Test data generation method and device, electronic equipment and storage medium

Abstract

The invention provides a test data generation method and device, electronic equipment and a storage medium, and the method comprises the steps: generating simulation test data of a target service based on a preset feature item corresponding to the target service, and then evaluating the simulation degree of the simulation test data based on a data evaluation strategy corresponding to the target service, and under the condition that the simulation degree is smaller than a preset threshold value, correcting the simulation test data, and obtaining target test data of the target service. Therefore, the simulation test data is highly similar to the real production environment data, so that the accuracy and efficiency of test data generation are improved.

Description

Technical Field

[0001] The present application relates to the field of testing technology, and in particular to a test data generating method, device, electronic device and storage medium. Background Art

[0002] Data processing in insurance systems faces many challenges due to its complexity and diversity. In order to meet these challenges and ensure the stability and reliability of the system in practical applications, it is particularly important to develop and maintain an effective testing framework. Especially in the testing phase, how to generate high-accuracy test data that meets actual business scenarios has become a major problem.

[0003] The traditional way of manually creating test data is not only time-consuming and labor-intensive, but also difficult to cover all possible business scenarios. Therefore, a test data generation method with high accuracy and efficiency is needed. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first objective of the present application is to propose a test data generation method to improve the accuracy and efficiency of the test data.

[0006] The second objective of the present application is to provide a test data generating device.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] A fifth object of the present application is to provide a computer program product.

[0010] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a test data generation method, comprising:

[0011] Generate simulation test data of the target business based on preset feature items corresponding to the target business;

[0012] Evaluate the simulation degree of simulation test data based on the data evaluation strategy corresponding to the target business;

[0013] When the degree of simulation is less than a preset threshold, the simulation test data is corrected to obtain target test data for the target business.

[0014] To achieve the above-mentioned purpose, the second aspect of the present application provides a test data generating device, including:

[0015] A generation module, used to generate simulation test data of the target business based on preset feature items corresponding to the target business;

[0016] An evaluation module, used to evaluate the simulation degree of simulation test data based on a data evaluation strategy corresponding to a target business;

[0017] The correction module is used to correct the simulation test data when the simulation degree is less than a preset threshold value to obtain the target test data of the target business.

[0018] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including:

[0019] at least one processor; and

[0020] a memory communicatively connected to at least one processor; wherein,

[0021] The memory stores instructions that can be executed by at least one processor. The instructions are executed by the at least one processor so that the at least one processor can execute the method of the above embodiment.

[0022] To achieve the above objectives, the fourth aspect of the present application proposes a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the method according to the above embodiment.

[0023] To achieve the above objectives, the fifth aspect of the present application proposes a computer program product, including a computer program, which implements the method of the above embodiment when executed by a processor.

[0024] The test data generation method, device, electronic device and storage medium provided by the present application generate simulation test data of a target business based on preset feature items corresponding to the target business, and then evaluate the simulation degree of the simulation test data based on the data evaluation strategy corresponding to the target business, and when the simulation degree is less than a preset threshold, correct the simulation test data to obtain the target test data of the target business. As a result, the simulation test data is highly similar to the real production environment data, thereby improving the accuracy and efficiency of test data generation.

[0025] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0027] Figure 1A flow chart of a test data generation method provided in an embodiment of the present application;

[0028] Figure 2 A schematic diagram of the structure of a test data generating device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0030] The test data generating method and device according to the embodiments of the present application are described below with reference to the accompanying drawings.

[0031] The test data generating method of the embodiment of the present application is executed by the test data generating device provided in the embodiment of the present application. The device can be configured in a computer device or a terminal device to achieve accuracy and efficiency of performance testing.

[0032] Figure 1 A flowchart of a test data generation method provided in an embodiment of the present application.

[0033] like Figure 1 As shown, the test data generation method includes the following steps:

[0034] Step 101: Generate simulation test data of the target service based on preset feature items corresponding to the target service.

[0035] In the insurance industry, different businesses (such as life insurance, health insurance, auto insurance, property insurance, etc.) have different key processes and steps involved in the business operation process due to their specific service objects and service contents. These differences further lead to different types of data that need to be collected, analyzed and managed when processing each type of insurance business. Therefore, the preset feature items corresponding to different businesses are different, so as to ensure the accuracy and effectiveness of the generated test data.

[0036] In the present application, the relevance and importance between the candidate feature items can be determined based on the historical data of the candidate feature items corresponding to the target business, and then the feature items of the target business are determined from the candidate feature items based on the relevance and importance.

[0037] For example, the feature selection algorithm of any mutual information, correlation coefficient and other statistics can be used to calculate the historical data of the candidate feature items corresponding to the target business to determine the correlation between the candidate feature items. The historical data of the candidate feature items corresponding to the target business are calculated using a machine learning algorithm (such as random forest, gradient boosting tree, etc.) to determine the importance of each candidate feature item. Afterwards, when the correlation of multiple candidate feature items is greater than a preset threshold, the candidate feature item with the greatest importance among the multiple candidate feature items is determined as the feature item of the target business. When the correlation between a candidate feature item and any other candidate feature item is less than a preset threshold, and the importance of the candidate feature item is greater than the preset threshold, the candidate feature item is determined as the feature item of the target business.

[0038] Optionally, the candidate feature items may be subjected to dimensionality reduction and decorrelation processing by methods such as principal component analysis (PCA) or least absolute shrinkage and selection operator (LASSO), thereby removing redundant data.

[0039] In the present application, the process of generating simulation test data for the target business is as follows: based on the conversion method of the numerical feature association corresponding to the feature item, the historical data of the feature item is converted to obtain the converted first feature data. Afterwards, based on the business constraints associated with the feature item, the first feature data corresponding to the feature item is verified and adjusted to obtain the second feature data. Then, the second feature data is fitted to obtain a statistical distribution model to generate simulation test data for the target business using the statistical distribution model. The business constraints may be nonlinear relationships between feature items (such as the nonlinear relationship between vehicle service life and premiums), prior knowledge of feature items (such as the range of possible values, etc.), etc.

[0040] For example, in the insurance business, different feature items correspond to different numerical features. In order to fully explore the data association relationship between feature items, different data conversions can be performed on different feature items to improve the distribution and linear relationship of the features. This will make the data association relationship between feature items more accurate, making the generated test data more effective and accurate.

[0041] In the auto insurance business, the feature items related to vehicles include: vehicle type, vehicle usage, vehicle age, etc. Among them, the data types corresponding to vehicle type and vehicle usage (such as private cars, commercial vehicles, operating vehicles, etc.) are limited discrete data, so they can be converted into binary vectors using one-hot encoding. If the vehicle type or vehicle usage is greater than the threshold, an embedding representation can be used to reduce the dimension and capture the similarity relationship between categories. The data type corresponding to the age of the vehicle is continuous data, but its impact in the auto insurance business may be nonlinear. Therefore, the age of the vehicle can be segmented, for example, the age of the vehicle can be divided into different segments such as "0-1 years", "1-3 years", and "3-5 years". Each segment can be regarded as an independent category and converted using one-hot encoding. In addition, if you want to retain the numerical information of the age of the vehicle, you can also use standardization or normalization methods to process it.

[0042] In the auto insurance business, the feature items related to payment include: payment period and payment amount. Logarithmic transformation or standardization can be used to reduce skew. Among them, the data type corresponding to the payment period is numerical data, which indicates the number or cycle of payment. Since the payment periods of different customers may vary greatly, directly using the original value may cause the model to be too sensitive to high-frequency payment periods. Therefore, standardization can be used to convert the payment period into a standard score with a mean of 0 and a standard deviation of 1, thereby reducing skew. The data type corresponding to the payment amount is also numerical data, indicating the amount of each payment. Since the payment amount often has a long-tail distribution, that is, a few large payments will occupy most of the data, logarithmic transformation can be used to reduce deviation. Logarithmic transformation can convert the original amount into logarithmic form, making the converted data closer to a normal distribution. If logarithmic transformation is not applicable (for example, there are zero or negative values), standardization can be used.

[0043] In the auto insurance business, the data types corresponding to feature items such as issuing institutions, agents, and products are discrete data, which can be converted using one-hot encoding or embedded representation.

[0044] It should be noted that One-Hot Encoding is suitable for situations where the number of categories is relatively small. It can directly convert data into binary form, which is convenient for model processing. However, it should be noted that when the amount of data is too large, One-Hot Encoding will cause the feature space to become very sparse, which will increase the computational burden of the model. The conversion process of Embedding is: Use the Embedding Layer in the neural network to convert the data into a low-dimensional, dense vector representation. Embedding is suitable for situations where the amount of data is large. Through the Embedding Layer, we can map each data to a vector in a low-dimensional space that captures the similarities and differences between the data. Embedding can not only reduce the dimension of the feature space, but also improve the generalization ability of the model.

[0045] Step 102: Evaluate the simulation degree of the simulation test data based on the data evaluation strategy corresponding to the target business.

[0046] When the target business is the auto insurance business, the data evaluation strategy includes: based on the numerical constraints corresponding to each feature item, verifying the simulation data corresponding to each feature item in the simulation test data, and determining the simulation degree of the simulation test data.

[0047] For example, the numerical constraint corresponding to the age of the vehicle is: the age of the vehicle is an integer. The numerical constraint corresponding to the payment period is: the payment period is within the preset range. The numerical constraint corresponding to the agent is: the agent number comes from the authorized issuing agency. When a certain numerical value corresponding to a certain feature item does not meet its corresponding numerical constraint, the numerical value is determined as the abnormal numerical value of the feature item. Afterwards, the ratio between the total number of abnormal numerical values ​​corresponding to each feature item and the total amount of simulation data corresponding to each feature item is determined, and the difference between 1 and the ratio corresponding to each feature item is determined as the simulation degree of the simulation data corresponding to each feature item, and the mean of the simulation degree corresponding to each feature item is determined as the simulation degree of the simulation test data corresponding to the target business.

[0048] When the target business is agricultural insurance business, the data evaluation strategy includes: comparing the simulation test data with the historical data of the characteristic items to determine the simulation degree of the simulation test data.

[0049] For example, in agricultural insurance business, there are risk-related characteristic items and business-related characteristic items. Among them, risk-related characteristic items include: natural disaster risk-related characteristic items: by analyzing historical meteorological data (such as precipitation, temperature, wind speed and other meteorological data) and crop growth conditions, the natural disaster risks faced by crops (such as drought, floods, pests and diseases, etc.) are evaluated. These characteristic items can be processed by statistical methods such as data smoothing functions to obtain relatively stable climate indicators; market volatility risk-related characteristic items: using market prices to evaluate the impact of agricultural product price fluctuations on agricultural production, which can be achieved by monitoring historical data on agricultural product market prices and analyzing their fluctuation patterns and trends; policy impact-related characteristic items: evaluating the impact of relevant policies (such as agricultural subsidies, insurance policies, etc.) on agricultural production. This can be reflected by analyzing indicators such as agricultural production data and insurance compensation data before and after policy changes. Business characteristic items include: Quantity characteristic items: indicators reflecting the overall scale, level, and absolute quantity of economic phenomena closely related to agricultural insurance, such as the original insurance premium income of agricultural insurance, the number of participating farmers in agricultural insurance, and the number of cities and counties where agricultural insurance is launched; Quality characteristic items: statistical indicators reflecting the relative level of economic phenomena closely related to agricultural insurance, generally expressed as relative numbers or averages, such as the comprehensive compensation ratio of agricultural insurance, the handling fee ratio, and the premium subsidy ratio of the finance. Underwriting situation characteristic items: such as the number of insurance, the insurance amount, the premium of the signed policy, etc., are used to evaluate the underwriting scale and efficiency of agricultural insurance business. Claims situation characteristic items: including settled claims indicators (such as the number of settled claims and the settled compensation) and pending claims indicators (such as the number of pending claims and the pending compensation), which are used to evaluate the compensation situation and efficiency of agricultural insurance business.

[0050] For natural disaster risk feature items, the simulated data under the natural disaster risk feature items in the simulation test data can be compared with the corresponding real historical meteorological data to determine the simulation degree of the simulated data under the natural disaster risk feature items in the simulation test data. This verifies whether the data under the natural disaster risk feature items (such as precipitation, temperature anomalies, pest outbreaks, etc.) simulated in the simulation test data conform to the data laws of historical data. For market volatility risk feature items, the simulated data under the market volatility risk feature items in the simulation test data can be compared with the corresponding real market price data to determine the simulation degree of the simulated data under the market volatility risk feature items in the simulation test data. This verifies whether the data under the market volatility risk feature items simulated in the simulation test data conform to market laws and whether the fluctuation range is reasonable. For policy impact feature items, it verifies whether the simulation test data fully covers policy changes that may affect agricultural insurance business, including the introduction of new policies, adjustments to old policies, etc., and determines the ratio of the number of covered policies to the total number of all policies as the simulation degree of the policy impact feature items.

[0051] For business feature items, data consistency can be determined, such as whether the correspondence between premium income and compensation expenditure meets the preset conditions (such as premium income is greater than compensation expenditure, etc.), and the ratio of the amount of simulation data that meets the preset conditions to the total amount of all simulation test data is determined as the simulation degree of the business feature item. This verifies whether there are logical errors or contradictions between the various feature items of the simulation test data, and ensures the accuracy of the generated test data.

[0052] Afterwards, the mean value of the simulation degree corresponding to each characteristic item is determined as the simulation degree of the simulation test data.

[0053] Step 103: When the degree of simulation is less than a preset threshold, the simulation test data is corrected to obtain target test data of the target service.

[0054] In this application, when the degree of simulation is less than a preset threshold, it means that the simulated test data is not similar to the real business data (i.e., historical data in the production environment). The parameters of the statistical distribution model for generating the simulated test data can be fine-tuned to regenerate the simulated test data using the adjusted statistical distribution model, thereby correcting the simulated test data and obtaining the target test data for the target business.

[0055] Optionally, the simulation data corresponding to the feature items in the simulation test data whose simulation degree is less than a preset threshold value may be modified in a targeted manner to obtain target test data for the target business, thereby improving the efficiency of test data generation.

[0056] In this application, based on the preset feature items corresponding to the target business, the simulation test data of the target business is generated, and then, based on the data evaluation strategy corresponding to the target business, the simulation degree of the simulation test data is evaluated. When the simulation degree is less than the preset threshold, the simulation test data is corrected to obtain the target test data of the target business. As a result, the simulation test data is highly similar to the real production environment data, thereby improving the accuracy and efficiency of test data generation.

[0057] In order to implement the above embodiment, the present application also proposes a test data generating device.

[0058] Figure 2 A schematic diagram of the structure of a test data generating device provided in an embodiment of the present application.

[0059] like Figure 2 As shown, the test data generating device includes a generating module 210 , an evaluating module 220 , and a correcting module 230 .

[0060] A generating module 210, configured to generate simulation test data of a target service based on preset feature items corresponding to the target service;

[0061] An evaluation module 220, for evaluating the simulation degree of the simulation test data based on a data evaluation strategy corresponding to the target business;

[0062] The correction module 230 is used to correct the simulation test data when the simulation degree is less than a preset threshold value to obtain target test data of the target business.

[0063] Furthermore, in a possible implementation of the embodiment of the present application, when the target business is an auto insurance business, the data evaluation strategy includes:

[0064] Based on the numerical constraints corresponding to each characteristic item, the simulation data corresponding to each characteristic item in the simulation test data is verified to determine the simulation degree of the simulation test data.

[0065] Furthermore, in a possible implementation of the embodiment of the present application, when the target business is an agricultural insurance business, the data evaluation strategy includes:

[0066] The simulation test data is compared with the historical data of the characteristic items to determine the simulation degree of the simulation test data.

[0067] Furthermore, in a possible implementation manner of the embodiment of the present application, a determination module is further included, which is used to:

[0068] Based on the historical data of the candidate feature items corresponding to the target business, determine the relevance and importance between the candidate feature items;

[0069] Based on the relevance and importance, the feature items of the target business are determined from the candidate feature items.

[0070] Furthermore, in a possible implementation of the embodiment of the present application, the generating module 210 is used to:

[0071] Based on a conversion method associated with a numerical feature corresponding to the feature item, the historical data of the feature item is converted to obtain converted first feature data;

[0072] Based on the business constraints associated with the feature items, verify and adjust the first feature data corresponding to the feature items to obtain second feature data;

[0073] The second characteristic data is fitted to obtain a statistical distribution model, so as to generate simulation test data of the target business using the statistical distribution model.

[0074] It should be noted that the aforementioned explanation of the test data generating method embodiment is also applicable to the test data generating device of this embodiment, and will not be repeated here.

[0075] In this application, based on the preset feature items corresponding to the target business, the simulation test data of the target business is generated, and then, based on the data evaluation strategy corresponding to the target business, the simulation degree of the simulation test data is evaluated. When the simulation degree is less than the preset threshold, the simulation test data is corrected to obtain the target test data of the target business. As a result, the simulation test data is highly similar to the real production environment data, thereby improving the accuracy and efficiency of test data generation.

[0076] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0077] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0078] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0079] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0080] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0081] This application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, this application is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, risks can be minimized by limiting data collection and deleting data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of users.

[0082] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0083] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0084] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0085] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0086] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0087] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0088] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0089] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A test data generation method, characterized in that: The method comprises: Generate simulation test data of the target business based on preset feature items corresponding to the target business; Based on the data evaluation strategy corresponding to the target business, evaluating the simulation degree of the simulation test data; When the simulation degree is less than a preset threshold, the simulation test data is corrected to obtain target test data of the target service.

2. The method according to claim 1, characterized in that When the target business is auto insurance business, the data evaluation strategy includes: Based on the numerical constraints corresponding to each of the characteristic items, the simulation data corresponding to each of the characteristic items in the simulation test data are verified to determine the simulation degree of the simulation test data.

3. The method according to claim 1, characterized in that When the target business is agricultural insurance business, the data evaluation strategy includes: The simulation test data is compared with the historical data of the characteristic item to determine the simulation degree of the simulation test data.

4. The method according to claim 1, characterized in that Also includes: Determine the relevance and importance between the candidate feature items based on the historical data of the candidate feature items corresponding to the target business; Based on the relevance and the importance, a feature item of the target business is determined from the candidate feature items.

5. The method according to claim 1, characterized in that The generating of simulation test data of the target service based on preset feature items corresponding to the target service includes: Based on the conversion method associated with the numerical feature corresponding to the feature item, convert the historical data of the feature item to obtain the converted first feature data; Based on the business constraints associated with the feature item, verify and adjust the first feature data corresponding to the feature item to obtain second feature data; The second characteristic data is fitted to obtain a statistical distribution model, so as to generate simulation test data of the target business using the statistical distribution model.

6. A test data generating device, characterized in that: The device comprises: A generating module, used to generate simulation test data of the target business based on preset feature items corresponding to the target business; An evaluation module, used to evaluate the simulation degree of the simulation test data based on the data evaluation strategy corresponding to the target business; The correction module is used to correct the simulation test data when the simulation degree is less than a preset threshold value to obtain the target test data of the target business.

7. The device according to claim 6, characterized in that When the target business is auto insurance business, the data evaluation strategy includes: Based on the numerical constraints corresponding to each of the characteristic items, the simulation data corresponding to each of the characteristic items in the simulation test data are verified to determine the simulation degree of the simulation test data.

8. The device according to claim 6, characterized in that When the target business is agricultural insurance business, the data evaluation strategy includes: The simulation test data is compared with the historical data of the characteristic item to determine the simulation degree of the simulation test data.

9. The device according to claim 6, characterized in that Also included is a determination module for: Determine the relevance and importance between the candidate feature items based on the historical data of the candidate feature items corresponding to the target business; Based on the relevance and the importance, a feature item of the target business is determined from the candidate feature items.

10. The device according to claim 6, characterized in that The generating module is used for: Based on the conversion method associated with the numerical feature corresponding to the feature item, convert the historical data of the feature item to obtain the converted first feature data; Based on the business constraints associated with the feature item, verify and adjust the first feature data corresponding to the feature item to obtain second feature data; The second characteristic data is fitted to obtain a statistical distribution model, so as to generate simulation test data of the target business using the statistical distribution model.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 5 when being executed by a processor.

Images