to determine the single-day inspection data based on the historical statistical data, wherein the single-day inspection data represents the probability of passing the qualification inspection of the plurality of financial data in a single day. In one embodiment, the second determination module 620 can be used to perform the operation S220 described above, which will not be described in detail here.

[0138] The third determination module 630 is used to determine the first inspection result according to the single-day inspection data, the target number and the time span corresponding to each data group, wherein the target number represents the number of financial data that pass the authenticity inspection in the data group, and the time span represents the time span of multiple financial data in the data group. In one embodiment, the third determination module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0139] The warning module 640 is used to generate warning information for the data group when the first inspection result is a failure. In one embodiment, the warning module 640 can be used to perform the operation S240 described above, which will not be described in detail here.

[0140] According to an embodiment of the present disclosure, the second determination module 620 includes: a generation submodule, a first determination submodule, and a second determination submodule. The generation submodule is used to determine the sampling parameters based on historical statistical data; based on the sampling parameters, a plurality of target statistical arrays are generated, wherein the target statistical array includes a preset number of test values, and the ratio of the number of test values ​​that pass the authenticity test to the preset number is equal to the sampling parameters. The first determination submodule is used to determine the first test probability of passing each test standard in the qualification test and the second test probability of simultaneously passing multiple test standards in the qualification test based on the plurality of target statistical arrays. The second determination submodule is used to determine the single-day test data based on the plurality of first test probabilities and the second test probabilities.

[0141] According to an embodiment of the present disclosure, the data early warning device 600 further includes: a fourth determination module, which is used to determine that the second inspection result is not passed and generate early warning information when the single-day inspection data is less than or equal to the first threshold. A fifth determination module is used to determine that the second inspection result is passed when the single-day inspection data is greater than the first threshold, and determine the first inspection result according to the target number and time span corresponding to the single-day inspection data and each data group.

[0142] According to an embodiment of the present disclosure, the third determination module 630 includes: a first calculation submodule, which is used to calculate the standard deviation of the data group and the product between the single-day inspection data and the time span according to the single-day inspection data and the time span. A second calculation submodule is used to determine a calculated value representing the dispersion degree of multiple financial data in the data group according to the difference between the target number and the product and the standard deviation. A third determination submodule is used to determine the first inspection result according to the comparison result between the calculated value and the second threshold.

[0143] According to an embodiment of the present disclosure, the second determination module 620 includes: a third calculation submodule, for determining a count dispersion value characterizing a data group according to a sampling parameter, a time span, and a target number. A first inspection submodule, for determining a third inspection result according to a comparison result between the count dispersion value and a third threshold. A second inspection submodule, for determining a first inspection result according to the target number and time span corresponding to each data group according to the single-day inspection data, when the third inspection result is passed.

[0144] According to an embodiment of the present disclosure, the data early warning device 600 further includes: a calling module, which is used to call a program script to load the target financial data from a preset data source into a temporary data table. A sixth determination module, which is used to determine the inspection parameters of the target financial data according to the temporary data table. A seventh determination module, which is used to determine the fourth inspection result of the target financial data according to the inspection parameters. An eighth determination module, which is used to generate early warning information for the data group according to the inspection parameters when the fourth inspection result is not passed.

[0145] According to an embodiment of the present disclosure, the inspection parameters include the data volume and / or data acquisition time of the target financial data; the seventh determination module includes: a fourth determination submodule, used to determine the fourth inspection result based on the comparison result of the data volume and the historical data volume, wherein the historical data volume is the average data volume of the financial data acquired each time within a preset time period; and / or, a fifth determination submodule, used to determine the fourth inspection result based on the comparison result of the data acquisition time and the current time.

[0146] According to an embodiment of the present disclosure, any multiple modules of the first determination module 610, the second determination module 620, the third determination module 630 and the early warning module 640 can be combined into one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first determination module 610, the second determination module 620, the third determination module 630 and the early warning module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in a suitable combination of any of them. Alternatively, at least one of the first determination module 610 , the second determination module 620 , the third determination module 630 and the early warning module 640 may be at least partially implemented as a computer program module, and when the computer program module is executed, a corresponding function may be executed.

[0147] Figure 7 A block diagram of an electronic device suitable for implementing a data early warning method according to an embodiment of the present disclosure is schematically shown.

[0148] like Figure 7 As shown, the electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 to a random access memory (RAM) 703. The processor 701 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 701 may also include an onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0149] In RAM 703, various programs and data required for the operation of electronic device 700 are stored. Processor 701, ROM 702 and RAM 703 are connected to each other via bus 704. Processor 701 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 702 and / or RAM 703. It should be noted that the program can also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0150] According to an embodiment of the present disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to the bus 704. The electronic device 700 may further include one or more of the following components connected to the input / output (I / O) interface 705: an input portion 706 including a keyboard, a mouse, etc.; an output portion 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 708 including a hard disk, etc.; and a communication portion 709 including a network interface card such as a LAN card, a modem, etc. The communication portion 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage portion 708 as needed.

[0151] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0152] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, it may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 702 and / or RAM 703 described above and / or one or more memories other than ROM 702 and RAM 703.

[0153] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer system, the program code is used to enable the computer system to implement the data early warning method provided by the embodiment of the present disclosure.

[0154] The above functions defined in the system / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 701. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0155] In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 709, and / or installed from a removable medium 711. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0156] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, the above functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the system, device, means, module, unit, etc. described above can be implemented by a computer program module.

[0157] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0158] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0159] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0160] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A data early warning method, characterized in that: The method comprises: Determine a plurality of data groups according to target financial data in the temporary data table, wherein the target financial data includes a plurality of financial data that have been verified for authenticity, and each of the data groups includes a plurality of financial data of at least one risk factor; Determine single-day inspection data according to historical statistical data, wherein the single-day inspection data represents the probability that the qualification inspection of the plurality of financial data within a single day is passed; Determine a first inspection result according to the single-day inspection data, a target number and a time span corresponding to each of the data groups, wherein the target number represents the number of financial data in the data group that pass the authenticity inspection, and the time span represents the time span of a plurality of the financial data in the data group; and When the first inspection result is failure, warning information for the data group is generated.

2. The method according to claim 1, characterized in that Determining the single-day inspection data based on historical statistical data includes: Determining sampling parameters based on the historical statistical data; Generate a plurality of target statistical arrays according to the sampling parameters, wherein the target statistical arrays include a preset number of test values, and a ratio of the number of test values ​​that pass the authenticity test to the preset number is equal to the sampling parameters; Determining, based on a plurality of said target statistical arrays, a first inspection probability of passing each inspection standard in the qualification inspection and a second inspection probability of simultaneously passing a plurality of said inspection standards in the qualification inspection; and The single-day inspection data is determined according to a plurality of the first inspection probabilities and the second inspection probabilities.

3. The method according to claim 1, characterized in that: The method further comprises: When the single-day inspection data is less than or equal to the first threshold, determining the second inspection result as failed, and generating the warning information; When the single-day inspection data is greater than the first threshold, the second inspection result is determined to be passed, and the first inspection result is determined based on the single-day inspection data, the target quantity corresponding to each of the data groups, and the time span.

4. The method according to claim 1 or 3, characterized in that: Determining the first inspection result according to the single-day inspection data, the target quantity and the time span corresponding to each of the data groups includes: Calculate the standard deviation of the data grouping and the product of the single-day inspection data and the time span according to the single-day inspection data and the time span; Determining a calculated value representing a dispersion degree of the plurality of financial data within the data group according to a difference between the target number and the product and the standard deviation; and The first inspection result is determined according to a comparison result between the calculated value and a second threshold value.

5. The method according to claim 2, characterized in that: The method further comprises: Determining a count dispersion value characterizing the data grouping based on the sampling parameter, the time span, and the target number; Determining a third test result according to a comparison result between the count dispersion value and a third threshold value; and When the third inspection result is passed, the first inspection result is determined according to the single-day inspection data, the target quantity and the time span corresponding to each of the data groups.

6. The method according to claim 1, characterized in that Before determining a plurality of data groups according to the target financial data in the temporary data table, the method further includes: Calling a program script to load the target financial data into the temporary data table from a preset data source; Determining the verification parameters of the target financial data according to the temporary data table; determining a fourth verification result of the target financial data according to the verification parameter; and When the fourth inspection result is failure, the warning information for the data group is generated according to the inspection parameter.

7. The method according to claim 6, characterized in that The verification parameter includes the data volume and / or data acquisition time of the target financial data; and determining the fourth verification result of the target financial data according to the verification parameter includes: Determining the fourth inspection result according to a comparison result between the data volume and the historical data volume, wherein the historical data volume is an average data volume of the financial data acquired each time within a preset time period; and / or, The fourth inspection result is determined according to a comparison result between the data acquisition time and the current time.

8. A data early warning device, characterized in that: The device comprises: A first determination module is used to determine a plurality of data groups according to target financial data in the temporary data table, wherein the target financial data includes a plurality of financial data that have been verified for authenticity, and each of the data groups includes a plurality of financial data of at least one risk factor; A second determination module is used to determine single-day inspection data based on historical statistical data, wherein the single-day inspection data represents the probability of passing the qualification inspection of the plurality of financial data within a single day; a third determination module, configured to determine a first inspection result according to the single-day inspection data, a target number and a time span corresponding to each of the data groups, wherein the target number represents the number of financial data in the data group that pass the qualification inspection, and the time span represents the time span of a plurality of the financial data in the data group; and An early warning module is used to generate early warning information for the data group when the first inspection result is failure.

9. An electronic device, comprising: one or more processors; a memory for storing one or more computer programs, It is characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images