Problem data and its link tracing method and device

Abstract

The application provides a problem data and a link tracing method and device thereof, relates to the technical field of data processing, and can be applied to the financial field or other technical fields.The method comprises the following steps: acquiring source data, identifying the integrity of the source data, determining a target data type corresponding to data with data loss if it is determined that there is at least one type of data with data loss, performing correlation analysis on target data corresponding to the target data type to obtain target data correlation data associated with the target data, determining that the target data is problem data, and determining that the correlation between the target data and the target data correlation data is a problem data link.The device executes the above method.The method and device provided in the embodiment of the application can comprehensively acquire problem data and problem data links from the root cause, and further simply and quickly find business risks.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method and apparatus for tracing problematic data and its links. Background Technology

[0002] Currently, when relevant regulatory departments conduct law enforcement data inspections, they first manually develop inspection rules using SQL statements in a database, then run the inspection rules on the data tables to be inspected, and finally output the problematic data between the fields of each table.

[0003] The aforementioned method of manually developing inspection rules using database SQL statements requires developing inspection rules one by one for each field of each table, which is inefficient. Furthermore, the problem data obtained consists of individual data records in each table, making it impossible for inspectors and financial institution personnel to have a macro-level understanding of the risk points and hierarchical chains of each problem in the problem data. As a result, financial institutions are unable to grasp the main problems or trace the source during the rectification process of the problem data. Summary of the Invention

[0004] To address the problems in the prior art, embodiments of the present invention provide a method and apparatus for tracing problematic data and its links, which can at least partially solve the problems existing in the prior art.

[0005] On the one hand, this invention proposes a method for tracing problematic data and its links, including:

[0006] Acquire source data and verify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data.

[0007] If it is determined that there is missing data for at least one data type, then determine the target data type corresponding to the missing data.

[0008] A correlation analysis is performed on the target data corresponding to the target data type to obtain the target data association data associated with the target data, and the target data is determined to be problem data, and the association relationship between the target data and the target data association data is determined to be the problem data link.

[0009] The step of identifying the integrity of the source data includes:

[0010] Identify a preset data missing marker in the source data; the preset data missing marker is a preset character symbol generated in advance in the source data to indicate data missing.

[0011] If the preset data missing marker is identified, the location of the preset data missing marker is determined as the data missing location, and the data corresponding to the data missing location is taken as the missing data.

[0012] The determination of the target data type corresponding to the data with missing data includes:

[0013] The target data type is determined by the data type corresponding to the missing data location.

[0014] The step of performing correlation analysis on target data corresponding to the target data type includes:

[0015] Based on a preset association analysis model, association analysis is performed on the target data corresponding to the target data type;

[0016] The preset association analysis model is obtained by training an association rule mining algorithm based on sample data.

[0017] The preset association analysis model is obtained by training an association rule mining algorithm based on sample data, including:

[0018] Initialize the parameters for association rule mining and mine the association rules between sample data;

[0019] The association rules obtained through mining are analyzed to obtain the mining rule results;

[0020] The mining rule results are verified. If the verification results meet the preset algorithm training termination condition, the training of the association rule mining algorithm is completed to obtain the preset association analysis model.

[0021] The problematic data and its tracing method further include:

[0022] If the verification result does not meet the preset algorithm training termination condition, the association rule mining parameters are optimized and adjusted, and the optimized association rule mining parameters are used to mine the association rules between the sample data. Subsequent steps are then executed until the verification result meets the preset algorithm training termination condition.

[0023] The problematic data and its tracing method further include:

[0024] Based on the fusion model, the source data is identified for integrity and correlation analysis is performed to obtain the problematic data and the problematic data link.

[0025] The fusion model includes a data integrity identification model connected in series with the preset association analysis model; the data integrity identification model is a pre-trained text semantic model, and the output of the data integrity identification model serves as the input of the preset association analysis model.

[0026] On one hand, the present invention proposes a problem data and its link tracing device, comprising:

[0027] The acquisition unit is used to acquire source data and identify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data.

[0028] The determining unit is used to determine the target data type corresponding to the missing data if it is determined that there is data missing for at least one data type.

[0029] The tracing unit is used to perform correlation analysis on target data corresponding to the target data type, obtain target data association data associated with the target data, determine that the target data is problem data, and determine the correlation relationship between the target data and the target data association data as a problem data link.

[0030] In another aspect, embodiments of the present invention provide an electronic device, including: a processor, a memory, and a bus, wherein,

[0031] The processor and the memory communicate with each other via the bus;

[0032] The memory stores program instructions that can be executed by the processor, and the processor can execute the following methods by calling the program instructions:

[0033] Acquire source data and verify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data.

[0034] If it is determined that there is missing data for at least one data type, then determine the target data type corresponding to the missing data.

[0035] A correlation analysis is performed on the target data corresponding to the target data type to obtain the target data association data associated with the target data, and the target data is determined to be problem data, and the association relationship between the target data and the target data association data is determined to be the problem data link.

[0036] This invention provides a non-transitory computer-readable storage medium, comprising:

[0037] The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the following methods:

[0038] Acquire source data and verify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data.

[0039] If it is determined that there is missing data for at least one data type, then determine the target data type corresponding to the missing data.

[0040] A correlation analysis is performed on the target data corresponding to the target data type to obtain the target data association data associated with the target data, and the target data is determined to be problem data, and the association relationship between the target data and the target data association data is determined to be the problem data link.

[0041] The present invention provides a problem data and its link tracing method and apparatus, which acquire source data and identify the integrity of the source data. The data types of the source data include customer basic information data, customer account information data, and customer transaction information data. If it is determined that data of at least one data type is missing, a target data type corresponding to the missing data is determined. Correlation analysis is performed on the target data corresponding to the target data type to obtain target data associated with the target data, and the target data is determined to be problem data. The relationship between the target data and the target data associated with the target data is determined to be a problem data link. This allows for comprehensive acquisition of problem data and problem data links from the root, thereby enabling simple and quick discovery of business risks. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0043] Figure 1 This is a flowchart illustrating the problem data and its link tracing method provided in an embodiment of the present invention.

[0044] Figure 2 This is a flowchart illustrating the problem data and its link tracing method provided in another embodiment of the present invention.

[0045] Figure 3 This is a schematic diagram illustrating the fusion model provided in an embodiment of the present invention.

[0046] Figure 4 This is a schematic diagram of the structure of the problem data and its link tracing device provided in an embodiment of the present invention.

[0047] Figure 5 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments and descriptions of the present invention are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0049] Explanation of relevant terms:

[0050] Problematic data: During law enforcement inspections, regulatory authorities discovered data in financial institutions' customer, account, and transaction data that did not conform to data integrity or business logic.

[0051] Association: When there is a certain regularity in the values ​​of two or more variables, it is called association.

[0052] Association analysis: Identifying relationships between data items in a dataset, exploring and extracting valuable knowledge describing the relationships between data items from large amounts of data, i.e., discovering association rules or degrees of correlation between things. If A occurs, then B has a 100% chance of occurring (C), where C is called the confidence level of the association rule.

[0053] Figure 1 This is a flowchart illustrating the problem data and its link tracing method provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the problem data and its link tracing method provided in this embodiment of the invention include:

[0054] Step S1: Obtain source data and verify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data.

[0055] Step S2: If it is determined that there is missing data for at least one data type, then determine the target data type corresponding to the missing data.

[0056] Step S3: Perform correlation analysis on the target data corresponding to the target data type to obtain the target data association data associated with the target data, determine that the target data is problem data, and determine the association relationship between the target data and the target data association data as the problem data link.

[0057] In step S1 above, the device acquires source data and verifies the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data. The device can be a computer device executing the method, for example, it may include a server. It should be noted that the acquisition and analysis of data involved in this embodiment of the invention are authorized by the user.

[0058] The source data conforms to the data format required by regulatory authorities and includes data records from financial institutions. This may include 15 interface specification tables from document No. 300 of a certain regulatory authority. Tables 3 and 4 store basic information for natural persons and non-natural persons, respectively; Table 5 contains customer account information; Tables 6-10 contain customer transaction information; and Table 13 contains customer online verification information. The basic information for natural persons and non-natural persons includes the following elements. If any of these elements are filled with @N, null, unknown, none, or temporarily unavailable, the element is considered incomplete.

[0059] The nine basic information elements for natural person customers include customer name, gender, nationality (region), occupation, address of residence or work unit, contact information, type of identification document, identification document number, and expiration date of identification document.

[0060] The 19 basic information elements for non-natural person customers include: customer name, address, business scope, name of the legally established or operating license, number of the legally established or operating license, expiration date of the legally established or operating license, name of the legal representative or person in charge, type of identification document of the legal representative or person in charge, number of identification document of the legal representative or person in charge, expiration date of the validity period of the identification document of the legal representative or person in charge, name of the authorized person handling the business, type of identification document of the authorized person handling the business, number of identification document of the authorized person handling the business, expiration date of the validity period of the identification document of the authorized person handling the business, name of the beneficial owner, address of the beneficial owner, type of identification document of the beneficial owner, number of identification document of the beneficial owner, and validity period of the identification document of the beneficial owner.

[0061] The specific details of customer account information data and customer transaction information data will not be elaborated further.

[0062] The process of identifying the integrity of the source data includes:

[0063] Identify a preset data missing marker in the source data; the preset data missing marker is a preset character symbol generated in advance in the source data to indicate data missing; the preset data missing marker may include @N, null, unknown, none, not available, etc.

[0064] If the preset data missing marker is identified, the location of the preset data missing marker is determined as the data missing location, and the data corresponding to the data missing location is taken as the missing data. For a data table, the data missing location may include the i-th row and j-th column of the data in the table.

[0065] In step S2 above, if the device determines that at least one data type has missing data, it then determines the target data type corresponding to the missing data. An example is given below:

[0066] If there are missing data in the customer basic information data, the target data type is the customer basic information data.

[0067] If both customer basic information data and customer account information data are missing, then the target data type is customer basic information data and customer account information data.

[0068] The determination of the target data type corresponding to the data with missing data includes:

[0069] The target data type is determined by the data type corresponding to the missing data location. Referring to the above explanation, if the data type corresponding to the data in row i and column j of table A is customer basic information, then the target data type is customer basic information.

[0070] In step S3 above, the device performs association analysis on the target data corresponding to the target data type to obtain target data association data associated with the target data, determines that the target data is problem data, and determines the association relationship between the target data and the target data association data as a problem data link. The association analysis on the target data corresponding to the target data type includes:

[0071] Based on a preset association analysis model, association analysis is performed on the target data corresponding to the target data type. The entire source data can be input into the preset association analysis model, and the output of the model is used as the association analysis result, thus obtaining the problem data and the problem data link. If the data corresponding to the i-th row and j-th column in Table A is target data a1, then the associated data can be the data corresponding to the p-th row and q-th column in Customer Account Information Data Table B, and the association between a1 and b1 is the problem data link.

[0072] The preset association analysis model is obtained by training an association rule mining algorithm based on sample data. The association rule mining algorithm can be selected as the Apriori algorithm.

[0073] Based on specific business operations, customers with incomplete information are linked to their accounts and transactions. Non-compliant account opening and transaction data are analyzed. Non-compliant account openings include opening accounts despite expired documents and failing to conduct online verification on the same day a natural person opens a Class I, II, or III account. Non-compliant transactions include payment transactions occurring despite expired documents, incomplete remittance and payee information in cross-border remittances, and failure to conduct online verification of customers and agents when a single cash deposit or withdrawal exceeds 50,000 RMB on the same day. Finally, the non-compliant problem data is output, forming a problem data chain.

[0074] like Figure 2 As shown, the preset association analysis model is obtained by training an association rule mining algorithm based on sample data, including:

[0075] Initialize the association rule mining parameters and mine the association rules between sample data; initializing the association rule mining parameters may specifically include giving initial association rule mining parameter values, etc.

[0076] Obtaining sample data may include:

[0077] The source data is processed, and incomplete customer information elements are used as sample customer data. Transaction data and other data are processed in the same way. Association rules may vary depending on the actual business type and will not be specified further.

[0078] The association rules obtained from the mining are analyzed to obtain the mining rule results; the association rule analysis may vary depending on the actual business type, and will not be described in detail here.

[0079] The mining rule results are verified. If the verification results meet the preset algorithm training termination condition, the training of the association rule mining algorithm is completed, and the preset association analysis model is obtained. Verifying the mining rule results may include:

[0080] The results of the mining rules are compared with the expected results of the mining rules. If the comparison error is within the preset error threshold, it means that the verification result meets the preset algorithm training termination condition. The association rule mining parameters at this time are used as the weight values ​​for model training to complete the model training.

[0081] The problem data and its tracing methods also include:

[0082] If the verification result does not meet the preset algorithm training termination condition, the association rule mining parameters are optimized and adjusted, and the optimized and adjusted association rule mining parameters are used to mine association rules between sample data. Subsequent steps are then executed until the verification result meets the preset algorithm training termination condition. The preset algorithm training termination condition may include the above-mentioned training termination condition based on error judgment, and is not specifically limited thereto.

[0083] like Figure 3 As shown, the problem data and its link tracing method also include:

[0084] Based on the fusion model, the source data is subjected to integrity identification and correlation analysis to obtain the problem data and the problem data link; the source data is input into the fusion model, integrity identification is achieved through the content of the fusion model, and the output of the fusion model is used as the problem data and the problem data link.

[0085] The fusion model includes a data integrity identification model connected in series with the preset association analysis model. The data integrity identification model is a pre-trained text semantic model, and its output serves as the input to the preset association analysis model. The text semantic model can be a conventional text semantic model. The method for training the text semantic model can be a conventional text semantic model training method.

[0086] The correlation analysis is explained below in conjunction with specific business content:

[0087] (1) Correlation analysis of document expiration

[0088] For the same customer number, the ID document in Table 3 has expired => there are records of opening Class I, II, and III accounts in Table 5; and there are payment transaction records in Table 6.

[0089] The same customer number has an expired license in Table 4 for legally established or operating businesses => there are records of account openings in Table 5; there are records of payment transactions in Table 6.

[0090] For the same customer number, if the legal representative or person in charge's ID document in Table 4 has expired, there is a record of opening an account in Table 5; for customers in Table 5 who are not NRA accounts, there are payment transaction records in Table 6.

[0091] (2) Correlation analysis of account opening

[0092] There were no online verification records in Table 13 for the day that natural persons opened Class I, II, and III accounts in Table 5.

[0093] Table 6 shows that when a single cash deposit or withdrawal at the counter exceeds 50,000 RMB on a given day, there are no online verification records for the customer and agent (if any) listed in Table 13.

[0094] (3) Correlation analysis of the completeness of cross-border remittance information

[0095] Table 7 shows that when making cross-border remittances, the remitter's name, account number, address, and the recipient's name and account information are incomplete.

[0096] The problem data and its link tracing method provided in this embodiment of the invention offer an efficient method for discovering problem data and the hierarchical relationships between links, and for predicting business risks of financial institutions in advance.

[0097] The technical solution of this invention eliminates the need for manual SQL development, improving the efficiency of law enforcement inspections by regulatory personnel. This method can also be flexibly applied to the enforcement data inspection of non-bank financial institutions such as the securities, insurance, and payment industries, as well as the discovery of problematic data within all financial institutions, enabling them to quickly and easily identify business risks.

[0098] The present invention provides a problem data and its link tracing method, which acquires source data and identifies the integrity of the source data. The data types of the source data include customer basic information data, customer account information data, and customer transaction information data. If it is determined that data of at least one data type is missing, a target data type corresponding to the missing data is determined. Correlation analysis is performed on the target data corresponding to the target data to obtain target data associated with the target data, and the target data is determined to be problem data. The relationship between the target data and the target data associated with the target data is determined to be a problem data link. This method can comprehensively acquire problem data and problem data links from the root, thereby easily and quickly discovering business risks.

[0099] Furthermore, identifying the integrity of the source data includes:

[0100] Identify a preset data missing marker in the source data; the preset data missing marker is a preset character symbol generated in advance in the source data to indicate data missingness; refer to the above description, and will not be repeated here.

[0101] If the preset data missing marker is identified, the location of the preset data missing marker is determined as the data missing location, and the data corresponding to the data missing location is taken as the missing data. This can be referred to the above explanation and will not be repeated here.

[0102] The problematic data and its traceability method provided in this invention can quickly and easily identify the integrity of the source data.

[0103] Furthermore, determining the target data type corresponding to the data with missing data includes:

[0104] The target data type is determined by the data type corresponding to the missing data location. This can be referred to the above explanation and will not be repeated here.

[0105] The problem data and its link tracing method provided in this embodiment of the invention can accurately determine the target data type.

[0106] Furthermore, the association analysis of the target data corresponding to the target data type includes:

[0107] The target data corresponding to the target data type is analyzed based on the preset association analysis model; the above description is provided and will not be repeated here.

[0108] The preset association analysis model is obtained by training an association rule mining algorithm based on sample data. This can be referred to the above description and will not be repeated here.

[0109] The problem data and its link tracing method provided in this embodiment of the invention can accurately perform data correlation analysis through a preset correlation analysis model.

[0110] Further, the preset association analysis model is obtained by training an association rule mining algorithm based on the sample data, including:

[0111] Initialize the parameters for association rule mining and mine the association rules between sample data; refer to the above instructions, which will not be repeated here.

[0112] The association rules obtained from the mining are analyzed to obtain the mining rule results; please refer to the above explanation, which will not be repeated here.

[0113] The mining rule results are verified. If the verification results meet the preset algorithm training termination condition, the training of the association rule mining algorithm is completed, and the preset association analysis model is obtained. Refer to the above description; further details are omitted.

[0114] The problem data and its link tracing method provided in this embodiment of the invention can ensure the accuracy of the model output results by training a preset correlation analysis model.

[0115] Furthermore, the problem data and its link tracing method also include:

[0116] If the verification result does not meet the preset algorithm training termination condition, the association rule mining parameters are optimized and adjusted, and the optimized association rule mining parameters are used to mine association rules between sample data. Subsequent steps are then executed until the verification result meets the preset algorithm training termination condition. This can be referred to the above description and will not be repeated here.

[0117] The problem data and its link tracing method provided in the embodiments of the present invention can further ensure the accuracy of the model output results.

[0118] Furthermore, the problem data and its link tracing method also include:

[0119] Based on the fusion model, the source data is used for integrity identification and correlation analysis to obtain the problematic data and the problematic data links; please refer to the above description, which will not be repeated here.

[0120] The fusion model includes a data integrity identification model connected in series with the preset association analysis model; the data integrity identification model is a pre-trained text semantic model, and the output of the data integrity identification model serves as the input of the preset association analysis model. This can be referred to the above description and will not be repeated here.

[0121] The problematic data and its link tracing method provided in this invention further improve the overall processing efficiency of data integrity identification and data correlation analysis.

[0122] It should be noted that the problem data and its link tracing method provided in the embodiments of the present invention can be used in the financial field, or in any technical field other than the financial field. The embodiments of the present invention do not limit the application field of problem data and its link tracing method.

[0123] Figure 4 This is a schematic diagram of the structure of the problem data and its link tracing device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the problem data and its link tracing device provided in this embodiment of the invention include an acquisition unit 401, a determination unit 402, and a tracing unit 403, wherein:

[0124] The acquisition unit 401 is used to acquire source data and identify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data; the determination unit 402 is used to determine the target data type corresponding to the data with missing data if it is determined that at least one data type has missing data; the tracing unit 403 is used to perform correlation analysis on the target data corresponding to the target data type, obtain the target data associated with the target data, determine that the target data is problematic data, and determine that the correlation between the target data and the target data associated data is a problematic data link.

[0125] Specifically, the acquisition unit 401 in the device is used to acquire source data and identify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data; the determination unit 402 is used to determine the target data type corresponding to the data with missing data if it is determined that at least one data type has missing data; the tracing unit 403 is used to perform correlation analysis on the target data corresponding to the target data type, obtain the target data associated with the target data, determine that the target data is problematic data, and determine that the correlation between the target data and the target data associated data is a problematic data link.

[0126] The problem data and its link tracing device provided in this embodiment of the invention acquires source data and identifies the integrity of the source data. The data types of the source data include customer basic information data, customer account information data, and customer transaction information data. If it is determined that data corresponding to at least one data type is missing, a target data type corresponding to the missing data is determined. Correlation analysis is performed on the target data corresponding to the target data type to obtain target data associated with the target data, and the target data is determined to be problem data. The relationship between the target data and the target data associated with the target data is determined to be a problem data link. This allows for comprehensive acquisition of problem data and problem data links from the root, thereby easily and quickly identifying business risks.

[0127] Furthermore, the acquisition unit 401 is specifically used for:

[0128] Identify a preset data missing marker in the source data; the preset data missing marker is a preset character symbol generated in advance in the source data to indicate data missing.

[0129] If the preset data missing marker is identified, the location of the preset data missing marker is determined as the data missing location, and the data corresponding to the data missing location is taken as the missing data.

[0130] The problem data and its traceability device provided in this embodiment of the invention can quickly and easily identify the integrity of the source data.

[0131] Furthermore, the determining unit 402 is specifically used for:

[0132] The target data type is determined by the data type corresponding to the missing data location.

[0133] The problem data and its link tracing device provided in this embodiment of the invention can accurately determine the target data type.

[0134] Furthermore, the traceability unit 403 is specifically used for:

[0135] Based on a preset association analysis model, association analysis is performed on the target data corresponding to the target data type;

[0136] The preset association analysis model is obtained by training an association rule mining algorithm based on sample data.

[0137] The problem data and its link tracing device provided in this embodiment of the invention can accurately perform data correlation analysis through a preset correlation analysis model.

[0138] Furthermore, the problem data and its link tracing device are also used for:

[0139] Initialize the parameters for association rule mining and mine the association rules between sample data;

[0140] The association rules obtained through mining are analyzed to obtain the mining rule results;

[0141] The mining rule results are verified. If the verification results meet the preset algorithm training termination condition, the training of the association rule mining algorithm is completed to obtain the preset association analysis model.

[0142] The problem data and its link tracing device provided in this embodiment of the invention can obtain a preset correlation analysis model through training, which can ensure the accuracy of the model output results.

[0143] Furthermore, the problem data and its link tracing device are also used for:

[0144] If the verification result does not meet the preset algorithm training termination condition, the association rule mining parameters are optimized and adjusted, and the optimized association rule mining parameters are used to mine the association rules between the sample data. Subsequent steps are then executed until the verification result meets the preset algorithm training termination condition.

[0145] The problem data and its link tracing device provided in this embodiment of the invention can further ensure the accuracy of the model output results.

[0146] Furthermore, the problem data and its link tracing device are also used for:

[0147] Based on the fusion model, the source data is identified for integrity and correlation analysis is performed to obtain the problematic data and the problematic data link.

[0148] The fusion model includes a data integrity identification model connected in series with the preset association analysis model; the data integrity identification model is a pre-trained text semantic model, and the output of the data integrity identification model serves as the input of the preset association analysis model.

[0149] The problematic data and its link tracing device provided in this embodiment of the invention further improve the overall processing efficiency of data integrity identification and data correlation analysis.

[0150] The embodiments of the present invention provide problem data and its link tracing device, which can be used to execute the processing flow of the above method embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the above method embodiments.

[0151] Figure 5 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 5 As shown, the electronic device includes: a processor 501, a memory 502, and a bus 503;

[0152] The processor 501 and the memory 502 communicate with each other via the bus 503.

[0153] The processor 501 is used to call program instructions in the memory 502 to execute the methods provided in the above-described method embodiments, including, for example:

[0154] Acquire source data and verify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data.

[0155] If it is determined that there is missing data for at least one data type, then determine the target data type corresponding to the missing data.

[0156] A correlation analysis is performed on the target data corresponding to the target data type to obtain the target data association data associated with the target data, and the target data is determined to be problem data, and the association relationship between the target data and the target data association data is determined to be the problem data link.

[0157] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can perform the methods provided in the above-described method embodiments, such as:

[0158] Acquire source data and verify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data.

[0159] If it is determined that there is missing data for at least one data type, then determine the target data type corresponding to the missing data.

[0160] A correlation analysis is performed on the target data corresponding to the target data type to obtain the target data association data associated with the target data, and the target data is determined to be problem data, and the association relationship between the target data and the target data association data is determined to be the problem data link.

[0161] This embodiment provides a computer-readable storage medium storing a computer program that causes the computer to execute the methods provided in the above-described method embodiments, including, for example:

[0162] Acquire source data and verify the integrity of the source data; the data types of the source data include customer basic information data, customer account information data, and customer transaction information data.

[0163] If it is determined that there is missing data for at least one data type, then determine the target data type corresponding to the missing data.

[0164] A correlation analysis is performed on the target data corresponding to the target data type to obtain the target data association data associated with the target data, and the target data is determined to be problem data, and the association relationship between the target data and the target data association data is determined to be the problem data link.

[0165] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0166] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0167] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0168] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0169] In the description of this specification, the references to terms such as "an embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0170] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A problem data and its link tracing method, characterized by, The method comprises the following steps: acquiring source data and identifying the integrity of the source data; the data types of the source data comprise customer basic information data, customer account information data and customer transaction information data; if it is determined that there is data missing corresponding to at least one data type, a target data type corresponding to the data with data missing is determined; correlation analysis is performed on target data corresponding to the target data type, target data correlation data associated with the target data is obtained, the target data is determined to be problem data, and the association relationship between the target data and the target data correlation data is determined to be a problem data link; wherein the correlation analysis of the target data corresponding to the target data type comprises: correlation analysis of the target data corresponding to the target data type is performed based on a preset correlation analysis model; wherein the method further comprises: performing integrity identification and correlation analysis on the source data based on a fusion model to obtain problem data and a problem data link; wherein the fusion model comprises a data integrity identification model connected in series with the preset correlation analysis model; the data integrity identification model is a pre-trained text semantic model, and the output result of the data integrity identification model is used as an input item of the preset correlation analysis model; the correlation analysis of the target data corresponding to the target data type comprises: initializing correlation rule mining parameters and mining the correlation rules between sample data; analyzing the mined correlation rules to obtain a mining rule result; verifying the mining rule result, and if it is determined that the verification result meets a preset algorithm training termination condition, the training correlation rule mining algorithm is completed to obtain the preset correlation analysis model.

2. The problem data and its link tracing method according to claim 1, wherein, The integrity of the source data is identified, comprising: identifying a preset data missing marker in the source data; the preset data missing marker is a preset character symbol generated in advance in the source data and used to indicate data missing; if it is determined that the preset data missing marker is identified, the position of the preset data missing marker is determined to be a data missing position, and the data corresponding to the data missing position is determined to be data missing.

3. The problem data and its link tracing method according to claim 2, wherein, The target data type corresponding to the data with data missing is determined, comprising: the data type corresponding to the data corresponding to the data missing position is determined to be the target data type.

4. The problem data and its link tracing method according to claim 1, wherein, The problem data and its link tracing method further comprises: if it is determined that the verification result does not meet the preset algorithm training termination condition, the correlation rule mining parameters are optimized and adjusted, the correlation rules between sample data are mined using the optimized and adjusted correlation rule mining parameters, and subsequent steps are executed until it is determined that the verification result meets the preset algorithm training termination condition.

5. A problem data and its link tracing apparatus, characterized by, The method comprises the following steps: an acquisition unit is configured to acquire source data and identify the integrity of the source data; the data types of the source data comprise customer basic information data, customer account information data and customer transaction information data; The determining unit is configured to determine a target data type corresponding to data with missing data if it is determined that there is data missing corresponding to at least one data type; The tracing unit is configured to perform association analysis on target data corresponding to the target data type to obtain target data association data associated with the target data, and determine that the target data is problem data and that an association relationship between the target data and the target data association data is a problem data link; The tracing unit is configured to perform association analysis on target data corresponding to the target data type based on a preset association analysis model. The problem data and link tracing apparatus is further configured to perform integrity identification and association analysis on the source data based on a fusion model to obtain problem data and problem data links; the fusion model includes a data integrity identification model connected in series with the preset association analysis model; the data integrity identification model is a pre-trained text semantic model, and an output result of the data integrity identification model is used as an input item of the preset association analysis model. The tracing unit is configured to initialize association rule mining parameters, mine association rules between sample data, analyze the mined association rules to obtain mining rule results, and verify the mining rule results; if it is determined that a verification result satisfies a preset algorithm training termination condition, training of an association rule mining algorithm is completed to obtain the preset association analysis model.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 4.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 4.

Images