Method and system for constructing credit investigation test data
By collecting, desensitizing and analyzing customer credit data, establishing and maintaining the mapping relationship of credit index indicators, forming a credit test data pool, solving the problems of low structure efficiency and inconsistent with actual application scenarios in the existing technology. It realizes efficient and accurate construction of credit test data.
Patent Information
- Application Number
- CN202411259503.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2025-02-14
AI Technical Summary
The existing methods are inefficient when constructing credit reporting test data, and the data constructed do not meet the actual application scenarios, resulting in a decrease in the quality and efficiency of model strategy rule testing.
By collecting customer credit data, desensitization processing and analysis processing, establishing a mapping relationship between credit reporting indicators and customer credit reporting data, dynamically maintaining and updating the label parameter set, forming a credit test data pool, and establishing query rules.
It improves the efficiency of building model test data, and ensures the correctness of credit test data and the matching of actual application scenarios.
Smart Images
Figure CN119444388A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for constructing credit investigation test data. Background Art
[0002] With the development of banking business, credit data is increasingly used in various financial products, especially for bank risk control models and quota control models. In order to ensure the correctness of the model application scenario, the strategy rule testing of the model is paid more and more attention by financial institutions. At present, the content of the credit report is mainly modified manually according to the credit report template of the People's Bank of China to construct credit test data that meets the policy rule testing conditions. However, due to the large number of elements and complex structure of the information unit of the People's Bank of China's credit report, the efficiency of constructing credit test data is low, and the constructed credit test data does not conform to the actual application scenario, which greatly restricts the quality and efficiency of the model strategy rule testing.
[0003] In view of this, this application is hereby filed. Summary of the invention
[0004] The purpose of the present invention is to solve the problem that the existing method is ineffective in constructing credit test data, and the constructed credit test data does not conform to the actual application scenario, resulting in reduced quality and efficiency of model strategy rule testing. This is achieved through the following technical solutions: In a first aspect, a method for constructing credit test data is provided, comprising the following steps: collecting customer credit data; calling a credit analysis and processing method at a preset time to analyze and process the customer credit data to obtain a plurality of credit indicators; storing the plurality of credit indicators in a label parameter set; establishing a mapping relationship between each credit indicator and the customer credit data; performing the following steps within each preset period: scanning the label parameter set of the current period; if the label parameter set of the current period is updated, rescanning each credit indicator in the label parameter set of the current period and the credit analysis and processing method corresponding to each credit indicator to obtain a scan result; comparing the scan result with the label parameter set of the previous period. Perform a comparison; according to the comparison result, assign a first mark to the credit indicator that is no longer used, assign a second mark to the credit indicator whose credit analysis and processing method has changed, and assign a third mark to the newly added credit indicator; delete the credit indicator assigned the first mark from the label parameter set of the current cycle, call the credit analysis and processing method to analyze and process the customer credit data corresponding to the credit indicator assigned the second mark and the customer credit data corresponding to the credit indicator assigned the third mark, respectively, to obtain a new credit indicator; use the new credit indicator to update the label parameter set of the current cycle to obtain a new label parameter set; establish a mapping relationship between each credit indicator in the new label parameter set and the customer credit data.
[0005] Furthermore, after collecting the customer credit data, the following steps are also included: desensitizing the customer credit data.
[0006] Furthermore, after establishing the mapping relationship between each credit indicator in the new label parameter set and the customer credit data, the following steps are also included: storing the new label parameter set and the mapping relationship between each credit indicator in the new label parameter set and the customer credit data, and establishing a credit test data pool.
[0007] Furthermore, after establishing the credit test data pool, the following steps are also included: establishing query rules for querying credit indicators from the credit test data pool.
[0008] In a second aspect, a system for constructing credit test data is provided, including: a credit data collection module for collecting customer credit data; a first data processing module for calling a credit analysis and processing method at a preset time to analyze and process the customer credit data to obtain a plurality of credit indicators; a first data storage module for storing the plurality of credit indicators in a label parameter set; a second data processing module for establishing a mapping relationship between each credit indicator and the customer credit data; a credit indicator scanning module for changing the label set parameters for scanning the current cycle, and if the label parameter set of the current cycle is updated, each credit indicator in the label parameter set of the current cycle and the credit analysis and processing method corresponding to each credit indicator are re-scanned to obtain a scanning result; a third data processing module for storing the scanning result The result is compared with the label parameter set of the previous cycle. According to the comparison result, the first mark is assigned to the credit indicator that is no longer used, the second mark is assigned to the credit indicator whose credit analysis and processing method has changed, and the third mark is assigned to the newly added credit indicator; the fourth data processing module is used to delete the credit indicator assigned the first mark from the label parameter set of the current cycle, call the credit analysis and processing method to analyze and process the customer credit data corresponding to the credit indicator assigned the second mark and the customer credit data corresponding to the credit indicator assigned the third mark, respectively, to obtain a new credit indicator; use the new credit indicator to update the label parameter set of the current cycle to obtain a new label parameter set; the fifth data processing module is used to establish a mapping relationship between each credit indicator in the new label parameter set and the customer credit data.
[0009] Furthermore, the system for constructing credit test data also includes: a data cleaning module for desensitizing customer credit data.
[0010] Furthermore, the system for constructing credit test data also includes: a second data storage module for storing a new label parameter set and a mapping relationship between each credit indicator in the new label parameter set and the customer credit data, and establishing a credit test data pool.
[0011] Furthermore, the system for constructing credit test data also includes: a query rule establishment module, which is used to establish a query rule for querying credit indicators from the credit test data pool.
[0012] Compared with the prior art, the present invention has the following advantages and beneficial effects: the present invention desensitizes the real customer credit data and saves it in a test environment. By setting label attributes for the credit data, testers can query the credit data that meets the test conditions according to the labels. On the one hand, the correctness of the constructed credit test data is effectively guaranteed. On the other hand, testers do not need to manually construct complex credit files, which greatly improves the efficiency of building model test data. BRIEF DESCRIPTION OF THE DRAWINGS
[0013] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0014] Figure 1 A schematic diagram of a method for constructing credit investigation test data provided by an embodiment of the present invention; Figure 2 A schematic diagram of a system structure for constructing credit test data provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0015] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.
[0016] In the following description, a large number of specific details are set forth in order to provide a thorough understanding of the present invention. However, it is apparent to one of ordinary skill in the art that these specific details are not necessarily employed to practice the present invention. In other embodiments, in order to avoid obscuring the present invention, well-known structures, circuits, materials, or methods are not specifically described.
[0017] Throughout the specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment of the present invention. Therefore, the phrases "one embodiment," "an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily all refer to the same embodiment or example. In addition, particular features, structures, or characteristics may be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. In addition, it will be appreciated by those of ordinary skill in the art that the figures provided herein are for illustrative purposes and that the figures are not necessarily drawn to scale. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.
[0018] In the description of the present invention, the directions or positional relationships indicated by terms such as “front”, “rear”, “left”, “right”, “up”, “down”, “vertical”, “horizontal”, “high”, “low”, “inside” and “outside” are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the scope of protection of the present invention.
[0019] Example: In a first aspect, this embodiment provides a method for constructing credit test data, such as Figure 1 As shown, the method comprises the following steps: Step 1: Collect customer credit data.
[0020] Step 2: Desensitize customer credit data.
[0021] The purpose of this step is to clean up sensitive information in the customer's credit data, for example, clean up sensitive information such as customer name, ID number, home address, mobile phone number, etc.
[0022] Step 3: Call the credit analysis and processing method at the preset time to analyze and process the desensitized customer credit data to obtain multiple credit indicators.
[0023] In the model application, the relevant policy rules involving customer credit need to parse the customer credit data into various credit indicators (such as rating, overdue, etc.), and then apply the individual credit indicators to the subsequent model logic judgment. It should be noted that according to the actual business conditions of different banks, the credit analysis methods adopted by each bank are different, and the names and types of the credit indicators obtained after analysis and processing are different. In this step, different users can call the credit analysis and processing method of the bank according to the actual business of the bank to process customer credit data.
[0024] Step 4: Store multiple credit indicators into a label parameter set, and establish a mapping relationship between each credit indicator and the customer's credit data.
[0025] This step directly saves the credit indicators obtained after parsing as labels and stores them in the label parameter set, and establishes a mapping relationship between each credit indicator and the customer's credit data, so that the existing credit test data that meets the test rules can be directly obtained according to the label value. The label parameter set is represented as List={X1,X2,X3,X4,......}.
[0026] According to the established label parameter set List, a mapping relationship is established by labeling the desensitized customer credit data. For example, the mapping relationship between the customer credit data Data and the credit indicator X1 can be expressed as Data: X1: 1.
[0027] Step 5: Dynamically maintain the credit reporting indicators and credit reporting analysis methods in each preset period, including executing steps 5.1 to 5.3.
[0028] Step 5.1: Scan the label parameter set of the current cycle. If the label parameter set of the current cycle is updated, rescan each credit indicator in the label parameter set of the current cycle and the credit analysis processing method corresponding to each credit indicator to obtain the scanning result. It should be noted that if the label parameter set of the current cycle is updated in this step, it means that if the number of credit indicators in the label parameter set of the current cycle is greater than the number of credit indicators in the label set of the previous cycle, it can be determined that the label parameter set has been updated; or, if the number of credit indicators in the label sets of the two cycles is the same, by traversing the credit indicators in the label set of the current cycle, it is found that there is at least one credit indicator that is not included in the label set of the previous cycle, then it can be determined that the label parameter set has been updated.
[0029] Step 5.2: Compare the scan results with the label parameter set of the previous cycle. Based on the comparison results, assign a first mark to the credit indicators that are no longer used, assign a second mark to the credit indicators whose credit analysis and processing methods have changed, and assign a third mark to the newly added credit indicators.
[0030] As shown in Table 1 below, credit indicators that are no longer used are marked as D, credit indicators whose credit analysis and processing methods have changed are marked as U, and newly added credit indicators are marked as A. Credit indicators that have not changed are not marked.
[0031]
[0032] Table 1 Step 5.3: Delete the credit indicator assigned with the first mark from the label parameter set of the current cycle, call the credit analysis and processing method to analyze and process the customer credit data corresponding to the credit indicator assigned with the second mark and the customer credit data corresponding to the credit indicator assigned with the third mark, respectively, to obtain a new credit indicator; use the new credit indicator to update the label parameter set of the current cycle to obtain a new label parameter set.
[0033] Based on step 5.2 and Table 1, the new label parameter set is List={X2,X3,X4,......}.
[0034] Step 5.3: Establish a mapping relationship between each credit indicator in the new label parameter set and the customer credit data.
[0035] Step 6: Store the new label parameter set and the mapping relationship between each credit indicator in the new label parameter set and the customer credit data, and establish a credit test data pool.
[0036] Step 7: Establish query rules for querying credit indicators from the credit test data pool.
[0037] For example, the query conditions are set as "Rating: A", "Loan Account: True", and the credit data label value containing the conditions is queried in the data storage module to obtain the corresponding test data that meets the conditions.
[0038] Based on the above steps 1 to 7, by desensitizing the real customer credit data, labeling the credit data, storing the customer credit data and the corresponding labels, a large number of real and available credit test data pools are formed. Testers can query the credit test data that meets the conditions through query conditions.
[0039] Corresponding to the method for constructing credit test data provided in the first aspect above, the second aspect of this embodiment provides a system for constructing credit test data, including: a credit data collection module, used to collect customer credit data; a first data processing module, used to call the credit analysis and processing method at a preset time to analyze and process the customer credit data to obtain multiple credit indicators; a first data storage module, used to store the multiple credit indicators in a label parameter set; a second data processing module, used to establish a mapping relationship between each credit indicator and the customer credit data; a credit indicator scanning module, used to change the label set parameters of the current cycle, if the label parameter set of the current cycle is updated, then re-scan each credit indicator in the label parameter set of the current cycle and the credit analysis and processing method corresponding to each credit indicator to obtain a scanning result; The third data processing module is used to compare the scanning results with the label parameter set of the previous cycle. According to the comparison results, the first mark is assigned to the credit indicators that are no longer used, the second mark is assigned to the credit indicators whose credit analysis and processing methods have changed, and the third mark is assigned to the newly added credit indicators; the fourth data processing module is used to delete the credit indicators assigned with the first mark from the label parameter set of the current cycle, call the credit analysis and processing method to analyze and process the customer credit data corresponding to the credit indicators assigned with the second mark and the customer credit data corresponding to the credit indicators assigned with the third mark, respectively, to obtain new credit indicators; use the new credit indicators to update the label parameter set of the current cycle to obtain a new label parameter set; the fifth data processing module is used to establish a mapping relationship between each credit indicator in the new label parameter set and the customer credit data.
[0040] Furthermore, the system for constructing credit test data also includes: a data cleaning module for desensitizing customer credit data.
[0041] Furthermore, the system for constructing credit test data also includes: a second data storage module for storing a new label parameter set and a mapping relationship between each credit indicator in the new label parameter set and the customer credit data, and establishing a credit test data pool.
[0042] Furthermore, the system for constructing credit test data also includes: a query rule establishment module, which is used to establish a query rule for querying credit indicators from the credit test data pool.
[0043] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is 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 in the scope of protection of the present invention.
Claims
1. A method for constructing credit test data, characterized in that: The following steps are involved: Collect customer credit data; Calling the credit analysis and processing method at a preset time to analyze and process the customer's credit data to obtain multiple credit indicators; storing the multiple credit indicators in a label parameter set; Establish a mapping relationship between each credit indicator and customer credit data; The following steps are performed in each preset cycle: Scan the tag parameter set of the current cycle; If there is an update to the label parameter set of the current period, each credit indicator in the label parameter set of the current period and the credit analysis processing method corresponding to each credit indicator are re-scanned to obtain a scanning result; Compare the scan results with the label parameter set of the previous cycle; According to the comparison results, the credit indicators that appeared in the label parameter set of the previous cycle but did not appear in the label parameter set of the current cycle are given a first mark, the credit indicators whose credit analysis processing methods have changed are given a second mark, and the newly added credit indicators are given a third mark; The credit indicator assigned with the first mark is deleted from the label parameter set of the current cycle, and the credit analysis and processing method is called to analyze and process the customer credit data corresponding to the credit indicator assigned with the second mark and the customer credit data corresponding to the credit indicator assigned with the third mark to obtain a new credit indicator; the label parameter set of the current cycle is updated using the new credit indicator to obtain a new label parameter set; Establish a mapping relationship between each credit indicator in the new label parameter set and the customer credit data.
2. A method for constructing credit test data according to claim 1, characterized in that: After collecting customer credit data, the following steps are also included: desensitizing the customer credit data.
3. A method for constructing credit test data according to claim 1 or 2, characterized in that: After establishing the mapping relationship between each credit indicator in the new label parameter set and the customer credit data, the following steps are also included: The new label parameter set and the mapping relationship between each credit indicator in the new label parameter set and the customer credit data are stored to establish a credit test data pool.
4. A method for constructing credit test data according to claim 3, characterized in that: After establishing the credit test data pool, the following steps are also included: Establish query rules for querying credit indicators from the credit test data pool.
5. A system for constructing credit test data, characterized in that: include: Credit data collection module, used to collect customer credit data; The first data processing module is used to call the credit analysis and processing method at a preset time to analyze and process the customer's credit data to obtain multiple credit indicators; A first data storage module, used to store multiple credit indicators into a tag parameter set; The second data processing module is used to establish a mapping relationship between each credit indicator and the customer credit data; The credit indicator scanning module is used to change the label set parameters of the current scanning cycle. If the label parameter set of the current cycle is updated, each credit indicator in the label parameter set of the current cycle and the credit analysis processing method corresponding to each credit indicator are re-scanned to obtain the scanning result; The third data processing module is used to compare the scanning result with the tag parameter set of the previous cycle, and according to the comparison result, assign the first mark to the credit indicators that are no longer used, assign the second mark to the credit indicators whose credit analysis processing methods have changed, and assign the third mark to the newly added credit indicators; The fourth data processing module is used to delete the credit indicator assigned with the first mark from the label parameter set of the current cycle, call the credit analysis and processing method to analyze and process the customer credit data corresponding to the credit indicator assigned with the second mark and the customer credit data corresponding to the credit indicator assigned with the third mark, respectively, to obtain a new credit indicator; and use the new credit indicator to update the label parameter set of the current cycle to obtain a new label parameter set; The fifth data processing module is used to establish a mapping relationship between each credit indicator in the new label parameter set and the customer credit data.
6. A system for constructing credit test data according to claim 5, characterized in that: Also includes: The data cleaning module is used to desensitize customer credit data.
7. A system for constructing credit investigation test data according to claim 5 or 6, characterized in that: Also includes: The second data storage module is used to store the new label parameter set and the mapping relationship between each credit indicator in the new label parameter set and the customer credit data, and establish a credit test data pool.
8. A system for constructing credit investigation test data according to claim 7, characterized in that: Also includes: The query rule establishment module is used to establish query rules for querying credit indicators from the credit test data pool.