Scene determination method and device, storage medium and electronic device

Abstract

The invention discloses a scene determination method and device, a storage medium and an electronic device.The scene determination method comprises the steps that a feature scene library corresponding to multiple error scenes is established, and the feature scene library comprises the multiple error scenes sequentially arranged according to scene priorities corresponding to the multiple error scenes and the multiple error scenes corresponding to the scene priorities corresponding to the multiple error scenes; each scene recognition statement corresponds to each error scene; the scene recognition statements in the feature scene library are sequentially executed according to the scene priorities, data marking is carried out on each row of error data which are not marked in an error data detail list according to each scene recognition statement, and first identification information of each row of error data is obtained, the first identification information is used for indicating a scene identification of a target error scene corresponding to each row of error data; and determining a target error scene corresponding to each row of error data according to the first identification information.

Description

Technical Field

[0001] This application relates to the field of data analysis, and more specifically, to a method and apparatus for determining a scenario, a storage medium, and an electronic device. Background Technology

[0002] Regulatory data reporting and analysis involves collecting, organizing, verifying, and reporting various types of business data in accordance with regulatory requirements. To this end, a data governance system should be established and improved, the responsibilities of the data governance department should be clearly defined, and the accuracy and completeness of the data should be ensured. At the same time, self-inspection and resolution of key issues of regulatory concern are necessary. With increasingly stringent regulatory requirements, related technologies face challenges in areas such as data quality, system upgrades, and reporting efficiency.

[0003] Currently, most regulatory verification errors are handled through manual sampling and analysis. During scenario analysis, there's a risk of duplicate labeling of data. This means that manual analysis requires repeated data analysis, identification, and removal, and these steps must be repeated even after acquiring new batches of data. Furthermore, there are no effective methods for removing outdated historical data or data that cannot be rectified due to historical reasons but still requires continuous reporting. This necessitates repeated analysis, resulting in wasted manpower, low efficiency, and low accuracy in identifying scenarios with erroneous data.

[0004] Therefore, in the process of scene recognition of erroneous data, there is a problem that the erroneous data may be repeatedly labeled, resulting in low accuracy of scene recognition of erroneous data.

[0005] There is no effective solution yet to address the issue that in the process of scene recognition of erroneous data, erroneous data may be repeatedly labeled, resulting in low accuracy of scene recognition of erroneous data. Summary of the Invention

[0006] This application provides a method and apparatus for determining a scene, a storage medium, and an electronic device to at least solve the problem in related technologies where erroneous data may be repeatedly labeled during the scene recognition process, resulting in low accuracy in scene recognition of erroneous data.

[0007] According to one embodiment of this application, a method for determining a scenario is provided, comprising: establishing a feature scenario library corresponding to multiple error scenarios, wherein the feature scenario library includes: multiple error scenarios arranged sequentially according to the scenario priority corresponding to the multiple error scenarios, and a scenario identification statement corresponding to each error scenario; executing each scenario identification statement in the feature scenario library sequentially according to the scenario priority, so as to mark each unmarked row of error data in the error data detail table according to the scenario identification statement, to obtain first identification information of each row of error data, wherein the first identification information is used to indicate the scenario identifier of the target error scenario corresponding to each row of error data; and determining the target error scenario corresponding to each row of error data according to the first identification information.

[0008] In an exemplary embodiment, each scene identification statement in the feature scene library is executed sequentially according to the scene priority to mark each unmarked row of error data in the error data detail table according to the scene identification statement, thereby obtaining first identification information for each row of error data. This includes: executing the first scene identification statement in the feature scene library to mark the first error data in the error data detail table according to the first scene identification statement, thereby obtaining second identification information for the first error data. The first scene identification statement is the scene identification statement corresponding to the first error scene with the first scene priority in the feature scene library, and the order of scene priorities is: first scene priority, second scene priority, ..., nth scene. The scene priority is determined, the first error data is the error data corresponding to the first error scenario in the error data detail table; the second error data in the error data detail table is determined, and the nth scene recognition statement in the feature scene library is executed to mark the second error data according to the nth scene recognition statement to obtain the third identification information of the second error data, where n is 2, 3, ..., n in sequence, the second error data is the error data of the unmarked target row in the error data detail table after executing the (n-1)th scene recognition statement, the nth scene recognition statement is the scene recognition statement corresponding to the nth error scenario with the nth scene priority in the feature scene library, and the first identification information includes: the second identification information and the third identification information.

[0009] In an exemplary embodiment, before executing each scene recognition statement in the feature scene library sequentially according to the scene priority, the method further includes: performing data verification on each row of target reporting data in the target reporting data detail table according to preset verification rules to determine the verification result corresponding to each row of target reporting data; determining one or more erroneous data in the target reporting data detail table according to the verification result; and performing data statistics on the one or more erroneous data to generate the erroneous data detail table.

[0010] In an exemplary embodiment, establishing a feature scenario library corresponding to multiple error scenarios includes: obtaining multiple historical error data that failed data verification from historical reporting data, and obtaining each first error scenario corresponding to each historical error data; configuring a first scenario identification statement corresponding to each first error scenario, and determining the scenario priority of each first error scenario; establishing a first mapping relationship between the arranged first scenario identification statements and each first error scenario; determining multiple first error scenarios as multiple error scenarios in the feature scenario library, and establishing the feature scenario library according to the scenario priority and the first mapping relationship, wherein the identification statements in the feature scenario library include: multiple first scenario identification statements.

[0011] In an exemplary embodiment, determining the scenario priority of each first error scenario includes: extracting features from the plurality of historical error data to determine a first data feature of each first error data corresponding to each first error scenario, wherein the plurality of historical error data includes: first error data, and the first data feature includes at least one of the following: field information of the first error data, business information associated with the first error data; determining a first scenario feature corresponding to each first error scenario based on the first data feature, and determining a first quantity of first error data corresponding to each first error scenario; and determining the scenario priority of each first error scenario based on the first quantity and the first scenario feature.

[0012] In an exemplary embodiment, after executing each scenario identification statement in the feature scenario library sequentially according to the scenario priority to data-mark each unmarked row of error data in the error data detail table according to each scenario identification statement to obtain the first identification information of each row of error data, the method further includes: if there is unmarked target error data in the error data detail table, performing feature extraction on the target error data to determine the second data feature of the target error data, and determining the second scenario feature according to the second data feature, wherein the second data feature includes at least one of the following: field information of the target error data, business information associated with the target error data; establishing a second error scenario corresponding to the second scenario feature, and updating the feature scenario library according to the second error scenario; data-marking the target error data according to the updated feature scenario library to obtain the fourth identification information corresponding to the target error data.

[0013] In one exemplary embodiment, updating the feature scene library according to the second error scenario includes: configuring a second identification statement corresponding to the second error scenario and determining the scenario priority corresponding to the second error scenario; establishing a second mapping relationship between the second identification statement and the second error scenario; and adding the second identification statement and the second error scenario to the feature scene library according to the scenario priority and the second mapping relationship to update the feature scene library.

[0014] According to another embodiment of the present application, a scene determination apparatus is also provided, comprising: a building module, configured to build a feature scene library corresponding to multiple error scenes, wherein the feature scene library includes: multiple error scenes arranged sequentially according to the scene priority corresponding to the multiple error scenes, and a scene identification statement corresponding to each error scene; an execution module, configured to execute each scene identification statement in the feature scene library sequentially according to the scene priority, so as to mark each unmarked row of error data in the error data detail table according to each scene identification statement, to obtain first identification information of each row of error data, wherein the first identification information is used to indicate the scene identifier of the target error scene corresponding to each row of error data; and a determination module, configured to determine the target error scene corresponding to each row of error data according to the first identification information.

[0015] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the determination method of the above-described scenario at runtime.

[0016] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for determining the above-mentioned scenario through the computer program.

[0017] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program, wherein the computer program is executed by a processor to determine the above-mentioned scenario.

[0018] In this embodiment, a feature scenario library is established, comprising multiple error scenarios arranged sequentially according to their scenario priorities, and a scenario identification statement corresponding to each error scenario. Each scenario identification statement in the feature scenario library is executed sequentially according to scenario priority to mark each unmarked row of error data in the error data detail table, obtaining first identification information indicating the target error scenario corresponding to each row of error data. The target error scenario corresponding to each row of error data is determined based on the first identification information. In other words, the feature scenario library established in this application contains multiple error scenarios arranged sequentially according to scenario priorities, and a scenario identification statement corresponding to each scenario. When the error data detail table is obtained, each row of data in the error data detail table can be marked sequentially using the scenario identification statements corresponding to each error scenario arranged sequentially according to scenario priority in the feature scenario library, thus determining the target error scenario corresponding to each row of error data. According to this application, the problem of low accuracy in scenario identification of error data due to repeated marking of error data during the process of scenario identification in related technologies can be solved, thereby improving the accuracy of scenario identification of data. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a hardware structure block diagram of a computer terminal device for a method of determining a scenario according to an embodiment of this application.

[0022] Figure 2 This is a flowchart of a method for determining a scenario according to an embodiment of this application;

[0023] Figure 3 This is a flowchart of an efficient method for analyzing the quality of detailed regulatory reporting data according to an optional embodiment of this application;

[0024] Figure 4 This is a structural block diagram of a scenario determination device according to an embodiment of this application. Detailed Implementation

[0025] The embodiments of this application will be described in detail below with reference to the accompanying drawings and examples.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0027] It should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of financial data or user data and other information involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0028] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0029] The methods and embodiments provided in this application can be executed on a computer terminal device or a similar computing device. Taking running on a computer terminal device as an example, Figure 1 This is a hardware structure block diagram of a computer terminal device for a scenario determination method according to an embodiment of this application. For example... Figure 1 As shown, a computer terminal device may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor (MPU) or a programmable logic device (PLD)) and a memory 104 for storing data are also shown. The computer terminal device may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that… Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal device described above. For example, the computer terminal device may also include components that are more complex than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0030] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the wind speed data determination method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to computer terminal devices via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider for the computer terminal equipment. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0032] Figure 2 This is a flowchart of a method for determining a scenario according to an embodiment of this application, such as... Figure 2 As shown, the methods for determining the scene include:

[0033] Step S202: Establish a feature scene library corresponding to multiple error scenarios, wherein the feature scene library includes: multiple error scenarios arranged in order of scenario priority corresponding to the multiple error scenarios, and each scenario recognition statement corresponding to each error scenario;

[0034] Step S204: Execute each scene recognition statement in the feature scene library in sequence according to the scene priority, so as to mark each row of unmarked error data in the error data detail table according to each scene recognition statement, and obtain the first identification information of each row of error data, wherein the first identification information is used to indicate the scene identifier of the target error scene corresponding to each row of error data;

[0035] Step S206: Determine the target error scenario corresponding to each row of error data based on the first identification information.

[0036] Through the above steps, a feature scene library is established, comprising multiple error scenarios arranged sequentially according to their respective scene priorities, and a scene identification statement corresponding to each error scenario. Each scene identification statement in the feature scene library is executed sequentially according to its scene priority to mark each unmarked row of error data in the error data details table, obtaining first identification information indicating the target error scenario corresponding to each row of error data. The target error scenario corresponding to each row of error data is determined based on the first identification information. In other words, the feature scene library established in this application contains multiple error scenarios arranged sequentially according to their scene priorities, and a scene identification statement corresponding to each scenario. When the error data details table is obtained, each row of data in the error data details table can be marked sequentially using the scene identification statements corresponding to each error scenario arranged sequentially according to its scene priority in the feature scene library, thus determining the target error scenario corresponding to each row of error data. According to this application, the problem of low accuracy in scene identification of error data due to repeated marking of error data during the process of scene identification in related technologies can be solved, thereby improving the accuracy of scene identification of data.

[0037] Optionally, step S204 above, which sequentially executes each scene recognition statement in the feature scene library according to the scene priority, to mark each unmarked row of error data in the error data detail table according to each scene recognition statement, and obtains the first identification information of each row of error data, includes: executing the first scene recognition statement in the feature scene library to mark the first error data in the error data detail table according to the first scene recognition statement, and obtaining the second identification information of the first error data, wherein the first scene recognition statement is the scene recognition statement corresponding to the first error scene with the first scene priority in the feature scene library, and the order of scene priorities is: first scene priority, second scene priority, ..., the first scene priority. The first error data is the error data corresponding to the first error scenario in the error data detail table; the second error data in the error data detail table is determined, and the nth scene recognition statement in the feature scene library is executed to mark the second error data according to the nth scene recognition statement, thereby obtaining the third identification information of the second error data, where n is 2, 3, ..., n in sequence, the second error data is the error data of the unmarked target row in the error data detail table after executing the (n-1)th scene recognition statement, and the nth scene recognition statement is the scene recognition statement corresponding to the nth error scenario with the nth scene priority in the feature scene library, and the first identification information includes: the second identification information and the third identification information.

[0038] It is understandable that the technical solution for marking each row of error data in the error data details table using scene recognition statements can include:

[0039] 1) Load scene recognition statements:

[0040] Initialize database connection: Connect to the database using Perl (Practical Extraction and Reporting Language) or a similar scripting language to prepare for extracting scene recognition statements from the scene feature library.

[0041] Read the scenario list: Read all error scenarios from the scenario feature library. These error scenarios can be evaluated and sorted according to multiple dimensions such as business impact, compliance risk, and handling difficulty to form a scenario priority order.

[0042] 2) Perform high-priority scene recognition:

[0043] Execute the first update statement: Retrieve the highest priority scene recognition statement from the scene feature library (e.g., scene 1 with priority 1). This scene recognition statement is used to identify specific types of erroneous data, such as data that is empty.

[0044] Data Tagging: In the error data details table, use this update statement to tag error data that meets the criteria. Tagging is achieved by adding a field (such as scene_id (scene identifier)) to the error data record, recording the specific scene code (such as 001) to which the data belongs.

[0045] 3) Repeatedly identify remaining data:

[0046] Check for unlabeled data: After completing the execution for priority 1 scenario, check the error data details table for any unlabeled data rows. These data rows will serve as the targets for the next round of scenario identification (secondary error data).

[0047] Execute the second update statement: Call the next identification statement in the priority sequence (such as scenario 2 of scenario priority 2, scenario ID is 002). This statement may be used to identify scenarios in the historical customer base where the ID number is missing due to account control reasons.

[0048] Data labeling iteration: Repeat the above process to perform scene recognition on unlabeled erroneous data until all scene recognition statements have been executed or all erroneous data has been labeled.

[0049] 4) Avoid scene coverage:

[0050] Controlling field updates: When designing scene recognition statements, add a condition to check if the `scene_id` field of the target data row is empty. Only execute the update statement to add the scene identifier if the field is empty.

[0051] Priority constraint: Ensures that once a data row is assigned a high-priority scene identifier, it will not be overwritten by a low-priority scene identifier. For example, if a data row is marked as 001 (high priority), during subsequent scene identification of priorities 2 to n, the non-empty check of this field will prevent low-priority scene identifiers from overwriting it.

[0052] Optionally, before executing each scene recognition statement in the feature scene library sequentially according to the scene priority in step S204, the method further includes: performing data verification on each row of target reporting data in the target reporting data detail table according to preset verification rules to determine the verification result corresponding to each row of target reporting data; determining one or more erroneous data in the target reporting data detail table according to the verification result; and performing data statistics on the one or more erroneous data to generate the erroneous data detail table.

[0053] Understandably, before executing each scene recognition statement, it is also necessary to obtain an error data detail table, specifically:

[0054] 1) Data verification:

[0055] Load Verification Rules: Load a set of preset verification rules, which can include inspection standards for data integrity, logical consistency, and format compliance. For example, the verification rules can require that the ID number field in all customer information must be non-empty and meet a specific length standard;

[0056] Row-by-row verification: Apply the above verification rules to each row of data in the target reported data details table. The verification process can be performed through database queries, data cleaning scripts, or dedicated verification software.

[0057] 2) Identify erroneous data:

[0058] Results Analysis: After the verification is completed, based on the results of the rule-based verification, all data records that do not meet the verification standards are analyzed and identified. For example, data rows with empty ID number fields or those that do not meet the specified length are considered erroneous data.

[0059] Error data location: Mark or isolate these error data in the target reported data details table.

[0060] 3) Error data statistics:

[0061] Statistical analysis of error data: Perform statistical analysis on the identified error data, including: the total number of error data, the distribution of various error types, and the time distribution of error data.

[0062] Generate a detailed error data table: Based on the statistical results, generate a detailed error data table. The error data table not only lists all error data but also includes the verification results, error type, and involved fields for each error. For example, a row in the table might display: "Customer ID = 123456, ID number field is empty, Error type = ID number missing, Verification rule = ID number cannot be empty and must be 18 digits long."

[0063] Optionally, step S202 above, establishing a feature scenario library corresponding to multiple error scenarios, includes: obtaining multiple historical error data that failed data verification from historical reporting data, and obtaining each first error scenario corresponding to each historical error data; configuring a first scenario identification statement corresponding to each first error scenario; performing feature extraction on the multiple historical error data to determine a first data feature of each first error data corresponding to each first error scenario, wherein the multiple historical error data includes: first error data, and the first data feature includes at least one of the following: field information of the first error data, business information associated with the first error data; determining a first scenario feature corresponding to each first error scenario based on the first data feature, and determining a first quantity of first error data corresponding to each first error scenario; determining a scenario priority of each first error scenario based on the first quantity and the first scenario feature; establishing a first mapping relationship between the arranged first scenario identification statement and each first error scenario; determining multiple first error scenarios as multiple error scenarios in the feature scenario library, and establishing the feature scenario library based on the scenario priority and the first mapping relationship, wherein the identification statement in the feature scenario library includes: multiple first scenario identification statements.

[0064] Understandably, the specific process for building a feature scene library can be as follows:

[0065] 1) Historical Error Data Collection: Extract all records of data that failed the verification process from historical reports. These records represent problems discovered during past verification processes.

[0066] 2) Configure scene recognition statements:

[0067] Analyze historical error scenarios: Conduct in-depth analysis of the causes of each historical error data point to identify the specific scenarios that led to the data errors.

[0068] Configure recognition statements: Based on the identified scenes, configure the corresponding scene recognition statements. These scene recognition statements will be used to automatically identify the same scenes in future data batches.

[0069] 3) Feature extraction and scene feature determination:

[0070] Feature extraction: Feature extraction is performed on historical error data, focusing on the field information and related business information of the error data, such as the length and format of the ID number field, as well as business attributes such as account status and customer type.

[0071] Scene feature determination: Based on the extracted features, define the feature set for each error scene.

[0072] 4) Determine scene priorities:

[0073] Scene count statistics: Count the number of erroneous data in each scene.

[0074] Scenario Prioritization: Prioritize scenarios based on their characteristics and the amount of erroneous data. Priorities can be determined by considering factors such as compliance risks, business impact, and processing difficulty.

[0075] 5) Establish mapping relationships and a feature scene library:

[0076] Mapping relationship establishment: Establish a mapping relationship between each configured scene recognition statement and the corresponding error scene.

[0077] Feature scenario library construction: Integrate all error scenarios, their priorities, and corresponding recognition statements into a feature scenario library.

[0078] Optionally, after step S204 above, which sequentially executes each scenario identification statement in the feature scenario library according to the scenario priority to mark each unmarked row of error data in the error data details table according to each scenario identification statement to obtain the first identification information of each row of error data, the method further includes: in the case of identified target error data, performing feature extraction on the target error data to determine the second data feature of the target error data, and determining the second scenario feature according to the second data feature, wherein the second data feature includes at least one of the following: field information of the target error data, business information associated with the target error data; establishing a second error scenario corresponding to the second scenario feature, configuring a second identification statement corresponding to the second error scenario, and determining the scenario priority corresponding to the second error scenario; establishing a second mapping relationship between the second identification statement and the second error scenario; adding the second identification statement and the second error scenario to the feature scenario library according to the scenario priority and the second mapping relationship to update the feature scenario library; and marking the target error data according to the updated feature scenario library to obtain the fourth identification information corresponding to the target error data.

[0079] Understandably, after marking each unmarked row of error data in the error data details table, it is necessary to confirm whether there are still unmarked error data in the error data details table. It's possible that the row of data was not marked because the feature scenario library does not contain the corresponding error scenario for the unmarked error data. Specifically:

[0080] 1) Feature extraction:

[0081] Analyzing Target Error Data: When newly identified target error data is discovered, in-depth analysis is conducted to identify the specific field information and associated business scenarios that cause this data to fail to meet preset verification rules. For example, if the "transaction amount" field of some corporate customer information is found to be negative in the submitted data, this may be a previously unencountered error type.

[0082] Determine the second data feature: Based on the above analysis of the target error data, extract the second data feature. The second data feature includes at least the specific information of the error field (e.g., "transaction amount is less than zero") and the relevant business background (e.g., customer type, transaction category, etc.).

[0083] 2) Construct error scenarios and scenario priorities:

[0084] Construct a second error scenario: Based on the second data feature, define a completely new error scenario. For example, creating the scenario "Abnormal (negative) transaction amount for corporate clients" describes a newly discovered error type.

[0085] Configure a second identification statement: Develop one or a series of identification statements for the newly defined second error scenario. These statements can automatically filter and label data in the database that matches the scenario characteristics.

[0086] Prioritize scenarios: Based on the assessment of business continuity, compliance risks, and resolvability of the second error scenario, determine the priority of the second error scenario.

[0087] 3) Establish mapping relationships and update the scene library:

[0088] Establish a second mapping relationship: Establish a mapping relationship between the second identification statement and the second error scenario to ensure that once the relevant statement is executed, the data belonging to the scenario can be accurately identified.

[0089] Update the feature scene library: Add the configured second recognition statement and the defined second error scene, along with their scene priority information, to the feature scene library.

[0090] 4) Data tagging:

[0091] Perform data labeling: Using the updated feature scene library, re-identify and label the erroneous data in the target reported data. This means executing all statements, including the newly added second identification statement, to ensure that all target erroneous data is correctly classified and labeled, obtaining the fourth identification information, namely the specific label under the new scene.

[0092] To better understand the process of determining the above scenario, the implementation flow of the method for determining the above scenario will be described below in conjunction with optional embodiments, but this is not intended to limit the technical solution of the embodiments of this application.

[0093] Regulatory data reporting and analysis is a crucial task in the financial industry. It involves collecting, organizing, verifying, and reporting various business data from financial institutions in accordance with regulatory requirements. Financial institutions should establish and improve their data governance systems, clearly define the responsibilities of their data governance departments, and ensure the accuracy and completeness of the data. Simultaneously, they need to conduct self-examinations and resolve key issues of regulatory concern. With increasingly stringent regulatory requirements, financial institutions face challenges in areas such as data quality, system upgrades, and reporting efficiency.

[0094] Currently, most regulatory verification error data is analyzed manually through sampling. After analyzing a specific scenario, data from the same scenario is removed, and the remaining data is analyzed, identified, and removed again. When a new batch of data is acquired, the above steps must be repeated to analyze the reasons for data triggering verification rules. Furthermore, there are no effective means to remove long-standing historical data or data that cannot be rectified due to historical reasons but still needs to be continuously reported, requiring repeated analysis, resulting in wasted manpower and low efficiency.

[0095] To address the aforementioned issues, this application proposes an efficient method for analyzing the quality of detailed regulatory reporting data. Specifically, it involves analyzing and categorizing reporting data that fails verification, prioritizing scenarios based on their specificity from a business perspective, establishing a scenario feature library, and sorting reporting data that triggers a certain verification rule from high to low specificity, prioritizing categorization into scenarios with high specificity. Furthermore, it involves developing technical recognition statements based on business characteristics, and identifying scenarios for data that fails verification during each data processing verification process.

[0096] Figure 3 This is a flowchart of an efficient method for analyzing the quality of detailed regulatory reporting data according to an optional embodiment of this application, such as... Figure 3 As shown:

[0097] Step S301: Processing of regulatory reporting data;

[0098] Perform ETL processing steps and generate regulatory reporting details in the database;

[0099] Step S302: Submit data verification module;

[0100] Input the detailed data to be submitted into the data verification module;

[0101] Step S303: Generate error details and check result statistics;

[0102] The data inspection module generates detailed error data (i.e., error data detail table) that triggers regulatory inspection rules, and summarizes the detailed data to generate inspection result statistics.

[0103] Step S304: Inject tags into the error data details through the scene feature library (i.e., feature scene library) to generate error details with scene feature identifiers (i.e., first identifier information);

[0104] After the check is completed, the recognition statements in the scene feature library are executed through the Perl script (the statements are database update statements, i.e. scene recognition statements). The statements are executed in the scene database according to the scene priority order. The error details are identified and labeled. When a piece of data has been marked by a high-priority scene, the low-priority scene will not be overwritten. This control point is implemented by checking the non-null value of the label field. When the label is empty, the current scene is labeled.

[0105] For example, the scenario recognition logic might involve a "Corporate Customer Information Form" in a reporting task, which has a field for "ID Number". Regulatory regulations require a non-empty check for this field. Data that fails the check needs to be identified and categorized as follows:

[0106] Scenario 1 (Priority 1, Business Setting Number 001): The customer is a classified agency, and the certificate information cannot be obtained. There will be an update SQL statement in the scenario feature database. Based on a classified customer table, the data in the report with empty certificate numbers will be labeled with

[001] .

[0107] Scenario 2 (Priority 2, Business Setting Number 002): Historical existing customers whose information is difficult to supplement, and whose accounts have been subject to payment control. The scenario feature database will have an update SQL statement. Based on the customer account information table, filter customers whose account control flag is "yes", and mark the data with empty ID numbers with the label "

[002] ".

[0108] In this process, business personnel assign priorities to each scenario, such as 1, 2, 3, 4, ... When executing the feature library statements, they are executed in ascending order of priority label fields, i.e., in the order of 1, 2, 3, 4. Each statement has a common filtering condition: only data with empty label fields are identified and tagged. This avoids conflicts and duplications. For example, if a piece of data hits both scenarios 001 and 002, scenario 001 will be executed and the scenario label field will not be empty, while scenario 002 will be excluded and not tagged. This ensures that the tagging of high-priority scenarios is not overwritten by low-priority scenarios.

[0109] Scenario priority can be ranked by business personnel based on the rationality and explainability of the scenario. For example, scenarios with clear exemptions due to regulatory norms, regulatory Q&As, or system explanations have higher priority, scenarios supported by business handling systems have higher priority, and special business scenarios of a certain institution have relatively lower priority.

[0110] The feature library can be supplemented or deleted based on regulatory agencies or internal policies to keep it up-to-date.

[0111] Step S305: Perform data analysis and new scenario identification based on the statistical information of the verification results;

[0112] By analyzing the statistical information of the inspection results, a detailed list of errors in the remaining unidentified scenarios is compiled. From a business perspective, new scenarios are identified and transformed into field feature information in a database table, which is then developed into scenario recognition update statements. The reliability of the statement recognition is verified by running the current batch of data. After verification, the statement is stored in the scenario feature library (i.e., the new scenario recognition statement is developed and stored in the library) for reuse in the next batch of data.

[0113] In summary, through the optional embodiments of this application, massive amounts of data can be transformed into scenario-based modular data management, avoiding redundant analysis and wasting manpower, thereby improving analysis and governance efficiency.

[0114] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0115] This embodiment also provides a scene determination device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0116] Figure 4 This is a structural block diagram of a scenario determination device according to an embodiment of this application, such as... Figure 4 As shown, the device includes:

[0117] The module 42 is used to establish a feature scene library corresponding to multiple error scenarios. The feature scene library includes: multiple error scenarios arranged in order of priority according to the scenario priority of the multiple error scenarios, and each scenario recognition statement corresponding to each error scenario.

[0118] Execution module 44 is used to execute each scene recognition statement in the feature scene library in sequence according to the scene priority, so as to mark each row of unmarked error data in the error data detail table according to each scene recognition statement, and obtain the first identification information of each row of error data, wherein the first identification information is used to indicate the scene identifier of the target error scene corresponding to each row of error data;

[0119] The determination module 46 is used to determine the target error scenario corresponding to each row of error data based on the first identification information.

[0120] Using the aforementioned apparatus, a feature scene library is established, comprising multiple error scenarios arranged sequentially according to their respective scene priorities, and a scene identification statement corresponding to each error scenario. Each scene identification statement in the feature scene library is executed sequentially according to its scene priority to mark each unmarked row of error data in the error data details table, obtaining first identification information indicating the target error scenario corresponding to each row of error data. The target error scenario corresponding to each row of error data is determined based on the first identification information. In other words, the feature scene library established in this application contains multiple error scenarios arranged sequentially according to their scene priorities, and a scene identification statement corresponding to each scenario. When the error data details table is obtained, each row of data in the error data details table can be marked sequentially using the scene identification statements corresponding to each error scenario arranged sequentially according to its scene priority in the feature scene library, thus determining the target error scenario corresponding to each row of error data. According to this application, the problem of low accuracy in scene identification of error data due to repeated marking of error data during the process of scene identification in related technologies can be solved, thereby improving the accuracy of scene identification of data.

[0121] In an exemplary embodiment, the execution module 44 is further configured to execute a first scene recognition statement in the feature scene library to mark the first error data in the error data detail table according to the first scene recognition statement, thereby obtaining second identification information of the first error data. The first scene recognition statement is a scene recognition statement corresponding to a first error scene with a first scene priority in the feature scene library, and the order of scene priorities is: first scene priority, second scene priority, ..., nth scene priority. The first error data is the error data corresponding to the first error scene in the error data detail table. The second error data in the error data detail table is defined, and the nth scene recognition statement in the feature scene library is executed to mark the second error data according to the nth scene recognition statement, thereby obtaining the third identification information of the second error data. Here, n is 2, 3, ..., n in sequence, the second error data is the error data of the unmarked target row in the error data detail table after executing the (n-1)th scene recognition statement, and the nth scene recognition statement is the scene recognition statement corresponding to the nth error scene with the nth scene priority in the feature scene library. The first identification information includes: the second identification information and the third identification information.

[0122] In an exemplary embodiment, the execution module 44 is further configured to perform data verification on each row of target reporting data in the target reporting data detail table according to preset verification rules, so as to determine the verification result corresponding to each row of target reporting data; determine one or more erroneous data in the target reporting data detail table according to the verification result; and perform data statistics on the one or more erroneous data to generate the erroneous data detail table.

[0123] In an exemplary embodiment, the establishment module 42 is further configured to obtain multiple historical error data that failed the data verification from historical reported data, and obtain each first error scenario corresponding to each historical error data; configure a first scenario identification statement corresponding to each first error scenario, and determine the scenario priority of each first error scenario; establish a first mapping relationship between the arranged first scenario identification statements and each first error scenario; determine multiple first error scenarios as multiple error scenarios in the feature scenario library, and establish the feature scenario library according to the scenario priority and the first mapping relationship, wherein the identification statements in the feature scenario library include: multiple first scenario identification statements.

[0124] In an exemplary embodiment, the establishment module 42 is further configured to perform feature extraction on the plurality of historical error data to determine a first data feature of each first error data corresponding to each first error scenario, wherein the plurality of historical error data includes: first error data, and the first data feature includes at least one of the following: field information of the first error data, business information associated with the first error data; determine a first scenario feature corresponding to each first error scenario based on the first data feature, and determine a first quantity of first error data corresponding to each first error scenario; determine the scenario priority of each first error scenario based on the first quantity and the first scenario feature.

[0125] In an exemplary embodiment, the execution module 44 is further configured to, when there is unidentified target error data in the error data detail table, extract features from the target error data to determine a second data feature of the target error data, and determine a second scenario feature based on the second data feature, wherein the second data feature includes at least one of the following: field information of the target error data, business information associated with the target error data; establish a second error scenario corresponding to the second scenario feature, and update the feature scenario library based on the second error scenario; and perform data tagging on the target error data based on the updated feature scenario library to obtain a fourth identification information corresponding to the target error data.

[0126] In an exemplary embodiment, the execution module 44 is further configured to configure a second identification statement corresponding to the second error scenario and determine the scenario priority corresponding to the second error scenario; establish a second mapping relationship between the second identification statement and the second error scenario; and add the second identification statement and the second error scenario to the feature scenario library according to the scenario priority corresponding to the second error scenario and the second mapping relationship to update the feature scenario library.

[0127] Embodiments of this application also provide a storage medium including a stored program, wherein the program executes the above-described method when it is run.

[0128] Optionally, in this embodiment, the storage medium may be configured to store program code for performing the following steps:

[0129] S1, establish a feature scene library corresponding to multiple error scenarios, wherein the feature scene library includes: multiple error scenarios arranged in order of scenario priority corresponding to the multiple error scenarios, and each scenario recognition statement corresponding to each error scenario;

[0130] S2, according to the scenario priority, each scenario identification statement in the feature scenario library is executed sequentially to mark each unmarked row of error data in the error data details table according to each scenario identification statement, so as to obtain the first identification information of each row of error data, wherein the first identification information is used to indicate the scenario identifier of the target error scenario corresponding to each row of error data;

[0131] S3, determine the target error scenario corresponding to each row of error data based on the first identification information.

[0132] Embodiments of this application also provide an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in the above method embodiments.

[0133] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0134] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0135] S1, establish a feature scene library corresponding to multiple error scenarios, wherein the feature scene library includes: multiple error scenarios arranged in order of scenario priority corresponding to the multiple error scenarios, and each scenario recognition statement corresponding to each error scenario;

[0136] S2, according to the scenario priority, each scenario identification statement in the feature scenario library is executed sequentially to mark each unmarked row of error data in the error data details table according to each scenario identification statement, so as to obtain the first identification information of each row of error data, wherein the first identification information is used to indicate the scenario identifier of the target error scenario corresponding to each row of error data;

[0137] S3, determine the target error scenario corresponding to each row of error data based on the first identification information.

[0138] Embodiments of this application also provide a computer program product, including a computer program that is executed by a processor using the steps described in the method embodiments above.

[0139] Optionally, in this embodiment, the above-mentioned computer program product can be executed by a processor using the following steps:

[0140] S1, establish a feature scene library corresponding to multiple error scenarios, wherein the feature scene library includes: multiple error scenarios arranged in order of scenario priority corresponding to the multiple error scenarios, and each scenario recognition statement corresponding to each error scenario;

[0141] S2, according to the scenario priority, each scenario identification statement in the feature scenario library is executed sequentially to mark each unmarked row of error data in the error data details table according to each scenario identification statement, so as to obtain the first identification information of each row of error data, wherein the first identification information is used to indicate the scenario identifier of the target error scenario corresponding to each row of error data;

[0142] S3, determine the target error scenario corresponding to each row of error data based on the first identification information.

[0143] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0144] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0145] The collection, storage, use, processing, transmission, provision, and disclosure of financial data or user data involved in the technical solution of this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0146] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0147] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0148] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of determining a scene, characterized by, The method comprises the steps of: establishing a feature scene library corresponding to a plurality of error scenes, wherein the feature scene library comprises a plurality of error scenes arranged in order according to scene priorities corresponding to the plurality of error scenes, and each scene identification statement corresponding to each error scene; executing the each scene identification statement in the feature scene library in order according to the scene priorities, to perform data marking on each unmarked row of error data in an error data detail table according to the each scene identification statement, to obtain first identification information of the each row of error data, wherein the first identification information is used to indicate a scene identification of a target error scene corresponding to the each row of error data; and determining the target error scene corresponding to the each row of error data according to the first identification information.

2. The method of claim 1, wherein, The method comprises the steps of: executing the each scene identification statement in the feature scene library in order according to the scene priorities, to perform data marking on each unmarked row of error data in an error data detail table according to the each scene identification statement, to obtain first identification information of the each row of error data, comprising: executing a first scene identification statement in the feature scene library, to perform data marking on first error data in the error data detail table according to the first scene identification statement, to obtain second identification information of the first error data, wherein the first scene identification statement is a scene identification statement corresponding to a first error scene of a first scene priority in the feature scene library, the order of the scene priorities is: the first scene priority, the second scene priority, …, the nth scene priority, and the first error data is error data corresponding to the first error scene in the error data detail table; determining second error data in the error data detail table, and executing an nth scene identification statement in the feature scene library, to perform data marking on the second error data according to the nth scene identification statement, to obtain third identification information of the second error data, wherein n is 2, 3, …, n in order, the second error data is error data of a target row in the error data detail table which is unmarked after execution of an (n-1)th scene identification statement, the nth scene identification statement is a scene identification statement corresponding to an nth error scene of an nth scene priority in the feature scene library, and the first identification information comprises the second identification information and the third identification information.

3. The method of claim 1, wherein, Before the step of executing the each scene identification statement in the feature scene library in order according to the scene priorities, the method further comprises the steps of: performing data checking on each row of target reporting data in a target reporting data detail table according to a preset checking rule, to determine a checking result corresponding to the each row of target reporting data; determining one or more rows of error data in the target reporting data detail table according to the checking result; 4. The method of claim 1, wherein, performing data statistics on the one or more rows of error data, to generate the error data detail table. establishing a feature scene library corresponding to a plurality of error scenes, comprising: obtain a plurality of historical error data that fails to pass data review from historical reporting data, and obtain each first error scene corresponding to each historical error data; configure a first scene identification sentence corresponding to each first error scene, and determine a scene priority of each first error scene; establish a first mapping relationship between the arranged first scene identification sentence and each first error scene; determine a plurality of first error scenes as a plurality of error scenes in the feature scene library, and establish the feature scene library according to the scene priority and the first mapping relationship, wherein the identification sentence in the feature scene library comprises a plurality of first scene identification sentences.

5. The method of claim 4, wherein, determining the scene priority of each first error scene comprises: performing feature extraction on the plurality of historical error data to determine a first data feature of each first error data corresponding to each first error scene, wherein the plurality of historical error data comprises first error data, and the first data feature comprises at least one of the following: field information of the first error data, and business information associated with the first error data; determining a first scene feature corresponding to each first error scene according to the first data feature, and determining a first quantity of first error data corresponding to each first error scene; determining the scene priority of each first error scene according to the first quantity and the first scene feature.

6. The method of claim 1, wherein, After sequentially executing each scene identification sentence in the feature scene library according to the scene priority to perform data labeling on each unmarked row of error data in the error data detail table according to each scene identification sentence, and obtaining first identification information of each row of error data, the method further comprises: in the case that there is target error data that has not been identified in the error data detail table, performing feature extraction on the target error data to determine a second data feature of the target error data, and determining a second scene feature according to the second data feature, wherein the second data feature comprises at least one of the following: field information of the target error data, and business information associated with the target error data; establishing a second error scene corresponding to the second scene feature, and updating the feature scene library according to the second error scene; performing data labeling on the target error data according to the updated feature scene library to obtain fourth identification information corresponding to the target error data.

7. The method of claim 6, wherein, updating the feature scene library according to the second error scene comprises: configuring a second identification sentence corresponding to the second error scene, and determining a scene priority corresponding to the second error scene; establishing a second mapping relationship between the second identification sentence and the second error scene; adding the second identification sentence and the second error scene to the feature scene library according to the scene priority corresponding to the second error scene and the second mapping relationship, so as to update the feature scene library.

8. A scene determination apparatus characterized by comprising: comprises: The establishing module is configured to establish a feature scene library corresponding to a plurality of error scenes, wherein the feature scene library comprises: a plurality of error scenes arranged in sequence according to scene priorities corresponding to the plurality of error scenes, and each scene identification statement corresponding to each error scene; The executing module is configured to execute the each scene identification statement in the feature scene library in sequence according to the scene priorities, to perform data marking on each unmarked error data in an error data detail table according to the each scene identification statement, and to obtain first identification information of the each error data, wherein the first identification information is used to indicate a scene identification of a target error scene corresponding to the each error data. The determining module is configured to determine the target error scene corresponding to the each error data according to the first identification information.

9. A computer readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program performs the method of claims 1-7 when executed. 10.An electronic device comprising a memory and a processor, the electronic device characterized by, The memory stores a computer program, and the processor is configured to execute the method of claims 1-7 by using the computer program.

Images