Native data voucher generation method and device, terminal equipment and storage medium

Abstract

The invention discloses a native data voucher generation method and apparatus, a terminal device and a storage medium. The method comprises the steps of obtaining business data, data source interface identifiers and business data generation time of a plurality of data sources; performing standardized preprocessing on the business data to obtain target business data; inputting the target business data into a pre-trained voucher generation model for data field conversion, and generating an initial native data voucher; encoding and encrypting the data source interface identifier and the initial native data credential according to a preset private key to generate a target native data credential; and storing the target native data voucher according to the business data generation time under the condition that the target native data voucher is successfully verified according to the preset public key. By implementing the method and the device, the business data of different data sources are ensured to follow a unified format and standard, the native data vouchers capable of circulating among different data sources are generated, and the generation efficiency of the native data vouchers of different data sources is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, terminal device and storage medium for generating native data credentials. Background Art

[0002] In today's digital age, information systems are widely used in all walks of life, generating a large amount of business processing data, which is crucial for corporate decision-making, auditing and compliance. The current data voucher process often relies on manual operations, and cannot capture and process business data in real time, resulting in data processing delays and failure to reflect the latest business situation. The current method of implementing data vouchers is based on the business data of each information system and requires manual operation. Because the usage requirements of each information system are different, the data formats of each information system are also inconsistent. The original data generated by the current information system can only be circulated and displayed in this system and cannot be circulated across systems. Manually unifying the format of the business data of each information system and then generating data vouchers is not only inefficient, but also due to manual operations, the accuracy and efficiency of data voucher generation cannot be guaranteed.

[0003] Therefore, how to improve the accuracy and efficiency of native data credential generation has become an urgent problem that needs to be solved. Summary of the invention

[0004] The embodiments of the present invention provide a method, apparatus, terminal device and storage medium for generating native data credentials, which can effectively solve the problems of low accuracy and efficiency in generating native data credentials in the prior art.

[0005] An embodiment of the present invention provides a method for generating a native data credential, comprising:

[0006] Obtain business data, data source interface identifiers, and business data generation time of several data sources;

[0007] Performing standardized preprocessing on the business data to obtain target business data;

[0008] Determine, according to the target business data, the business data type and business data field corresponding to the target business data; and determine, according to the business data type, the target voucher generation template type corresponding to the target business data;

[0009] Determine, according to the business data field, a target voucher generation template field corresponding to the target voucher generation template type; and generate a target voucher generation template according to the target voucher generation template type and the target voucher generation template field;

[0010] According to the target credential generation template and the target business data, the target business data is mapped to the target credential generation template to generate an initial native data credential;

[0011] Encode and encrypt the data source interface identifier and the initial native data credential according to a preset private key to generate a target native data credential;

[0012] When the target native data credential is successfully verified according to the preset public key, the target native data credential is stored according to the business data generation time;

[0013] Each target business data corresponds to a business data type, and each target business data corresponds to a plurality of business data fields.

[0014] Furthermore, the business data is subjected to standardized preprocessing to obtain target business data, including:

[0015] Identifying missing values ​​and outliers in the business data, and performing missing value filling and outlier processing on the business data to obtain processed initial business data;

[0016] Calculate the mean and standard deviation of the initial business data.

[0017] The initial business data is standardized according to the mean and the standard deviation to obtain target business data.

[0018] Furthermore, the training of the credential generation model includes:

[0019] Obtain business data samples of several different business data types;

[0020] Performing standardization preprocessing on the business data samples to obtain target business data samples;

[0021] Performing field type annotation on the data fields in the target business data sample to obtain annotated target business data samples;

[0022] According to the labeled target business data sample, the verification operation is repeatedly performed until the preset model loss function converges, thereby obtaining a trained voucher generation model;

[0023] The verification operation includes:

[0024] Inputting the labeled target business data sample into the voucher generation model to be trained, and obtaining the prediction field type corresponding to the target business data sample;

[0025] Calculating a model loss function according to the predicted field type and the field type annotation in the annotated target business data sample;

[0026] When the model loss function does not converge, update the parameters of the current credential generation model to be trained.

[0027] Further, the data source interface identifier and the initial native data credential are encoded and encrypted according to a preset private key to generate a target native data credential, including:

[0028] Get the preset private keys corresponding to several data sources;

[0029] Encode the data source interface identifier to obtain a data source interface identifier code;

[0030] Combine the data source interface identification code and the initial native data credential to obtain signature data;

[0031] Calculate the hash value corresponding to the signature data according to the signature data;

[0032] Encrypting the hash summary value according to the preset private key to obtain a target digital signature;

[0033] A target native data certificate is generated according to the initial native data certificate and the target digital signature.

[0034] Furthermore, the target native data credential is verified according to a preset public key, including:

[0035] Decrypt the target native data certificate according to a preset public key to obtain a decrypted hash summary value;

[0036] The decrypted hash summary value is compared with the hash summary value corresponding to the signature data to verify the target native data credential.

[0037] Furthermore, according to the business data generation time, the target native data credential is stored, including:

[0038] Get the current operation time;

[0039] Calculate the time interval for generating the business data according to the business data generation time and the current operation time;

[0040] Sorting the time intervals in descending order to obtain sorted time intervals;

[0041] The target native data vouchers corresponding to the sorted time intervals are stored in a preset voucher database in the order of the sorted time intervals.

[0042] As an improvement of the above solution, another embodiment of the present invention provides a native data credential generation device, including:

[0043] A data acquisition module is used to acquire business data from several data sources, data source interface identifiers, and business data generation time;

[0044] A preprocessing module, used for performing standardized preprocessing on the business data to obtain target business data;

[0045] A voucher template type determination module is used to determine the business data type and business data field corresponding to the target business data according to the target business data; and determine the target voucher generation template type corresponding to the target business data according to the business data type;

[0046] A voucher template generation module, configured to determine, according to the business data field, a target voucher generation template field corresponding to the target voucher generation template type; and to generate a target voucher generation template according to the target voucher generation template type and the target voucher generation template field;

[0047] An initial credential generation module, used to input the target business data into a pre-trained credential generation model to perform data field conversion and generate an initial native data credential;

[0048] A target credential generation module, used to encode and encrypt the data source interface identifier and the initial native data credential according to a preset private key to generate a target native data credential;

[0049] A credential storage module, used to store the target native data credential according to the business data generation time;

[0050] Each target business data corresponds to a business data type, and each target business data corresponds to a plurality of business data fields.

[0051] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, a native data credential generation method as described in the above embodiment is implemented.

[0052] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a native data credential generation method described in the above embodiment.

[0053] By implementing the present invention, at least the following beneficial effects are achieved:

[0054] The present invention provides a native data voucher generation method, apparatus, terminal device and storage medium, wherein the method can obtain business data, data source interface identifiers and business data generation time of several data sources; perform standardized preprocessing on the business data to obtain target business data; determine the business data type and business data field corresponding to the target business data according to the target business data; and determine the target voucher generation template type corresponding to the target business data according to the business data type; determine the target voucher generation template field corresponding to the target voucher generation template type according to the business data field; and determine the target voucher generation template type according to the target voucher generation template type. and the target credential generation template field, generate a target credential generation template; according to the target credential generation template and the target business data, map the target business data to the target credential generation template to generate an initial native data credential; encode and encrypt the data source interface identifier and the initial native data credential according to the preset private key to generate a target native data credential; when the target native data credential is successfully verified according to the preset public key, store the target native data credential according to the business data generation time; wherein each target business data corresponds to a business data type, and each target business data corresponds to a number of business data fields. By implementing the present invention, it is ensured that business data from different data sources follow a unified format and standard, generate native data credentials that can be circulated between different data sources, and improve the efficiency of native data credential generation from different data sources; after the pre-trained credential generation model can automatically convert data fields, the native data credential is generated by encoding and encryption, which reduces manual intervention and improves the accuracy of native data credential generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flowchart of a method for generating a native data credential provided by an embodiment of the present invention;

[0056] Figure 2 It is a structural diagram of a native data credential generation device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1, is a flow chart of a method for generating a native data credential provided by an embodiment of the present invention, comprising:

[0059] S1. Obtain business data, data source interface identifiers, and business data generation time of several data sources;

[0060] S2, performing standardization preprocessing on the business data to obtain target business data;

[0061] S3. Determine the business data type and business data field corresponding to the target business data according to the target business data; and determine the target voucher generation template type corresponding to the target business data according to the business data type;

[0062] S4. Determine, according to the business data field, a target voucher generation template field corresponding to the target voucher generation template type; and generate a target voucher generation template according to the target voucher generation template type and the target voucher generation template field;

[0063] S5. According to the target credential generation template and the target business data, the target business data is mapped to the target credential generation template to generate an initial native data credential;

[0064] S6. Encode and encrypt the data source interface identifier and the initial native data certificate according to a preset private key to generate a target native data certificate;

[0065] S7. When the target native data credential is successfully verified according to the preset public key, the target native data credential is stored according to the business data generation time;

[0066] Each target business data corresponds to a business data type, and each target business data corresponds to a plurality of business data fields.

[0067] Specifically, the business data content and data format of each data source are inconsistent, and the interfaces for data transmission by the data source are also inconsistent, so the data source interface identifiers are also inconsistent. First, the business data, data source interface identifiers and business data generation time of several data sources are obtained, and then the business data is standardized and preprocessed to obtain the target business data. Then, the target business data is input into the pre-trained credential generation model for data field conversion. For different data source formats and corresponding data fields that are inconsistent, the data is converted into data with consistent data fields, and then the initial native data credential is generated to ensure the consistency of data fields and usage methods, and reduce errors caused by different formats or standards; the data source interface identifier and the initial native data credential are encoded and encrypted according to the preset private key to generate the target native data credential. In the target native data credential, the data source interface identifier and the initial native data credential are encoded and encrypted to protect the data content from being parsed, and ensure that the data is not modified without authorization during transmission or storage; when encrypting data, the unique identification information of the data source interface is included, so that the source of the data can be accurately tracked in subsequent processing, which is convenient for problem troubleshooting and responsibility attribution; finally, when the target native data credential is successfully verified according to the preset public key, the target native data credential is stored according to the business data generation time, and the native data credential is generated and stored.

[0068] Specifically, the business data is subjected to standardized preprocessing to obtain target business data, including:

[0069] Identifying missing values ​​and outliers in the business data, and performing missing value filling and outlier processing on the business data to obtain processed initial business data;

[0070] Calculate the mean and standard deviation of the initial business data.

[0071] The initial business data is standardized according to the mean and the standard deviation to obtain target business data.

[0072] In a preferred embodiment of the present invention, business data from different data sources have missing values ​​and outliers. Standardization preprocessing is a key step to ensure data quality, which directly affects the accuracy and reliability of native data voucher generation. Before processing missing values ​​and outliers, it is necessary to first evaluate the importance of these values ​​in the data set and their possible impact on the final data voucher results, analyze the causes of missing values ​​and outliers, such as data input errors, equipment failures, etc., to determine the appropriate processing method. The processing of missing values ​​includes mean filling, median filling, filling with preset values, or interpolation methods based on neighboring values. Which strategy to choose depends on the scenario characteristics of native data voucher generation. For example, in the government affairs processing scenario, the mean can be used to fill missing values. The identification of outliers uses statistical methods (such as IQR, Z-score) or model-based methods (such as isolation forests) to identify outliers. At the same time, the outlier processing method is selected according to the scenario characteristics of native data voucher generation, including deletion, replacement, and keeping it as it is. For example, in the government affairs processing scenario, choose to delete outliers to ensure the accuracy of data voucher generation. The z-score normalization method is used, that is, the mean is subtracted from each data value and then divided by the standard deviation, to ensure that the processed data has a uniform scale, which is conducive to inputting the pre-trained credential generation model to generate the initial native data credential.

[0073] Preferably, each target business data corresponds to a business data type, and each target business data corresponds to a plurality of business data fields;

[0074] Input the target business data into the pre-trained credential generation model to perform data field conversion to generate initial native data credentials, including:

[0075] Determining, according to the target business data, the business data type and business data field corresponding to the target business data;

[0076] Determine, according to the business data type, a target voucher generation template type corresponding to the target business data;

[0077] Determine, according to the business data field, a target voucher generation template field corresponding to the target voucher generation template type;

[0078] Generate a target credential generation template according to the target credential generation template type and the target credential generation template field;

[0079] According to the target credential generation template and the target business data, the target business data is mapped to the target credential generation template to generate an initial native data credential.

[0080] In a preferred embodiment of the present invention, each target business data corresponds to a business data type, and each target business data corresponds to a plurality of business data fields;

[0081] In a preferred embodiment of the present invention, according to the target business data, the business data type and business data field corresponding to the target business data are determined, for example, the target business data whose data source is the financial system, and the corresponding business data type is the financial data type. According to the business data type, the target voucher generation template type corresponding to the target business data is determined, and the most suitable voucher generation template is selected according to the type of business data, for example, financial data may require a specific financial information template. According to the business data field, the target voucher generation template field corresponding to the target voucher generation template type is determined, and a library of multiple preset templates is preset, which covers various common business scenarios and data structures, and considers the application of data fields in different business scenarios, including whether the fields need to be dynamically adjusted or optimized according to different business scenarios. According to the target voucher generation template type and the target voucher generation template field, a target voucher generation template is generated, and according to the target voucher generation template and the target business data, the target business data is mapped to the target voucher generation template to generate an initial native data voucher. Ensure that each business data field can be accurately mapped to the corresponding field of the voucher template, including the name, data type, format, etc. of the field. Set the properties of each field in detail, such as whether it is required, default value setting, input validation rules, etc. By automatically mapping business data fields to voucher template fields, the need for manual operations is reduced and processing speed and accuracy are improved.

[0082] Schematically, the training of the credential generation model includes:

[0083] Obtain business data samples of several different business data types;

[0084] Performing standardization preprocessing on the business data samples to obtain target business data samples;

[0085] Performing field type annotation on the data fields in the target business data sample to obtain annotated target business data samples;

[0086] According to the labeled target business data sample, the verification operation is repeatedly performed until the preset model loss function converges, thereby obtaining a trained voucher generation model;

[0087] The verification operation includes:

[0088] Inputting the labeled target business data sample into the voucher generation model to be trained, and obtaining the prediction field type corresponding to the target business data sample;

[0089] Calculating a model loss function according to the predicted field type and the field type annotation in the annotated target business data sample;

[0090] When the model loss function does not converge, update the parameters of the current credential generation model to be trained.

[0091] In a preferred embodiment of the present invention, the data source interface identifier and the initial native data credential are encoded and encrypted according to a preset private key to generate a target native data credential, including:

[0092] Get the preset private keys corresponding to several data sources;

[0093] Encode the data source interface identifier to obtain a data source interface identifier code;

[0094] Combine the data source interface identification code and the initial native data credential to obtain signature data;

[0095] Calculate the hash value corresponding to the signature data according to the signature data;

[0096] Encrypting the hash summary value according to the preset private key to obtain a target digital signature;

[0097] A target native data certificate is generated according to the initial native data certificate and the target digital signature.

[0098] Each data source corresponds to a different preset private key, and the private key is stored in a secure manner, such as using a hardware security module or a secure key library to avoid private key leakage or loss. Select a suitable encoding format for the data source interface identifier, such as Base64 or Hexadecima l, to ensure that the encoded identifier will not fail due to character compatibility issues when transmitted between different systems. According to the signature data, select a suitable hash algorithm, such as SHA-256, and calculate the hash summary value corresponding to the signature data; use the preset private key to encrypt the hash summary through the selected asymmetric encryption algorithm to generate a target digital signature, and generate the target native data certificate based on the initial native data certificate and the target digital signature. Before applying the digital signature to the initial native data certificate, the hash value of the certificate should be calculated again and compared with the hash value used in the signing process to ensure that the data has not been tampered with during transmission or processing.

[0099] In a preferred embodiment of the present invention, verifying the target native data credential according to a preset public key includes:

[0100] Decrypt the target native data certificate according to a preset public key to obtain a decrypted hash summary value;

[0101] The decrypted hash summary value is compared with the hash summary value corresponding to the signature data to verify the target native data credential.

[0102] At the same time, ensure that all timestamps involved in the comparison operation are synchronized to avoid verification failures due to time differences. Once the verification is successful, the verification results should be notified to all relevant parties, and the credential status should be updated in the system to indicate that it is valid and credible; if the verification fails, it is necessary to immediately take preset security measures, such as notifying the administrator, suspending the use of the credential, and initiating further investigation. The process of verifying the target native data credential using the preset public key includes strict security measures and detailed management strategies, which together ensure the integrity, reliability and security of the data credential.

[0103] In a preferred embodiment of the present invention, storing the target native data voucher according to the business data generation time includes:

[0104] Get the current operation time;

[0105] Calculate the time interval for generating the business data according to the business data generation time and the current operation time;

[0106] Sorting the time intervals in descending order to obtain sorted time intervals;

[0107] The target native data vouchers corresponding to the sorted time intervals are stored in a preset voucher database in the order of the sorted time intervals.

[0108] By indexing the sorted time intervals, the data credential storage speed can be accelerated. At the same time, a reasonable data expiration policy can be set to regularly clean up outdated or no longer needed data and optimize the use of storage resources.

[0109] In a preferred embodiment of the present invention, a native data voucher generation method can be applied to a data voucher generation device, which can obtain business data (including business processing data, business process data, and business result data) from each information system (data source) in real time through an inter-system interface, fill the business data of each information system into the corresponding data voucher template, and generate a native data voucher. The data voucher generation device can automatically sign the initial native data voucher, add the unique number identification of the information system to the voucher, and provide the possibility of tracing the data back to the production link; and store the generated native data voucher to form a voucher library, reducing manual intervention and ensuring the accuracy of the generation of native data vouchers.

[0110] By implementing this embodiment, business data, data source interface identifiers, and business data generation time of several data sources are obtained; the business data is standardized and preprocessed to obtain target business data; the target business data is input into a pre-trained credential generation model for data field conversion to generate an initial native data credential; the data source interface identifier and the initial native data credential are encoded and encrypted according to a preset private key to generate a target native data credential; when the target native data credential is successfully verified according to a preset public key, the target native data credential is stored according to the business data generation time. By implementing the present invention, it is ensured that business data from different data sources follow a unified format and standard, and native data credentials that can be circulated between different data sources are generated, thereby improving the efficiency of native data credential generation from different data sources; after the pre-trained credential generation model can automatically convert data fields, native data credentials are generated by encoding and encryption, reducing manual intervention and improving the accuracy of native data credential generation.

[0111] See also Figure 2 , is a schematic diagram of a structure of a native data credential generation device provided by an embodiment of the present invention, comprising:

[0112] A data acquisition module is used to acquire business data from several data sources, data source interface identifiers, and business data generation time;

[0113] A preprocessing module, used for performing standardized preprocessing on the business data to obtain target business data;

[0114] An initial credential generation module, used to input the target business data into a pre-trained credential generation model to perform data field conversion and generate an initial native data credential;

[0115] A target credential generation module, used to encode and encrypt the data source interface identifier and the initial native data credential according to a preset private key to generate a target native data credential;

[0116] The credential storage module is used to store the target native data credential according to the business data generation time.

[0117] The present invention provides a native data credential generation device, which obtains business data, data source interface identifiers and business data generation time of several data sources according to a data acquisition module; performs standardized preprocessing on the business data according to a preprocessing module to obtain target business data; in an initial credential generation module, inputs the target business data into a pre-trained credential generation model to perform data field conversion to generate an initial native data credential; in a target credential generation module, encodes and encrypts the data source interface identifier and the initial native data credential according to a preset private key to generate a target native data credential; and finally, in a credential storage module, stores the target native data credential according to the business data generation time. It ensures that business data of different data sources follow a unified format and standard, generates native data credential that can be circulated between different data sources, and improves the efficiency of generating native data credential of different data sources; after the pre-trained credential generation model can automatically convert data fields, generates native data credential by encoding and encryption, reduces manual intervention, and improves the accuracy of generating native data credential.

[0118] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0119] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0120] Another embodiment of the present invention further provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements a method for generating a native data credential as described in the above embodiment when executing the computer program. The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0121] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0122] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med i aCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device or other volatile solid-state storage device.

[0123] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a native data credential generation method described in the above embodiment.

[0124] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0125] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating a native data credential, characterized in that: include: Obtain business data, data source interface identifiers, and business data generation time of several data sources; Performing standardized preprocessing on the business data to obtain target business data; Determine, according to the target business data, the business data type and business data field corresponding to the target business data; and determine, according to the business data type, the target voucher generation template type corresponding to the target business data; Determine, according to the business data field, a target voucher generation template field corresponding to the target voucher generation template type; and generate a target voucher generation template according to the target voucher generation template type and the target voucher generation template field; According to the target credential generation template and the target business data, the target business data is mapped to the target credential generation template to generate an initial native data credential; Encode and encrypt the data source interface identifier and the initial native data credential according to a preset private key to generate a target native data credential; When the target native data credential is successfully verified according to the preset public key, the target native data credential is stored according to the business data generation time; Each target business data corresponds to a business data type, and each target business data corresponds to a plurality of business data fields.

2. A method for generating a native data credential according to claim 1, characterized in that: The business data is subjected to standardized preprocessing to obtain target business data, including: Identifying missing values ​​and outliers in the business data, and performing missing value filling and outlier processing on the business data to obtain processed initial business data; Calculate the mean and standard deviation of the initial business data. The initial business data is standardized according to the mean and the standard deviation to obtain target business data.

3. A method for generating a native data credential according to claim 1, characterized in that: The training of the credential generation model includes: Obtain business data samples of several different business data types; Performing standardization preprocessing on the business data samples to obtain target business data samples; Performing field type annotation on the data fields in the target business data sample to obtain annotated target business data samples; According to the labeled target business data sample, the verification operation is repeatedly performed until the preset model loss function converges, thereby obtaining a trained voucher generation model; The verification operation includes: Inputting the labeled target business data sample into the voucher generation model to be trained, and obtaining the prediction field type corresponding to the target business data sample; Calculating a model loss function according to the predicted field type and the field type annotation in the annotated target business data sample; When the model loss function does not converge, update the parameters of the current credential generation model to be trained.

4. A method for generating a native data credential according to claim 1, characterized in that: Encoding and encrypting the data source interface identifier and the initial native data credential according to a preset private key to generate a target native data credential includes: Get the preset private keys corresponding to several data sources; Encode the data source interface identifier to obtain a data source interface identifier code; Combine the data source interface identification code and the initial native data credential to obtain signature data; Calculate the hash value corresponding to the signature data according to the signature data; Encrypt the hash summary value according to the preset private key to obtain a target digital signature; A target native data certificate is generated according to the initial native data certificate and the target digital signature.

5. A method for generating a native data credential according to claim 4, characterized in that: Verifying the target native data credential according to the preset public key includes: Decrypt the target native data certificate according to a preset public key to obtain a decrypted hash summary value; The decrypted hash summary value is compared with the hash summary value corresponding to the signature data to verify the target native data credential.

6. A method for generating a native data credential according to claim 5, characterized in that: According to the business data generation time, the target native data credential is stored, including: Get the current operation time; Calculate the time interval for generating the business data according to the business data generation time and the current operation time; Sorting the time intervals in descending order to obtain sorted time intervals; The target native data vouchers corresponding to the sorted time intervals are stored in a preset voucher database in the order of the sorted time intervals.

7. A native data credential generation device, characterized in that: include: A data acquisition module is used to acquire business data from several data sources, data source interface identifiers, and business data generation time; A preprocessing module, used for performing standardized preprocessing on the business data to obtain target business data; A voucher template type determination module is used to determine the business data type and business data field corresponding to the target business data according to the target business data; and determine the target voucher generation template type corresponding to the target business data according to the business data type; A voucher template generation module, configured to determine, according to the business data field, a target voucher generation template field corresponding to the target voucher generation template type; and to generate a target voucher generation template according to the target voucher generation template type and the target voucher generation template field; An initial credential generation module, used to input the target business data into a pre-trained credential generation model to perform data field conversion and generate an initial native data credential; A target credential generation module, used to encode and encrypt the data source interface identifier and the initial native data credential according to a preset private key to generate a target native data credential; A credential storage module, used to store the target native data credential according to the business data generation time; Each target business data corresponds to a business data type, and each target business data corresponds to a plurality of business data fields.

8. A terminal device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements a native data credential generation method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute a native data credential generation method as described in any one of claims 1 to 6.

Images