A data verification method, device, computer device, and storage medium

Abstract

The present application discloses a data verification method, apparatus, computer device, and storage medium, belonging to the field of artificial intelligence technology. By combining historical verification data and a historical data configuration table to construct training data, the initial neural network model is trained using the training data to obtain a data configuration table generation model. A data verification instruction is received, the data to be verified corresponding to the data verification instruction is obtained, and the data to be verified is imported into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified. The data to be verified is imported into the initial data configuration table to obtain a target data configuration table, and the target data configuration table is verified by executing a preset data verification script, and the data verification result of the data to be verified is output. In addition, the present application also relates to blockchain technology, and the data to be verified can be stored in a blockchain. The present application can perform data verification configuration according to different user requirements, and at the same time improve the accuracy and timeliness of data verification.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, and particularly relates to a data verification method, device, computer device, and storage medium. Background Art

[0002] With the advent of the big data era, the amount of data has grown exponentially. Data is the foundation of each enterprise or institution, and enterprises and institutions pay more attention to data protection and backup. At the technical level of data processing, data collection, data verification, and data storage have also been further developed.

[0003] However, the current verification of data accuracy is basically achieved through manual verification, and the manual verification method has the following problems:

[0004] First, generally speaking, the error rate of manual verification is higher, and various problems will occur even for repetitive work; second, the manual verification cycle is long. Currently, for the verification of a large amount of data, the manual verification method generally needs to be verified once every few months, and the cycle may be as long as half a year or even once a year in some cases. Such a long verification cycle obviously cannot meet the needs of enterprises and institutions; third, manual verification is not comprehensive enough. In many cases, verification is carried out according to historical error-prone places, and potential problems are difficult to discover; finally, manual verification takes a long time. For some scenarios that often require verification, arranging a large amount of manpower for long-term verification each time is of little significance and may not achieve the expected results. Summary of the Invention

[0005] The purpose of the embodiments of this application is to provide a data verification method, device, computer device, and storage medium to solve the technical problems of high error rate, long cycle, long time consumption, and incomplete data verification existing in the existing manual verification data verification method.

[0006] To solve the above technical problems, the embodiments of this application provide a data verification method, which adopts the following technical solutions:

[0007] A data verification method includes:

[0008] Obtain historical verification data and the corresponding historical data configuration table;

[0009] Combine the historical verification data and the historical data configuration table to construct training data;

[0010] Import the training data into a preset initial neural network model, and use the training data to train the initial neural network model to obtain a data configuration table generation model;

[0011] Receive a data verification instruction, obtain the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table to generate a model, obtaining an initial data configuration table corresponding to the data to be verified;

[0012] Import the data to be verified into the initial data configuration table to obtain a target data configuration table;

[0013] Verify the target data configuration table by executing a preset data verification script, and output the data verification result of the data to be verified.

[0014] Furthermore, the preset initial neural network model is a convolutional neural network model. The initial neural network model includes an embedding unit, a convolutional unit, and a fully connected unit. Import the training data into the preset initial neural network model, and use the training data to train the initial neural network model to obtain a data configuration table generation model, specifically including:

[0015] Import the training data into the initial neural network model. Among them, input the historical verification data in the training data into the embedding unit of the initial neural network model, and input the historical data configuration table corresponding to the historical verification data into the fully connected unit of the initial neural network model;

[0016] Extract features and perform vector transformation processing on the historical verification data through the embedding unit of the initial neural network model to obtain a first initial vector;

[0017] Perform convolution on the first initial vector through the convolutional unit of the initial neural network model to obtain first initial feature data;

[0018] Calculate the similarity of the first initial feature data through the fully connected unit of the initial neural network model to obtain a first similarity calculation result;

[0019] Iteratively update the initial neural network model based on the first similarity calculation result until the model fits, obtaining a data configuration table generation model.

[0020] Furthermore, calculating the similarity of the first initial feature data through the fully connected unit of the initial neural network model to obtain a first similarity calculation result specifically includes:

[0021] Calculate the similarity of the first initial feature data using the classifier pre-configured in the fully connected unit of the initial neural network model to obtain a first initial feature similarity;

[0022] Sort the obtained first initial feature similarities, and combine all the first initial feature similarities whose similarity values are greater than a preset threshold to obtain a first similarity calculation result.

[0023] Further, based on the first similarity calculation result, the initial neural network model is iteratively updated until the model is fitted to obtain a data configuration table generation model, specifically including:

[0024] Determine the first initial feature data corresponding to the first similarity calculation result;

[0025] Construct an intermediate data configuration table based on the first initial feature data corresponding to the first similarity calculation result;

[0026] Compare the intermediate data configuration table with the historical data configuration table to obtain a prediction error;

[0027] Compare the prediction error with a preset error threshold, and iteratively update the initial neural network model according to the error comparison result until the model is fitted to obtain a data configuration table generation model.

[0028] Further, compare the prediction error with a preset error threshold, and iteratively update the initial neural network model according to the error comparison result until the model is fitted to obtain a data configuration table generation model, specifically including:

[0029] Transmit the prediction error in the initial neural network model based on a preset backpropagation algorithm;

[0030] Obtain the error values of each network layer in the initial neural network model;

[0031] Compare the error values of each network layer in the initial neural network model with a preset error threshold;

[0032] If there is any network layer whose error value is greater than the preset error threshold, iteratively update the initial neural network model until the error values of all network layers of the initial neural network model are less than or equal to the preset threshold, and a data configuration table generation model is obtained.

[0033] Further, the data configuration table generation model includes an embedding unit, a convolutional unit, and a fully connected unit. It receives a data verification instruction, obtains the data to be verified corresponding to the data verification instruction, and imports the data to be verified into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified, specifically including:

[0034] Obtain the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model;

[0035] Extract features and perform vector conversion processing on the data to be verified through the embedding unit of the data configuration table generation model to obtain a second initial vector;

[0036] Perform convolution on the second initial vector through the convolutional unit of the data configuration table generation model to obtain second initial feature data;

[0037] The fully connected unit of the model generated from the data configuration table calculates the similarity of the second initial feature data to obtain the second similarity calculation result;

[0038] Determine the second initial feature data corresponding to the second similarity calculation result;

[0039] Construct a data configuration table based on the second initial feature data corresponding to the second similarity calculation result to obtain the initial data configuration table.

[0040] Furthermore, by executing a preset data verification script to verify the target data configuration table, the data verification result of the data to be verified is output, specifically including:

[0041] Obtain the preset data verification script and the data verification requirement file of the data to be verified;

[0042] Execute the data verification script to parse the data verification requirement file to obtain the data verification requirements;

[0043] Traverse the target data configuration table, verify the data in the target data configuration table according to the data verification requirements, and obtain the data verification result of the data to be verified.

[0044] To solve the above technical problems, an embodiment of the present application further provides a data verification device, which adopts the following technical solutions:

[0045] A data verification device, comprising:

[0046] A historical data acquisition module, configured to acquire historical verification data and the corresponding historical data configuration table of the historical verification data;

[0047] A training data construction module, configured to combine the historical verification data and the historical data configuration table to construct training data;

[0048] A model iterative training module, configured to import the training data into a preset initial neural network model, and use the training data to train the initial neural network model to obtain a data configuration table generation model;

[0049] A data configuration table generation module, configured to receive a data verification instruction, acquire the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model to obtain the initial data configuration table corresponding to the data to be verified;

[0050] A data to be verified import module, configured to import the data to be verified into the initial data configuration table to obtain the target data configuration table;

[0051] A data automatic verification module is used to verify a target data configuration table by executing a preset data verification script and output a data verification result of the data to be verified.

[0052] To solve the above technical problems, an embodiment of the present application further provides a computer device, which adopts the following technical solutions:

[0053] A computer device includes a memory and a processor. Computer-readable instructions are stored in the memory. When the processor executes the computer-readable instructions, the steps of the data verification method described in any one of the above are implemented.

[0054] To solve the above technical problems, an embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solutions:

[0055] A computer-readable storage medium has computer-readable instructions stored thereon. When the computer-readable instructions are executed by a processor, the steps of the data verification method described in any one of the above are implemented.

[0056] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects:

[0057] The present application discloses a data verification method, device, computer device and storage medium, belonging to the field of artificial intelligence technology. The present application combines historical verification data and a historical data configuration table to construct training data, uses the training data to train an initial neural network model to obtain a data configuration table generation model, receives a data verification instruction, obtains the data to be verified corresponding to the data verification instruction, and imports the data to be verified into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified, imports the data to be verified into the initial data configuration table to obtain a target data configuration table, verifies the target data configuration table by executing a preset data verification script, and outputs a data verification result of the data to be verified. The present application trains a data configuration table generation model, uses the data configuration table generation model to generate a data configuration table of the data to be verified, and finally verifies the target data configuration table through a data verification script, which can meet the data verification requirements of different users and improve the accuracy and timeliness of data verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] To more clearly illustrate the solutions in the present application, the following will briefly introduce the drawings required for the description of the embodiments of the present application. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0059] Figure 1Shows an exemplary system architecture diagram to which the present application can be applied;

[0060] Figure 2 Shows a flowchart of an embodiment of the data verification method according to the present application;

[0061] Figure 3 Shows a schematic structural diagram of an embodiment of the data verification device according to the present application;

[0062] Figure 4 Shows a schematic structural diagram of an embodiment of the computer device according to the present application. Detailed implementation manners

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs; the terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above drawings are intended to cover non-exclusive inclusion. The terms "first", "second", etc. in the specification and claims of this application or the above drawings are used to distinguish different objects and not to describe a specific order.

[0064] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0065] In order to enable those skilled in the technical field to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings.

[0066] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0067] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0068] Terminal devices 101, 102, and 103 can be various electronic devices with a display screen and supporting web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, and desktop computers, etc.

[0069] Server 105 can be a server that provides various services. For example, it is a background server that provides support for the pages displayed on terminal devices 101, 102, and 103. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0070] It should be noted that the data verification method provided by the embodiments of the present application is generally executed by the server. Correspondingly, the data verification device is generally set in the server.

[0071] It should be understood that Figure 1 the numbers of the terminal devices, network, and server in

[0072] are merely illustrative. According to the implementation requirements, there can be any number of terminal devices, network, and server. Figure 2 Continuing to refer to

[0073] The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, mechatronics, etc. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning. The data verification method includes the following steps:

[0074] S201, Obtain historical verification data and the corresponding historical data configuration table of the historical verification data.

[0075] Specifically, the server obtains historical verification data and the corresponding historical data configuration table from a preset database. Among them, the historical verification data is the data that has undergone the data verification process, and the historical data configuration table corresponding to the historical verification data is the data configuration table used by the historical verification data in the above data verification process. The data configuration table is configured according to different data verification requirements, and various data can be quickly verified through the data configuration table.

[0076] S202, Combine the historical verification data and the historical data configuration table to construct training data.

[0077] Specifically, the server combines the historical verification data obtained from the preset database and the corresponding historical data configuration table to obtain a training data set for model training. In a specific embodiment of the present application, multiple combinations of historical verification data and historical data configuration tables can be obtained to construct a training data set.

[0078] S203, Import the training data into a preset initial neural network model, and use the training data to train the initial neural network model to obtain a data configuration table generation model.

[0079] Among them, the initial neural network model can adopt a CNN (Convolutional Neural Network) model. Convolutional Neural Networks (CNN) is a type of feedforward neural network with convolutional calculations and a deep structure, and it is one of the representative algorithms of deep learning. Convolutional neural networks have the ability of representation learning and can perform shift-invariant classification on input information according to their hierarchical structure. Therefore, they are also called "Shift-Invariant Artificial Neural Networks (SIANN)". The convolutional neural network is constructed by imitating the visual perception mechanism of organisms and can perform supervised learning and unsupervised learning. The sharing of convolutional kernel parameters in its hidden layer and the sparsity of inter-layer connections enable the convolutional neural network to learn grid-like topology features such as pixels and audio with a small amount of computation, have stable effects, and have no additional requirements for feature engineering of data.

[0080] Specifically, the server imports the training data into a preset initial neural network model and uses the training data to train the initial neural network model to obtain a data configuration table generation model. Among them, the initial neural network model includes an embedding unit, a convolutional unit, and a fully connected unit.

[0081] Specifically, the server performs feature extraction and vector conversion processing on the historical verification data through the embedding unit of the initial neural network model to obtain the initial vector of the historical verification data, performs convolution on the initial vector of the historical verification data through the convolutional unit of the initial neural network model to obtain the initial feature data of the historical verification data, performs similarity calculation on the initial feature data of the historical verification data through the fully connected unit of the initial neural network model to obtain the similarity calculation result of the historical verification data, and iteratively updates the initial neural network model based on the similarity calculation result of the historical verification data until the model is fitted to obtain a data configuration table generation model. The data configuration table generation model can be used to generate a data configuration table for the input data.

[0082] S204, receive a data verification instruction, obtain the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model to obtain the initial data configuration table corresponding to the data to be verified.

[0083] Specifically, when the server receives a data verification instruction, it obtains the data to be verified corresponding to the data verification instruction, and imports the data to be verified into the data configuration table to generate a model. The model generated by the data configuration table processes the output data to be verified. Finally, the model generated by the data configuration table outputs the initial data configuration table corresponding to the data to be verified, and realizes the rapid verification of the data to be verified through the initial data configuration table.

[0084] In this embodiment, the electronic device (such as the server shown) on which the data verification method runs can receive the data verification instruction through a wired connection method or a wireless connection method. It should be noted that the above wireless connection method can include, but is not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other currently known or future-developed wireless connection methods. Figure 1 In this embodiment, the electronic device (such as the server shown) on which the data verification method runs can receive the data verification instruction through a wired connection method or a wireless connection method. It should be noted that the above wireless connection method can include, but is not limited to, 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other currently known or future-developed wireless connection methods.

[0085] S205, Import the data to be verified into the initial data configuration table to obtain the target data configuration table.

[0086] Specifically, the server parses the initial data configuration table, and divides the data to be verified according to the information of the initial data configuration table obtained by parsing, to obtain multiple data segments, and fills the obtained multiple data segments into the initial data configuration table in sequence to obtain the target data configuration table.

[0087] S206, Verify the target data configuration table by executing a preset data verification script, and output the data verification result of the data to be verified.

[0088] Specifically, the server obtains the preset data verification script and the verification requirement file of the data to be verified, executes the data verification script to parse the data verification requirement file to obtain the data verification requirement, then traverses the target data configuration table corresponding to the data to be verified, and automatically verifies the data in the target data configuration table according to the data verification requirement to obtain the data verification result of the data to be verified.

[0089] In the embodiment of the present application, after obtaining the data verification result, fill the data verification result into the test result table. The test result table can display the verification result. The user can obtain the data test result by viewing the test result table by himself, or can present the test result online by creating an online report, clearly and intuitively displaying the data accuracy verification result, and better meeting the user's need to view data.

[0090] In the above embodiments, the present application constructs training data by combining historical verification data and a historical data configuration table, trains an initial neural network model using the training data to obtain a data configuration table generation model, receives a data verification instruction, obtains the data to be verified corresponding to the data verification instruction, and imports the data to be verified into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified. The data to be verified is imported into the initial data configuration table to obtain a target data configuration table, and the target data configuration table is verified by executing a preset data verification script, and the data verification result of the data to be verified is output. The present application trains a data configuration table generation model, uses the data configuration table generation model to generate a data configuration table for the data to be verified, and finally verifies the target data configuration table through a data verification script, which can meet the data verification requirements of different users and improve the accuracy and timeliness of data verification.

[0091] Further, the preset initial neural network model is a convolutional neural network model. The initial neural network model includes an embedding unit, a convolutional unit, and a fully connected unit. Importing the training data into the preset initial neural network model and training the initial neural network model using the training data to obtain a data configuration table generation model specifically includes:

[0092] Import the training data into the initial neural network model. Among them, input the historical verification data in the training data into the embedding unit of the initial neural network model, and input the historical data configuration table corresponding to the historical verification data into the fully connected unit of the initial neural network model;

[0093] Extract features and perform vector transformation processing on the historical verification data through the embedding unit of the initial neural network model to obtain a first initial vector;

[0094] Perform convolution on the first initial vector through the convolutional unit of the initial neural network model to obtain first initial feature data;

[0095] Perform similarity calculation on the first initial feature data through the fully connected unit of the initial neural network model to obtain a first similarity calculation result;

[0096] Iteratively update the initial neural network model based on the first similarity calculation result until the model fits to obtain a data configuration table generation model.

[0097] Specifically, the preset initial neural network model is a convolutional neural network model, and the initial neural network model includes an embedding unit, a convolutional unit, and a fully connected unit. The server imports the training data into the initial neural network model. Among them, the historical verification data in the training data is input into the embedding unit of the initial neural network model for data feature processing, and the historical data configuration table corresponding to the historical verification data is input into the fully connected unit of the initial neural network model for model iteration.

[0098] The server performs feature extraction and vector transformation processing on the historical verification data through the embedding unit of the initial neural network model to obtain the first initial vector, performs convolution on the first initial vector through the convolutional unit of the initial neural network model to obtain the first initial feature data, performs similarity calculation on the first initial feature data through the fully connected unit of the initial neural network model to obtain the first similarity calculation result, and iteratively updates the initial neural network model based on the first similarity calculation result until the model fits to obtain the data configuration table generation model.

[0099] It should be noted that initial parameters are preset for the weights and biases of each network layer in the convolutional neural network model, so that the convolutional neural network model can perform feature extraction and vector transformation processing on the training data. Among them, the weights and biases are model parameters used for refractive transformation calculation of the input data in the network, so that the result output by the network after calculation can match the actual situation.

[0100] The convolution calculation process is as follows: for an m*n matrix, taking 1D convolution as an example, a convolution kernel of x*n is constructed, and this convolution kernel slides and operates on the original matrix. For example, if the value of m is 5 and the value of x is 1, the convolution kernel slides from top to bottom. First, x multiplies and sums with the n-dimensional vector of the first row to obtain a value. Subsequently, x continues to slide down and performs convolution operations with the second row, the third row... A total of 5*1 matrix is obtained, which is the convolution result.

[0101] The fully connected layer contains a preset classifier. When the fully connected layer receives the feature data, it uses the preset classifier to calculate the similarity of the feature data and outputs the similarity calculation result.

[0102] Furthermore, performing similarity calculation on the first initial feature data through the fully connected unit of the initial neural network model to obtain the first similarity calculation result specifically includes:

[0103] Using the classifier preset in the fully connected unit of the initial neural network model to calculate the similarity of the first initial feature data to obtain the first initial feature similarity;

[0104] Sort the obtained first initial feature similarities, and combine all the first initial feature similarities whose similarity values are greater than a preset threshold to obtain a first similarity calculation result.

[0105] Specifically, the server uses a classifier pre-configured in the fully connected unit of the initial neural network model to calculate the similarity of the first initial feature data to obtain the first initial feature similarity, sorts the obtained first initial feature similarity, and combines all the first initial feature similarities whose similarity values are greater than the preset threshold to obtain the first similarity calculation result. The preset threshold can be set in advance. For example, the preset threshold is set to 0.5. At this time, the server combines the first initial feature similarities whose similarity values are greater than 0.5 in the first similarity calculation result.

[0106] Furthermore, iteratively update the initial neural network model based on the first similarity calculation result until the model fits to obtain a data configuration table generation model, which specifically includes:

[0107] Determine the first initial feature data corresponding to the first similarity calculation result;

[0108] Construct an intermediate data configuration table based on the first initial feature data corresponding to the first similarity calculation result;

[0109] Compare the intermediate data configuration table with the historical data configuration table to obtain a prediction error;

[0110] Compare the size of the prediction error with a preset error threshold, and iteratively update the initial neural network model according to the error comparison result until the model fits to obtain a data configuration table generation model.

[0111] Specifically, after the server completes the similarity calculation through the fully connected unit of the initial neural network model, it determines all the first initial feature data corresponding to the first similarity calculation result, constructs an intermediate data configuration table based on the first initial feature data corresponding to the first similarity calculation result, then compares the intermediate data configuration table with the historical data configuration table to obtain a prediction error, and transmits the prediction error according to the backpropagation algorithm, compares the size of the prediction error with the preset error threshold, and iteratively updates the initial neural network model according to the error comparison result until the model fits to obtain a data configuration table generation model.

[0112] Furthermore, compare the size of the prediction error with a preset error threshold, and iteratively update the initial neural network model according to the error comparison result until the model fits to obtain a data configuration table generation model, which specifically includes:

[0113] Transmit the prediction error in the initial neural network model based on a preset backpropagation algorithm;

[0114] Obtain the error values of each network layer in the initial neural network model;

[0115] Compare the error values of each network layer in the initial neural network model with the preset error threshold;

[0116] If there is any network layer whose error value is greater than the preset error threshold, iterate and update the initial neural network model until the error values of all network layers in the initial neural network model are less than or equal to the preset threshold, and obtain the data configuration table generation model.

[0117] Among them, the Backpropagation Algorithm is a learning algorithm suitable for multi-layer neuron networks, which is based on the gradient descent method. The input-output relationship of the backpropagation algorithm network is essentially a mapping relationship: the function completed by an n-input m-output BP neural network is a continuous mapping from the n-dimensional Euclidean space to a finite domain in the m-dimensional Euclidean space, and this mapping is highly non-linear.

[0118] Specifically, the server transmits the prediction error in the initial neural network model based on the preset backpropagation algorithm, obtains the error values of each network layer in the initial neural network model, compares the error values of each network layer in the initial neural network model with the preset error threshold, and if there is any network layer whose error value is greater than the preset error threshold, iterate and update the initial neural network model until the error values of all network layers in the initial neural network model are less than or equal to the preset threshold, and obtain the data configuration table generation model.

[0119] Furthermore, the data configuration table generation model includes an embedding unit, a convolutional unit, and a fully connected unit. It receives a data verification instruction, obtains the data to be verified corresponding to the data verification instruction, and imports the data to be verified into the data configuration table generation model to obtain the initial data configuration table corresponding to the data to be verified, specifically including:

[0120] Obtain the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model;

[0121] Extract features and perform vector conversion processing on the data to be verified through the embedding unit of the data configuration table generation model to obtain a second initial vector;

[0122] Perform convolution on the second initial vector through the convolutional unit of the data configuration table generation model to obtain second initial feature data;

[0123] Perform similarity calculation on the second initial feature data through the fully connected unit of the data configuration table generation model to obtain a second similarity calculation result;

[0124] Determine the second initial feature data corresponding to the second similarity calculation result;

[0125] Construct a data configuration table based on the second initial feature data corresponding to the second similarity calculation result to obtain an initial data configuration table.

[0126] Specifically, when performing data verification, obtain the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model. Through the embedding unit of the data configuration table generation model, perform feature extraction and vector conversion processing on the data to be verified to obtain a second initial vector. Through the convolutional unit of the data configuration table generation model, perform convolution on the second initial vector to obtain second initial feature data. Through the fully connected unit of the data configuration table generation model, perform similarity calculation on the second initial feature data to obtain a second similarity calculation result. Determine the second initial feature data corresponding to the second similarity calculation result, and construct a data configuration table based on the second initial feature data corresponding to the second similarity calculation result to obtain an initial data configuration table.

[0127] Furthermore, verify the target data configuration table by executing a preset data verification script, and output the data verification result of the data to be verified, specifically including:

[0128] Obtain a preset data verification script and a data verification requirement file for the data to be verified;

[0129] Execute the data verification script to parse the data verification requirement file to obtain data verification requirements;

[0130] Traverse the target data configuration table, and verify the data in the target data configuration table according to the data verification requirements to obtain the data verification result of the data to be verified.

[0131] Specifically, the server obtains a preset data verification script and a data verification requirement file for the data to be verified. Among them, the data verification requirement file for the data to be verified is a file uploaded by the user and records the data verification requirements of the data to be verified. Then execute the above data verification script to parse the data verification requirement file to obtain the data verification requirements in the data verification requirement file. Finally, traverse the target data configuration table, and verify the data in the target data configuration table according to the data verification requirements to obtain the data verification result of the data to be verified.

[0132] In the above embodiments, the present application discloses a data verification method, belonging to the field of artificial intelligence technology. The present application constructs training data by combining historical verification data and a historical data configuration table, trains an initial neural network model using the training data to obtain a data configuration table generation model, receives a data verification instruction, obtains the data to be verified corresponding to the data verification instruction, and imports the data to be verified into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified. The data to be verified is imported into the initial data configuration table to obtain a target data configuration table, and the target data configuration table is verified by executing a preset data verification script, and the data verification result of the data to be verified is output. The present application trains a data configuration table generation model, uses the data configuration table generation model to generate a data configuration table for the data to be verified, and finally verifies the target data configuration table through a data verification script, which can meet the data verification requirements of different users, and improve the accuracy and timeliness of data verification.

[0133] It should be emphasized that, to further ensure the privacy and security of the above data to be verified, the above data to be verified can also be stored in a node of a blockchain.

[0134] The blockchain referred to in the present application is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. A blockchain, essentially a decentralized database, is a string of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity (anti-counterfeiting) of the information and generate the next block. A blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer, etc.

[0135] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the above method embodiments. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0136] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless otherwise clearly stated in this text, there is no strict order restriction for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0137] Further referring to Figure 3 , as an implementation of the method shown above Figure 2 , this application provides an embodiment of a data verification device. This device embodiment corresponds to Figure 2 the method embodiment shown, and this device can be specifically applied to various electronic devices.

[0138] As shown in Figure 3 , the data verification device described in this embodiment includes:

[0139] A historical data acquisition module 301, configured to acquire historical verification data and a historical data configuration table corresponding to the historical verification data;

[0140] A training data construction module 302, configured to combine the historical verification data and the historical data configuration table to construct training data;

[0141] A model iterative training module 303, configured to import the training data into a preset initial neural network model, and use the training data to train the initial neural network model to obtain a data configuration table generation model;

[0142] A data configuration table generation module 304, configured to receive a data verification instruction, acquire the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified;

[0143] A data to be verified import module 305, configured to import the data to be verified into the initial data configuration table to obtain a target data configuration table;

[0144] A data automatic verification module 306, configured to verify the target data configuration table by executing a preset data verification script, and output a data verification result of the data to be verified.

[0145] Furthermore, the preset initial neural network model is a convolutional neural network model. The initial neural network model includes an embedding unit, a convolutional unit, and a fully connected unit. The model iterative training module 303 specifically includes:

[0146] A training data import sub-module for importing training data into the initial neural network model. Among them, the historical verification data in the training data is input into the embedding unit of the initial neural network model, and the historical data configuration table corresponding to the historical verification data is input into the fully connected unit of the initial neural network model;

[0147] A first feature vector conversion sub-module for performing feature extraction and vector conversion processing on the historical verification data through the embedding unit of the initial neural network model to obtain a first initial vector;

[0148] A first convolution operation sub-module for performing convolution on the first initial vector through the convolution unit of the initial neural network model to obtain first initial feature data;

[0149] A first similarity calculation sub-module for performing similarity calculation on the first initial feature data through the fully connected unit of the initial neural network model to obtain a first similarity calculation result;

[0150] A model iteration sub-module for iteratively updating the initial neural network model based on the first similarity calculation result until the model is fitted to obtain a data configuration table generation model.

[0151] Further, the similarity calculation sub-module specifically includes:

[0152] A similarity calculation unit for performing similarity calculation on the first initial feature data by using a classifier pre-configured in the fully connected unit of the initial neural network model to obtain a first initial feature similarity;

[0153] A similarity sorting unit for sorting the obtained first initial feature similarities and combining all the first initial feature similarities with similarity values greater than a preset threshold to obtain a first similarity calculation result.

[0154] Further, the model iteration sub-module specifically includes:

[0155] A feature data determination unit for determining the first initial feature data corresponding to the first similarity calculation result;

[0156] A configuration table construction unit for constructing an intermediate data configuration table based on the first initial feature data corresponding to the first similarity calculation result;

[0157] A configuration table comparison unit for comparing the intermediate data configuration table with the historical data configuration table to obtain a prediction error;

[0158] A model iteration unit for comparing the size of the prediction error with a preset error threshold and iteratively updating the initial neural network model according to the error comparison result until the model is fitted to obtain a data configuration table generation model.

[0159] Further, the model iteration unit specifically includes:

[0160] An error transmission sub-unit, configured to transmit prediction errors in the initial neural network model based on a preset backpropagation algorithm;

[0161] An error value acquisition sub-unit, configured to acquire the error values of each network layer in the initial neural network model;

[0162] An error value comparison sub-unit, configured to compare the error values of each network layer in the initial neural network model with a preset error threshold;

[0163] A model iteration sub-unit, configured to, when there is any network layer whose error value is greater than the preset error threshold, iteratively update the initial neural network model until the error values of all network layers of the initial neural network model are less than or equal to the preset threshold, so as to obtain a data configuration table generation model.

[0164] Further, the data configuration table generation model includes an embedding unit, a convolutional unit, and a fully connected unit. The data configuration table generation module 304 specifically includes:

[0165] A to-be-verified data import sub-module, configured to acquire the to-be-verified data corresponding to the data verification instruction and import the to-be-verified data into the data configuration table generation model;

[0166] A second feature vector conversion sub-module, configured to perform feature extraction and vector conversion processing on the to-be-verified data through the embedding unit of the data configuration table generation model to obtain a second initial vector;

[0167] A second convolution operation sub-module, configured to perform convolution on the second initial vector through the convolutional unit of the data configuration table generation model to obtain second initial feature data;

[0168] A second similarity calculation sub-module, configured to perform similarity calculation on the second initial feature data through the fully connected unit of the data configuration table generation model to obtain a second similarity calculation result;

[0169] A feature data determination sub-module, configured to determine the second initial feature data corresponding to the second similarity calculation result;

[0170] A configuration table construction sub-module, configured to construct a data configuration table based on the second initial feature data corresponding to the second similarity calculation result to obtain an initial data configuration table.

[0171] Further, the data automatic verification module 306 specifically includes:

[0172] A script file acquisition sub-module, configured to acquire a preset data verification script and a data verification requirement file of the to-be-verified data;

[0173] A requirements document parsing sub-module, configured to execute a data verification script to parse a data verification requirements document and obtain data verification requirements.

[0174] A data automatic verification sub-module, configured to traverse a target data configuration table and verify the data in the target data configuration table according to the data verification requirements, so as to obtain a data verification result of the data to be verified.

[0175] In the above embodiment, the present application discloses a data verification device, belonging to the field of artificial intelligence technology. The present application constructs training data by combining historical verification data and a historical data configuration table, trains an initial neural network model using the training data to obtain a data configuration table generation model, receives a data verification instruction, obtains the data to be verified corresponding to the data verification instruction, and imports the data to be verified into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified, imports the data to be verified into the initial data configuration table to obtain a target data configuration table, and verifies the target data configuration table by executing a preset data verification script, and outputs a data verification result of the data to be verified. The present application trains a data configuration table generation model, uses the data configuration table generation model to generate a data configuration table of the data to be verified, and finally verifies the target data configuration table through a data verification script, which can meet the data verification requirements of different users, and improve the accuracy and timeliness of data verification.

[0176] To solve the above technical problems, an embodiment of the present application also provides a computer device. For details, please refer to Figure 4 , Figure 4 which is a basic structural block diagram of the computer device in this embodiment.

[0177] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are communicatively connected to each other through a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented. Among them, those skilled in the art of the present technology can understand that a computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0178] The computer device can be a computing device such as a desktop computer, a notebook, a palm computer, or a cloud server. The computer device can interact with a user through a keyboard, a mouse, a remote control, a touchpad, or a voice control device, etc.

[0179] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, a hard disk, a multimedia card, a card-type memory (such as an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disc, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a FlashCard, etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit and the external storage device of the computer device 4. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the data verification method. In addition, the memory 41 can also be used to temporarily store various data that have been output or will be output.

[0180] In some embodiments, the processor 42 can be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run the computer-readable instructions stored in the memory 41 or process data, such as running the computer-readable instructions of the data verification method.

[0181] The network interface 43 can include a wireless network interface or a wired network interface, and the network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0182] The present application discloses a computer device, belonging to the field of artificial intelligence technology. In the present application, training data is constructed by combining historical verification data and a historical data configuration table, and an initial neural network model is trained using the training data to obtain a data configuration table generation model. A data verification instruction is received, the data to be verified corresponding to the data verification instruction is obtained, and the data to be verified is imported into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified. The data to be verified is imported into the initial data configuration table to obtain a target data configuration table, and the target data configuration table is verified by executing a preset data verification script, and the data verification result of the data to be verified is output. In the present application, a data configuration table generation model is trained, the data configuration table generation model is used to generate the data configuration table of the data to be verified, and finally the target data configuration table is verified by the data verification script, which can meet the data verification requirements of different users and improve the accuracy and timeliness of data verification.

[0183] The present application also provides another implementation manner, that is, a computer-readable storage medium is provided. The computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor, so that the at least one processor executes the steps of the data verification method as described above.

[0184] The present application discloses a storage medium, belonging to the field of artificial intelligence technology. In the present application, training data is constructed by combining historical verification data and a historical data configuration table, and an initial neural network model is trained using the training data to obtain a data configuration table generation model. A data verification instruction is received, the data to be verified corresponding to the data verification instruction is obtained, and the data to be verified is imported into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified. The data to be verified is imported into the initial data configuration table to obtain a target data configuration table, and the target data configuration table is verified by executing a preset data verification script, and the data verification result of the data to be verified is output. In the present application, a data configuration table generation model is trained, the data configuration table generation model is used to generate the data configuration table of the data to be verified, and finally the target data configuration table is verified by the data verification script, which can meet the data verification requirements of different users and improve the accuracy and timeliness of data verification.

[0185] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0186] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0187] Obviously, the above-described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the drawings, but do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosed content of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing specific embodiments, or perform equivalent replacements on some of the technical features. Any equivalent structure directly or indirectly using the content of the specification and drawings of the present application in other related technical fields is equally within the scope of the patent protection of the present application.

Claims

1. A data verification method, characterized in that, it includes: Obtain historical verification data and the corresponding historical data configuration table of the historical verification data; Combine the historical verification data and the historical data configuration table to construct training data; Import the training data into a preset initial neural network model, and use the training data to train the initial neural network model to obtain a data configuration table generation model; Receive a data verification instruction, obtain the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified; Import the data to be verified into the initial data configuration table to obtain a target data configuration table; Verify the target data configuration table by executing a preset data verification script, and output the data verification result of the data to be verified; The preset initial neural network model is a convolutional neural network model. The initial neural network model includes an embedding unit, a convolutional unit, and a fully connected unit. The step of importing the training data into the preset initial neural network model and using the training data to train the initial neural network model to obtain a data configuration table generation model specifically includes: Import the training data into the initial neural network model. Among them, input the historical verification data in the training data into the embedding unit of the initial neural network model, and input the historical data configuration table corresponding to the historical verification data into the fully connected unit of the initial neural network model; Extract features and perform vector conversion processing on the historical verification data through the embedding unit of the initial neural network model to obtain a first initial vector; Perform convolution on the first initial vector through the convolutional unit of the initial neural network model to obtain first initial feature data; Perform similarity calculation on the first initial feature data through the fully connected unit of the initial neural network model to obtain a first similarity calculation result; Iteratively update the initial neural network model based on the first similarity calculation result until the model fits to obtain the data configuration table generation model; The step of iteratively updating the initial neural network model based on the first similarity calculation result until the model fits to obtain the data configuration table generation model specifically includes: Determine the first initial feature data corresponding to the first similarity calculation result; Construct an intermediate data configuration table based on the first initial feature data corresponding to the first similarity calculation result; Compare the intermediate data configuration table with the historical data configuration table to obtain a prediction error; Compare the size of the prediction error with a preset error threshold, and iteratively update the initial neural network model according to the error comparison result until the model fits to obtain the data configuration table generation model.

2. The data verification method according to claim 1, characterized in that, The step of performing similarity calculation on the first initial feature data through the fully connected unit of the initial neural network model to obtain a first similarity calculation result specifically includes: Calculate the similarity of the first initial feature data by using the classifier pre-configured in the fully connected unit of the initial neural network model to obtain the first initial feature similarity; Sort the obtained first initial feature similarity and combine all the first initial feature similarities with similarity values greater than the preset threshold to obtain the first similarity calculation result.

3. The data verification method according to claim 1, characterized in that, comparing the prediction error with the preset error threshold, and iteratively updating the initial neural network model according to the error comparison result until the model is fitted to obtain the data configuration table generation model, specifically including: Transmitting the prediction error in the initial neural network model based on the preset backpropagation algorithm; Obtain the error values of each network layer in the initial neural network model; Compare the error values of each network layer in the initial neural network model with the preset error threshold; If there is any network layer with an error value greater than the preset error threshold, iteratively update the initial neural network model until the error values of all network layers of the initial neural network model are less than or equal to the preset threshold, and obtain the data configuration table generation model.

4. The data verification method according to any one of claims 1 to 3, characterized in that, The data configuration table generation model includes an embedding unit, a convolutional unit and a fully connected unit. The method for receiving a data verification instruction, obtaining the data to be verified corresponding to the data verification instruction, and importing the data to be verified into the data configuration table generation model to obtain the initial data configuration table corresponding to the data to be verified specifically includes: Obtain the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model; Perform feature extraction and vector conversion processing on the data to be verified through the embedding unit of the data configuration table generation model to obtain a second initial vector; Perform convolution on the second initial vector through the convolutional unit of the data configuration table generation model to obtain second initial feature data; Calculate the similarity of the second initial feature data through the fully connected unit of the data configuration table generation model to obtain a second similarity calculation result; Determine the second initial feature data corresponding to the second similarity calculation result; Construct a data configuration table based on the second initial feature data corresponding to the second similarity calculation result to obtain the initial data configuration table.

5. The data verification method according to claim 4, characterized in that, The method for verifying the target data configuration table by executing a preset data verification script and outputting the data verification result of the data to be verified specifically includes: Obtain a preset data verification script and a data verification requirement file of the data to be verified; Execute the data verification script to parse the data verification requirement file to obtain data verification requirements; Traverse the target data configuration table, and verify the data in the target data configuration table according to the data verification requirements to obtain the data verification result of the data to be verified.

6. A data verification device, characterized in that, The data verification device implements the steps of the data verification method according to any one of claims 1 to 5, and the data verification device includes: A historical data acquisition module, configured to acquire historical verification data and a historical data configuration table corresponding to the historical verification data; A training data construction module, configured to combine the historical verification data and the historical data configuration table to construct training data; A model iterative training module, configured to import the training data into a preset initial neural network model, and use the training data to train the initial neural network model to obtain a data configuration table generation model; A data configuration table generation module, configured to receive a data verification instruction, acquire the data to be verified corresponding to the data verification instruction, and import the data to be verified into the data configuration table generation model to obtain an initial data configuration table corresponding to the data to be verified; A data to be verified import module, configured to import the data to be verified into the initial data configuration table to obtain a target data configuration table; A data automatic verification module, configured to verify the target data configuration table by executing a preset data verification script, and output a data verification result of the data to be verified.

7. A computer device characterized in that it includes a memory and a processor, wherein computer-readable instructions are stored in the memory, and when the processor executes the computer-readable instructions, the steps of the data verification method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium characterized in that computer-readable instructions are stored on the computer-readable storage medium, and when the computer-readable instructions are executed by a processor, the steps of the data verification method according to any one of claims 1 to 5 are implemented.

Images