A method and system for verifying bank statement data

Abstract

The present invention provides a method and system for verifying bank statement data. The method includes preprocessing the bank statement data to be verified to obtain processed statement data; performing a first verification on the processed statement data based on first feature data to obtain a first verification value; performing a second verification on the processed statement data based on second feature data to obtain a second verification value; performing a third verification on the processed statement data based on third feature data to obtain a third verification value; performing a fourth verification on the processed statement data based on fourth feature data to obtain a fourth verification value; and completing the verification of the processed statement data based on the first verification value, the second verification value, the third verification value, and the fourth verification value. By performing four verification processes on the bank statement data, the present invention can improve the accuracy of verification and also facilitate the improvement of data supervision.

Description

Technical Field

[0001] The present invention belongs to the technical field of data verification, and particularly relates to a method and system for verifying bank statement data. Background Art

[0002] For the operation of an enterprise, the quality management of bank statement data is very necessary. For financial personnel at the group level, the bank statement data of each company under the entire group usually needs to be imported into the Kingdee system, and the auxiliary functions of the Kingdee system are combined with the manual work of financial personnel to complete the verification process of bank statement data. As a result, on the one hand, the verification efficiency is low, and on the other hand, the verification accuracy is not high. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention provides a method and system for verifying bank statement data to solve the technical problems in the prior art.

[0004] On the one hand, the present invention provides the following technical solution. A method for verifying bank statement data includes:

[0005] Obtain the bank statement data to be verified, and preprocess the bank statement data to be verified to obtain processed statement data;

[0006] Extract the first feature data of the processed statement data, and perform a first verification on the processed statement data based on the first feature data to obtain a first verification value;

[0007] Extract the second feature data of the processed statement data, and perform a second verification on the processed statement data based on the second feature data to obtain a second verification value;

[0008] Extract the third feature data of the processed statement data, and perform a third verification on the processed statement data based on the third feature data to obtain a third verification value;

[0009] Extract the fourth feature data of the processed statement data, and perform a fourth verification on the processed statement data based on the fourth feature data to obtain a fourth verification value;

[0010] Complete the verification of the processed statement data based on the first verification value, the second verification value, the third verification value, and the fourth verification value.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows: First, the present invention obtains the bank statement data to be verified, preprocesses the bank statement data to be verified to obtain processed statement data; extracts the first feature data of the processed statement data, and performs a first verification on the processed statement data based on the first feature data to obtain a first verification value; extracts the second feature data of the processed statement data, and performs a second verification on the processed statement data based on the second feature data to obtain a second verification value; extracts the third feature data of the processed statement data, and performs a third verification on the processed statement data based on the third feature data to obtain a third verification value; extracts the fourth feature data of the processed statement data, and performs a fourth verification on the processed statement data based on the fourth feature data to obtain a fourth verification value; completes the verification of the processed statement data based on the first verification value, the second verification value, the third verification value, and the fourth verification value. The present invention performs four verification processes on the bank statement data, thereby improving the accuracy of verification and facilitating the improvement of data supervision.

[0012] Preferably, the steps of obtaining the bank statement data to be verified and preprocessing the bank statement data to be verified to obtain processed statement data include:

[0013] Successively perform null value data removal, duplicate data removal, and format unit adjustment processing on the bank statement data to be verified to obtain processed statement data.

[0014] Preferably, the steps of extracting the first feature data of the processed statement data and performing a first verification on the processed statement data based on the first feature data to obtain a first verification value include:

[0015] Successively extract the processed statement data of the target company under the same data source to obtain the first feature data;

[0016] Set a data integrity rule based on the data standard of each group of the first feature data, and traverse and verify all the first feature data based on the data integrity rule to obtain a traversal result;

[0017] Calculate a first complete verification value based on the traversal result :

[0018] ;

[0019] In the formula, represents the total number of data traversed by the data integrity rule, represents the number of data that fails to pass the data integrity rule traversal test;

[0020] Extract the company set in the bank statement data to be verified, and calculate a second complete verification value based on the company set :

[0021] ;

[0022] In the formula, represents the th company in the company set, represents the target company;

[0023] Scan the zero-value attribute fields in the first feature data, and calculate the third complete verification value based on the zero-value attribute fields :

[0024] ;

[0025] In the formula, , represent the number of data groups and the number of attribute fields in the first feature data, represents the th data group where there are zero-value attribute fields;

[0026] Integrate the first complete verification value , the second complete verification value , and the third complete verification value to obtain the first verification value.

[0027] Preferably, the step of extracting the second feature data of the processing flow data and performing a second verification on the processing flow data based on the second feature data to obtain a second verification value includes:

[0028] Sequentially extract the processing flow data of the target company under different data sources to obtain the second feature data;

[0029] Obtain each data item name under the second feature data, extract the meaning of the data item name and perform a meaning comparison in a preset meaning library, and unify the data item names with the same meaning to obtain unified feature data;

[0030] Arbitrarily select a group of data in the unified feature data as the reference data, and perform hashing processing on the reference data and the remaining data in the unified feature data to obtain reference hash data and the remaining hash data;

[0031] Calculate the similarity between the remaining hash data and the reference hash data. If the similarity between the remaining hash data and the reference hash data is not greater than the preset similarity, then eliminate the unified feature data corresponding to the remaining hash data. If the similarity between the remaining hash data and the reference hash data is greater than the preset similarity, then retain the unified feature data corresponding to the remaining hash data to obtain the retained feature data;

[0032] Calculate the first similarity verification value based on the retained feature data :

[0033] ;

[0034] Wherein, represents the number of data groups in the unified feature data, represents the number of data groups in the retained feature data;

[0035] Extract the dependency relationships between each data item of the unified feature data, determine the dependency verification rules based on the dependency relationships, and traverse and verify all the unified feature data based on the dependency verification rules to obtain the dependency traversal result;

[0036] Calculate the second similarity verification value based on the dependency traversal result :

[0037] ;

[0038] Wherein, represents the number of data covered by the th dependency verification rule traversal, represents the number of data that pass the verification by the th dependency verification rule traversal, represents the unified feature data;

[0039] Integrate the first similarity verification value , the second similarity verification value to obtain the second verification value.

[0040] Preferably, the step of extracting the third feature data of the processing flow data and performing a third verification on the processing flow data based on the third feature data to obtain a third verification value includes:

[0041] Extract the processing flow data of the target company in the same data source and within a preset time period to obtain the third feature data;

[0042] Perform normalization processing on the third feature data to obtain normalized feature data;

[0043] Perform a normalization verification on the normalized feature data to obtain a verification box plot, and identify and extract the first abnormal data in the verification box plot;

[0044] Use the K-clustering algorithm to perform clustering analysis on the third feature data to obtain the second abnormal data;

[0045] Calculate the third verification value based on the first abnormal data and the second abnormal data :

[0046] ;

[0047] Wherein, represents the number of data of the third characteristic data, , respectively represent the first abnormal data and the second abnormal data.

[0048] Preferably, the step of extracting the fourth characteristic data of the processed pipeline data and performing a fourth verification on the processed pipeline data based on the fourth characteristic data to obtain a fourth verification value includes:

[0049] Extract the data of a single dimension of the target company in different data cycles to obtain the fourth characteristic data;

[0050] Obtain the time stamp of the fourth characteristic data, and determine the set time requirement based on the time stamp;

[0051] Determine the unit verification value based on the set time requirement :

[0052] ;

[0053] Wherein, represents the total number of data within a unit time, represents the total number of data that meet the set time requirement within a unit time;

[0054] Based on the unit verification value Determine the fourth verification value :

[0055] ;

[0056] Wherein, represents the total number of data cycles.

[0057] In a second aspect, the present invention provides the following technical solution, a bank statement data verification system, the system includes:

[0058] A processing module, configured to obtain the bank statement data to be verified, preprocess the bank statement data to be verified to obtain processed pipeline data;

[0059] A first verification module, configured to extract the first characteristic data of the processed pipeline data, and perform a first verification on the processed pipeline data based on the first characteristic data to obtain a first verification value;

[0060] The second verification module is used to extract the second feature data of the processed transaction data, and perform a second verification on the processed transaction data based on the second feature data to obtain a second verification value;

[0061] The third verification module is used to extract the third feature data of the processed transaction data, and perform a third verification on the processed transaction data based on the third feature data to obtain a third verification value;

[0062] The fourth verification module is used to extract the fourth feature data of the processed transaction data, and perform a fourth verification on the processed transaction data based on the fourth feature data to obtain a fourth verification value;

[0063] The final verification module is used to complete the verification of the processed transaction data based on the first verification value, the second verification value, the third verification value, and the fourth verification value.

[0064] Preferably, the processing module is specifically used for:

[0065] Removing null value data, duplicate data, and adjusting the format unit of the bank transaction data to be verified in sequence to obtain the processed transaction data.

[0066] In a third aspect, the present invention provides the following technical solution. A computer includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the bank transaction data verification method as described above is implemented.

[0067] In a fourth aspect, the present invention provides the following technical solution. A storage medium stores a computer program, and when the computer program is executed by a processor, the bank transaction data verification method as described above is implemented. Description of the Drawings

[0068] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0069] Figure 1 It is a flowchart of the bank transaction data verification method provided in Embodiment 1 of the present invention;

[0070] Figure 2 It is a structural block diagram of the bank transaction data verification system provided in Embodiment 2 of the present invention;

[0071] Figure 3Schematic diagram of the hardware structure of a computer provided by another embodiment of the present invention.

[0072] The embodiments of the present invention will be further described below with reference to the accompanying drawings. Specific embodiments

[0073] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the embodiments of the present invention, and should not be construed as a limitation of the present invention.

[0074] In the description of the embodiments of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing the embodiments of the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0075] In addition, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present invention, "a plurality" means two or more unless otherwise specifically defined.

[0076] In the embodiments of the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or integrated; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0077] Embodiment 1

[0078] In Embodiment 1 of the present invention, as Figure 1 shown, a method for verifying bank statement data includes:

[0079] S1. Obtain the bank statement data to be verified, and preprocess the bank statement data to be verified to obtain processed statement data;

[0080] Among them, the step S1 is specifically used for:

[0081] Removing null data, duplicate data, and adjusting the format and unit of the bank statement data to be verified in sequence to obtain processed statement data;

[0082] Specifically, the purpose of preprocessing is to remove the blank values and duplicate data existing in the data. At the same time, since the data from different data sources may have different formats and units, it is necessary to unify the format and unit thereof.

[0083] S2. Extract the first feature data of the processed statement data, and perform a first verification on the processed statement data based on the first feature data to obtain a first verification value;

[0084] Among them, the step S2 includes:

[0085] S21. Sequentially extract the processed statement data of the target company under the same data source to obtain the first feature data;

[0086] S22. Set a data integrity rule based on the data standard of each group of the first feature data, and traverse and verify all the first feature data based on the data integrity rule to obtain a traversal result;

[0087] Specifically, assuming that complete data requires at least items such as foreign key, primary key, field length, precision, type, and attribute, the data integrity rule is to determine whether the data includes all the above items.

[0088] S23. Calculate a first complete verification value based on the traversal result :

[0089] ;

[0090] In the formula, represents the total number of data traversed by the data integrity rule, represents the number of data that fails to pass the traversal test of the data integrity rule.

[0091] S24. Extract the company set in the bank statement data to be verified, and calculate a second complete verification value based on the company set :

[0092] ;

[0093] In the formula, represents the th company in the company set, represents the target company.

[0094] S24. Scan the zero-value attribute fields in the first feature data, and calculate the third complete verification value based on the zero-value attribute fields. :

[0095] ;

[0096] In the formula, , represent the number of data groups and the number of attribute fields in the first feature data, represents the th data group, and there are zero-value attribute fields.

[0097] S26. Synthesize the first complete verification value , the second complete verification value , and the third complete verification value to obtain the first verification value;

[0098] Specifically, the first verification process is specifically the integrity verification of data. The first complete verification value is used to judge the integrity of metadata, the second complete verification value is used to judge the integrity of the data set, and the third complete verification value is used to judge the integrity of data items. Therefore, in the actual process of the first verification, the first complete verification value , the second complete verification value , and the third complete verification value can be independently verified respectively, or weighted fusion verification can be performed.

[0099] S3. Extract the second feature data of the processing flow data, and perform a second verification on the processing flow data based on the second feature data to obtain a second verification value;

[0100] Among them, the step S3 includes:

[0101] S31. Extract the processing flow data of the target company under different data sources in sequence to obtain the second feature data;

[0102] S32. Obtain each data item name under the second feature data, extract the meaning of the data item name and perform a meaning comparison in a preset meaning library, and unify the data item names with the same meaning to obtain unified feature data;

[0103] Specifically, in different data sources, the meanings expressed by different data items are the same. For example, for the company number, some data sources directly use the company name as the company number, some use the unified social credit code as the company number, and some will number according to their data source systems. Therefore, it is necessary to unify the data items expressing the same meaning, and then the feature data corresponding to each company can be obtained.

[0104] S33. Randomly select a group of data from the unified feature data as reference data, and perform hashing on the reference data and the remaining data in the unified feature data to obtain reference hash data and the remaining hash data.

[0105] S34. Calculate the similarity between the remaining hash data and the benchmark hash data. If the similarity between the remaining hash data and the benchmark hash data is not greater than the preset similarity, the unified feature data corresponding to the remaining hash data will be eliminated. If the similarity between the remaining hash data and the benchmark hash data is greater than the preset similarity, the unified feature data corresponding to the remaining hash data will be retained to obtain retained feature data.

[0106] S35: Calculate a first similarity check value based on the retained feature data :

[0107] ;

[0108] In the formula, represents the number of data groups in the unified feature data, Indicates the number of data groups in the retained feature data.

[0109] S36, extracting the dependency relationship between each data item of the unified feature data, determining a dependency verification rule based on the dependency relationship, and traversing and verifying all unified feature data based on the dependency verification rule to obtain a dependency traversal result;

[0110] Specifically, for transaction data, there will be certain dependencies between different data items. For example, the current account balance is related to the account balance of the last deposit and withdrawal, the last deposit, and the last withdrawal. Therefore, the data is traversed by setting dependent verification rules to complete the second verification process.

[0111] S37: Calculate a second similarity check value based on the dependency traversal result. :

[0112] ;

[0113] In the formula, Indicates that The number of data covered by the dependent verification rules, Indicates that The number of data that has passed the verification of the dependent verification rules. Represents unified feature data;

[0114] S38, comprehensive first similarity check value , the second similarity check value , to obtain a second verification value;

[0115] Specifically, the second verification process is specifically a consistency verification process. The first similarity verification value is specifically used to determine whether the data is equal in value, and the second similarity verification value is used to determine whether the data logic is consistent.

[0116] S4. Extract the third characteristic data of the processed flow data, and perform a third verification on the processed flow data based on the third characteristic data to obtain a third verification value;

[0117] Among them, the step S4 includes:

[0118] S41. Extract the processed flow data of the target company within the same data source and a preset time period to obtain the third characteristic data.

[0119] S42. Perform normalization processing on the third characteristic data to obtain normalized characteristic data.

[0120] S43. Perform a normalization verification on the normalized characteristic data to obtain a verification box plot, and identify and extract the first abnormal data in the verification box plot.

[0121] S44. Use the K-clustering algorithm to perform clustering analysis on the third characteristic data to obtain the second abnormal data.

[0122] S45. Calculate the third verification value based on the first abnormal data and the second abnormal data :

[0123] ;

[0124] In the formula, represents the data quantity of the third characteristic data, , respectively represent the first abnormal data and the second abnormal data;

[0125] Specifically, the first abnormal data and the second abnormal data are the outliers or abnormal values existing in the characteristic data, and the third verification process is specifically the verification of data accuracy, and the third verification value is specifically used to judge the qualitative accuracy and quantitative accuracy of the data.

[0126] S5. Extract the fourth characteristic data of the processed flow data, and perform a fourth verification on the processed flow data based on the fourth characteristic data to obtain a fourth verification value;

[0127] Among them, the step S5 includes:

[0128] S51. Extract the data of a single dimension of the target company in different data cycles to obtain the fourth characteristic data.

[0129] S52. Obtain the timestamp of the fourth feature data, and determine the set time requirement based on the timestamp.

[0130] S53. Determine the unit check value based on the set time requirement :

[0131] ;

[0132] In the formula, represents the total number of data within a unit time, represents the total number of data that meet the set time requirement within a unit time.

[0133] S54. Determine the fourth check value based on the unit check value : :

[0134] ;

[0135] In the formula, represents the total number of data cycles;

[0136] Specifically, for the timestamp of the data, the check of the data needs to be time-sensitive. Therefore, the set time requirement can be determined according to the check requirement. Therefore, the fourth check value is used to determine whether the data is within the preset time period, and the fourth check is specifically the check of the data time validity.

[0137] S6. Complete the check of the processed transaction data based on the first check value, the second check value, the third check value, and the fourth check value;

[0138] Specifically, after determining the first check value, the second check value, the third check value, and the fourth check value, the final check process can be carried out according to the first check value, the second check value, the third check value, and the fourth check value, which can be divided into a separate check and a fusion check process;

[0139] When performing a separate check, corresponding thresholds can be set according to the first check value, the second check value, the third check value, and the fourth check value respectively, and the check can be carried out according to the comparison between the first check value, the second check value, the third check value, and the fourth check value and the thresholds, and the data with unqualified checks can be extracted. When performing a fusion check, the first check value, the second check value, the third check value, and the fourth check value can be weighted and fused, and then a fusion threshold is determined. By comparing with the fusion threshold, the entire batch of bank transaction data can be checked as a whole. However, compared with the separate check, the separate check has higher accuracy.

[0140] The bank statement data verification method provided in the first embodiment of the present invention first obtains the bank statement data to be verified, preprocesses the bank statement data to be verified to obtain processed statement data; extracts the first feature data of the processed statement data, and performs a first verification on the processed statement data based on the first feature data to obtain a first verification value; extracts the second feature data of the processed statement data, and performs a second verification on the processed statement data based on the second feature data to obtain a second verification value; extracts the third feature data of the processed statement data, and performs a third verification on the processed statement data based on the third feature data to obtain a third verification value; extracts the fourth feature data of the processed statement data, and performs a fourth verification on the processed statement data based on the fourth feature data to obtain a fourth verification value; and completes the verification of the processed statement data based on the first verification value, the second verification value, the third verification value, and the fourth verification value. The present invention performs four verification processes on the bank statement data, thereby improving the accuracy of verification and facilitating the improvement of data supervision.

[0141] Embodiment 2

[0142] As Figure 2 shown, the second embodiment of the present invention provides a bank statement data verification system, and the system includes:

[0143] A processing module 1, configured to obtain the bank statement data to be verified, and preprocess the bank statement data to be verified to obtain processed statement data;

[0144] A first verification module 2, configured to extract the first feature data of the processed statement data, and perform a first verification on the processed statement data based on the first feature data to obtain a first verification value;

[0145] A second verification module 3, configured to extract the second feature data of the processed statement data, and perform a second verification on the processed statement data based on the second feature data to obtain a second verification value;

[0146] A third verification module 4, configured to extract the third feature data of the processed statement data, and perform a third verification on the processed statement data based on the third feature data to obtain a third verification value;

[0147] A fourth verification module 5, configured to extract the fourth feature data of the processed statement data, and perform a fourth verification on the processed statement data based on the fourth feature data to obtain a fourth verification value;

[0148] A final verification module 6, configured to complete the verification of the processed statement data based on the first verification value, the second verification value, the third verification value, and the fourth verification value.

[0149] The processing module 1 is specifically configured to:

[0150] The to-be-verified bank statement data is successively subjected to null data removal, duplicate data removal, and format unit adjustment processing to obtain processed statement data.

[0151] The first verification module 2 includes:

[0152] A first extraction sub-module, configured to successively extract the processed statement data of the target company under the same data source to obtain first feature data;

[0153] A complete traversal sub-module, configured to set data integrity rules based on the data standards of each group of the first feature data, and traverse and verify all the first feature data based on the data integrity rules to obtain a traversal result;

[0154] A first complete verification value calculation sub-module, configured to calculate a first complete verification value based on the traversal result :

[0155] ;

[0156] In the formula, represents the total number of data traversed by the data integrity rules, represents the number of data that fails to pass the data integrity rule traversal test;

[0157] A second complete verification value calculation sub-module, configured to extract the company set from the to-be-verified bank statement data and calculate a second complete verification value based on the company set :

[0158] ;

[0159] In the formula, represents the th company in the company set, represents the target company;

[0160] A third complete verification value calculation sub-module, configured to scan the zero-value attribute fields in the first feature data and calculate a third complete verification value based on the zero-value attribute fields :

[0161] ;

[0162] In the formula, , represent the number of data groups and the number of attribute fields in the first feature data, represents the th data group in which there are zero-value attribute fields;

[0163] A first verification sub-module, configured to comprehensively use the first complete verification value , the second complete verification value , the third complete verification value to obtain the first verification value.

[0164] The second verification module 3 includes:

[0165] A second extraction sub-module, configured to sequentially extract the processing flow data of the target company under different data sources to obtain second feature data;

[0166] A comparison sub-module, configured to obtain each data item name under the second feature data, extract the meaning of the data item name and perform meaning comparison in a preset meaning library, and unify the data item names with the same meaning to obtain unified feature data;

[0167] A hash processing sub-module, configured to arbitrarily select a set of data in the unified feature data as reference data, and perform hashing processing on the reference data and the remaining data in the unified feature data to obtain reference hash data and remaining hash data;

[0168] A judgment sub-module, configured to calculate the similarity between the remaining hash data and the reference hash data. If the similarity between the remaining hash data and the reference hash data is not greater than the preset similarity, the unified feature data corresponding to the remaining hash data is excluded. If the similarity between the remaining hash data and the reference hash data is greater than the preset similarity, the unified feature data corresponding to the remaining hash data is retained to obtain retained feature data;

[0169] A first similarity verification value calculation sub-module, configured to calculate a first similarity verification value based on the retained feature data :

[0170] ;

[0171] In the formula, represents the number of data groups in the unified feature data, represents the number of data groups in the retained feature data;

[0172] A dependency traversal sub-module, configured to extract the dependency relationships between each data item of the unified feature data, determine dependency verification rules based on the dependency relationships, and traverse and verify all the unified feature data based on the dependency verification rules to obtain a dependency traversal result;

[0173] A second similarity verification value calculation sub-module, configured to calculate a second similarity verification value based on the dependency traversal result :

[0174] ;

[0175] In the formula, Indicates the number of data covered by traversal of the th dependency verification rule, Indicates the number of data that passed the traversal verification by the th dependency verification rule, Indicates unified feature data;

[0176] The second verification sub-module is used to synthesize the first similarity verification value , the second similarity verification value , to obtain the second verification value.

[0177] The third verification module 4 includes:

[0178] A third extraction sub-module for extracting the processing flow data of the target company in the same data source within a preset time period to obtain third feature data;

[0179] A normalization sub-module for normalizing the third feature data to obtain normalized feature data;

[0180] A graph output sub-module for performing a normalization check on the normalized feature data to obtain a check box plot, identifying and extracting the first abnormal data in the check box plot;

[0181] A clustering sub-module for performing clustering analysis on the third feature data using the K-clustering algorithm to obtain second abnormal data;

[0182] A third verification sub-module for calculating a third verification value based on the first abnormal data and the second abnormal data :

[0183] ;

[0184] In the formula, Indicates the number of data of the third feature data, , respectively represent the first abnormal data and the second abnormal data.

[0185] The fourth verification module 5 includes:

[0186] A fourth extraction sub-module for extracting data of a single dimension of the target company in different data cycles to obtain fourth feature data;

[0187] A time sub-module for obtaining the time stamp of the fourth feature data and determining the set time requirement based on the time stamp;

[0188] A unit verification value calculation sub-module for determining the unit verification value based on the set time requirement :

[0189] ;

[0190] In the formula, represents the total number of data within a unit time, represents the total number of data that meet the set time requirement within a unit time;

[0191] The fourth checksum sub-module is used to determine the fourth checksum value based on the unit checksum value : :

[0192] ;

[0193] In the formula, represents the total number of data cycles.

[0194] In some other embodiments of the present invention, the embodiments of the present invention provide the following technical solution. A computer includes a memory 102, a processor 101, and a computer program stored on the memory 102 and executable on the processor 101. When the processor 101 executes the computer program, the bank statement data verification method described above is implemented.

[0195] Specifically, the above-mentioned processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC for short), or may be configured as one or more integrated circuits for implementing the embodiments of the present invention.

[0196] Among them, the memory 102 may include a mass storage for data or instructions. By way of example and not limitation, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In appropriate cases, the memory 102 may include removable or non-removable (or fixed) media. In appropriate cases, the memory 102 may be internal or external to the data processing device. In a particular embodiment, the memory 102 is non-volatile memory. In a particular embodiment, the memory 102 includes a read-only memory (ROM) and a random access memory (RAM). In appropriate cases, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these. In appropriate cases, the RAM may be a static random-access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM may be a fast page mode dynamic random access memory (FPMDRAM), an extended data out dynamic random access memory (EDODRAM), a synchronous dynamic random-access memory (SDRAM), etc.

[0197] The memory 102 can be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 101.

[0198] The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement the above-mentioned bank statement data verification method.

[0199] In some of the embodiments, the computer may further include a communication interface 103 and a bus 100. Among them, as Figure 3 shown, the processor 101, the memory 102, and the communication interface 103 are connected through the bus 100 and complete communication with each other.

[0200] The communication interface 103 is used to implement communication between the various modules, devices, units, and / or devices in the embodiments of the present invention. The communication interface 103 can also implement data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations, etc.

[0201] Bus 100 includes hardware, software, or both, and couples components of a computer device to each other. Bus 100 includes, but is not limited to, at least one of the following: Data Bus, Address Bus, Control Bus, Expansion Bus, Local Bus. By way of example and not limitation, Bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a Memory Bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable bus or a combination of two or more of these. In a suitable case, Bus 100 may include one or more buses. Although embodiments of the present invention describe and illustrate specific buses, the present invention contemplates any suitable bus or interconnect.

[0202] The computer can execute the bank statement data verification method of the present invention based on the obtained bank statement data verification system, thereby realizing the verification of bank statement data.

[0203] In still some other embodiments of the present invention, in combination with the above bank statement data verification method, embodiments of the present invention provide the following technical solution: a storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above bank statement data verification method is realized.

[0204] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a defined sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus or device), or used in combination with these instruction execution systems, apparatus or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by or in connection with an instruction execution system, apparatus or device.

[0205] More specific examples (non-exhaustive list) of the readable medium include the following: an electrical connection part (electronic device) having one or more wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation or other appropriate processing as necessary, and then stored in a computer memory.

[0206] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0207] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0208] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A method for verifying bank statement data, characterized in that, Including: Obtain the bank statement data to be verified, and preprocess the bank statement data to be verified to obtain processed statement data; Extract the first feature data of the processed statement data, and perform a first verification on the processed statement data based on the first feature data to obtain a first verification value; Wherein, the first feature data is the processed statement data of the target company under the same data source; Extract the second feature data of the processed statement data, and perform a second verification on the processed statement data based on the second feature data to obtain a second verification value; Wherein, the second feature data is the processed statement data of the target company under different data sources; Extract the third feature data of the processed statement data, and perform a third verification on the processed statement data based on the third feature data to obtain a third verification value; Wherein, the third feature data is the processed statement data of the target company within the same data source and a preset time period; Extract the fourth feature data of the processed statement data, and perform a fourth verification on the processed statement data based on the fourth feature data to obtain a fourth verification value; Wherein, the fourth feature data is the data of a single dimension of the target company in different data cycles; Complete the verification of the processed statement data based on the first verification value, the second verification value, the third verification value, and the fourth verification value; The step of extracting the second feature data of the processed statement data and performing a second verification on the processed statement data based on the second feature data to obtain a second verification value includes: Obtain each data item name under the second feature data, extract the meaning of the data item name and perform a meaning comparison in a preset meaning library, and unify the data item names with the same meaning to obtain unified feature data; Arbitrarily select a group of data in the unified feature data as reference data, and perform hashing processing on the reference data and the remaining data in the unified feature data to obtain reference hash data and remaining hash data; Calculate the similarity between the remaining hash data and the reference hash data. If the similarity between the remaining hash data and the reference hash data is not greater than the preset similarity, the unified feature data corresponding to the remaining hash data is excluded. If the similarity between the remaining hash data and the reference hash data is greater than the preset similarity, the unified feature data corresponding to the remaining hash data is retained to obtain retained feature data; Calculate a first similarity verification value based on the retained feature data : ； In the formula, represents the number of data groups in the unified feature data, represents the number of data groups in the retained feature data; Extract the dependency relationship between each data item of the unified feature data, determine the dependency verification rule based on the dependency relationship, and traverse and verify all the unified feature data based on the dependency verification rule to obtain a dependency traversal result; Calculate a second similarity verification value based on the dependency traversal result : ； In the formula, represents the number of data covered by traversing and covering with the th dependency verification rule, represents the number of data that pass the traversal and verification by the th dependency verification rule, represents unified feature data; Integrated first similarity verification value and second similarity verification value to obtain a second verification value.

2. The bank statement data verification method according to claim 1, wherein The step of obtaining the bank statement data to be verified and preprocessing the bank statement data to be verified to obtain processed statement data includes: Successively perform null value data removal, duplicate data removal, and format unit adjustment processing on the bank statement data to be verified to obtain processed statement data.

3. The bank statement data verification method according to claim 1, wherein The step of extracting the first feature data of the processed statement data and performing a first verification on the processed statement data based on the first feature data to obtain a first verification value includes: Set data integrity rules based on the data standards of each group of the first feature data, and traverse and verify all the first feature data based on the data integrity rules to obtain a traversal result; Calculate a first complete verification value based on the traversal result : ； In the formula, represents the total number of data traversed by the data integrity rule, represents the number of data that fails to pass the data integrity rule traversal test; Extract the company set from the bank statement data to be verified, and calculate the second complete verification value based on the company set : ； In the formula, represents the -th company in the company set, represents the target company; Scan the zero-value attribute field in the first feature data, and calculate the third complete verification value based on the zero-value attribute field : ； In the formula, , represent the number of data groups and the number of attribute fields in the first feature data, represents the th data group where there are zero-valued attribute fields; Comprehensive first complete verification value , second complete verification value , third complete verification value to obtain the first verification value.

4. The bank statement data verification method according to claim 1, wherein The step of extracting the third feature data of the processing flow data and performing a third verification on the processing flow data based on the third feature data to obtain a third verification value includes: Perform normalization processing on the third feature data to obtain normalized feature data; Perform normalization verification on the normalized feature data to obtain a verification box plot, identify and extract the first abnormal data in the verification box plot; Use the K-clustering algorithm to perform clustering analysis on the third feature data to obtain second abnormal data; Calculate a third verification value based on the first abnormal data and the second abnormal data .

5. The bank statement data verification method according to claim 1, characterized in that The step of extracting the fourth feature data of the processing flow data and performing a fourth verification on the processing flow data based on the fourth feature data to obtain a fourth verification value includes: Obtain the time stamp of the fourth feature data, and determine the set time requirement based on the time stamp; Determine a unit check value based on the set time requirement : ； Wherein, represents the total number of data within a unit time, represents the total number of data that meet the set time requirement within a unit time; Based on the unit check value Determine the fourth check value : ； In the formula, represents the total number of data cycles.

6. A bank statement data verification system, which uses the bank statement data verification method described in claim 1 to verify bank statement data, characterized in that, The system includes: A processing module, configured to obtain bank statement data to be verified, and perform preprocessing on the bank statement data to be verified to obtain processing flow data; A first verification module, configured to extract the first feature data of the processing flow data, and perform a first verification on the processing flow data based on the first feature data to obtain a first verification value; A second verification module, configured to extract the second feature data of the processing flow data, and perform a second verification on the processing flow data based on the second feature data to obtain a second verification value; A third verification module, configured to extract the third feature data of the processing flow data, and perform a third verification on the processing flow data based on the third feature data to obtain a third verification value; A fourth verification module, configured to extract the fourth feature data of the processing flow data, and perform a fourth verification on the processing flow data based on the fourth feature data to obtain a fourth verification value; A final verification module, configured to complete the verification of the processing flow data based on the first verification value, the second verification value, the third verification value, and the fourth verification value.

7. The bank statement data verification system according to claim 6, wherein The processing module is specifically configured to: Successively perform null value data removal, duplicate data removal, and format unit adjustment processing on the bank statement data to be verified to obtain processing flow data.

8. A computer, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the bank statement data verification method according to any one of claims 1 to 5.

9. A storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is executed by the processor, it implements the bank statement data verification method according to any one of claims 1 to 5.

Images