WO2021196935A1

WO2021196935A1 - Data checking method and apparatus, electronic device, and storage medium

Info

Publication number: WO2021196935A1
Application number: PCT/CN2021/078082
Authority: WO
Inventors: 刘振涛
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2020-04-01
Filing date: 2021-02-26
Publication date: 2021-10-07
Also published as: CN111598122A; CN111598122B

Abstract

Disclosed in the present application are a data checking method and apparatus, an electronic device, and a storage medium, wherein same relate to the technical field of data processing. The data checking method comprises: acquiring the service type of a target service, and an image file, which needs to be checked, in the target service; and determining the file type of the image file according to the image file, determining, according to the service type and the file type of the image file, the file type of a target checking file that needs to perform checking, and determining a data source identifier of the target checking file and a file identifier of the target checking file according to the image file, wherein the target checking file is a file that checks the image file. According to the technical solution provided in the present application, image files can be quickly and accurately checked.

Description

Data verification method, device, electronic equipment and storage medium

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on April 1, 2020, the application number is CN202010249650.5, and the invention title is "data verification method, device, electronic equipment and storage medium", and its entire content Incorporated in this application by reference.

Technical field

This application relates to the field of data processing technology, in particular to data-based verification methods, devices, electronic equipment and storage media.

Background technique

At present, in the self-service processing of a certain business, in order to improve the efficiency of business processing, users can only upload image files related to the business handled, and the system will verify the image files uploaded by the user based on the real verification file. , In order to ensure that the uploaded image files are true and effective, and thus facilitate the smooth processing of the business.

The inventor realized that as the types of services increase and the number of image files that need to be verified for each type of service increases, the prior art lacks a mechanism for quickly and accurately verifying each image file.

Summary of the invention

A data verification method includes: obtaining the business type of the target business and the image files that need to be verified by the target business; determining the file type of the image file according to the image file, and according to the business type and the image The file type of the file determines the file type of the target verification file that needs to be verified, and the data source identifier of the target verification file and the file identifier of the target verification file are determined according to the image file, wherein the target verification file It is a file for verifying image files; input the business type and the file type of the image file into the pre-trained first machine learning model, and output that the image file corresponding to the file type needs to be verified The first field name of the pre-trained first machine learning model is obtained by training sample data including the business type, the file type of the image file, and the first field name in the image file that needs to be verified; input the image The file type of the file, the service type, the file type of the target verification file, and the first field name to the pre-trained second machine learning model, the output is obtained in the target verification file for the The second field name for verifying the field value data in the first field name. The pre-trained second machine learning model uses the business type, the file type of the target verification file, and the target verification file to verify the first The field value data in the field name is obtained by training the sample data of the second field name for verifying the field value data, and the field value data in the second field name is used to verify the field value data in the first field name; Acquiring the field value data in the first field name according to the first field name, and acquiring the target verification file according to the data source information of the target verification file and the file identifier of the target verification file; The field value data in the first field name is verified based on the field value data in the second field name in the target verification file.

A data verification device includes: a first acquisition unit, used to acquire the business type of a target business and the image file that the target business needs to be verified; a first execution unit, used to determine the image file according to the image file The file type of the target verification file to be verified is determined according to the service type and the file type of the image file, and the data source identification and target verification of the target verification file are determined according to the image file. The file identification of the verification file, wherein the target verification file is a file for verifying the image file; the second execution unit is used to input the service type and the file type of the image file to the pre-trained first In the machine learning model, the first field name that needs to be verified in the image file corresponding to the file type is output, and the pre-trained first machine learning model includes the service type, the file type of the image file, and the image The sample data of the first field name in the file that needs to be verified is obtained through training; the third execution unit is used to input the file type of the image file, the service type, the file type of the target verification file, and the From the first field name to the second pre-trained machine learning model, output the second field name obtained in the target verification file for verifying the field value data in the first field name, and the pre-training The second machine learning model is obtained by training the sample data containing the business type, the file type of the target verification file, and the second field name in the target verification file that verifies the field value data in the first field name, so The field value data in the second field name is used to verify the field value data in the first field name; the second obtaining unit is used to obtain the field value data in the first field name according to the first field name. And obtain the target verification file according to the data source information of the target verification file and the file identifier of the target verification file; the verification unit is used to obtain the target verification file based on the data in the target verification file The field value data in the second field name is verified against the field value data in the first field name.

An electronic device includes a memory and a processor, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the following steps:

Obtain the service type of the target service and the image file that needs to be verified for the target service; determine the file type of the image file according to the image file, and determine the need for verification according to the service type and the file type of the image file The file type of the target verification file, and the data source identification of the target verification file and the file identification of the target verification file are determined according to the image file, wherein the target verification file is a file for verifying the image file Input the service type and the file type of the image file to the pre-trained first machine learning model, and output the first field name that needs to be verified in the image file corresponding to the file type, and the pre- The trained first machine learning model is obtained by training the sample data containing the service type, the file type of the image file, and the first field name in the image file that needs to be verified; input the file type of the image file, the service type , The file type of the target verification file and the first field name to the pre-trained second machine learning model, and output the data of the field value in the first field name in the target verification file The name of the second field to be verified. The pre-trained second machine learning model collates the field value data in the first field name by including the business type, the file type of the target verification file, and the target verification file. The sample data of the second field name of the verification is obtained through training, and the field value data in the second field name is used to verify the field value data in the first field name; the obtained data is obtained according to the first field name The field value data in the first field name, and obtain the target verification file according to the data source information of the target verification file and the file identifier of the target verification file; based on the data in the target verification file The field value data in the second field name is verified against the field value data in the first field name.

A storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the following steps:

This application can quickly and accurately verify each image file.

Description of the drawings

Fig. 1 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of the present application can be applied.

Fig. 2 is a flowchart of a data verification method shown in an exemplary embodiment of the application.

FIG. 3 is a specific flowchart of step S220 of the data verification method shown in an exemplary embodiment of the application.

Fig. 4 is a flowchart of a data verification method shown in an exemplary embodiment of the application.

Fig. 5 is a flowchart of a data verification method shown in an exemplary embodiment of the application.

Fig. 6 is a block diagram of a data verification device shown in an exemplary embodiment of the present application.

Fig. 7 is an exemplary block diagram of an electronic device for implementing the foregoing data verification method according to an exemplary embodiment of the present application.

Fig. 8 shows a computer-readable storage medium for implementing the above-mentioned data verification method according to an exemplary embodiment of the present application.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms, and should not be construed as being limited to the examples set forth herein; on the contrary, the provision of these embodiments makes this application more comprehensive and complete, and fully conveys the concept of the example embodiments To those skilled in the art.

In addition, the described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to give a sufficient understanding of the embodiments of the present application. However, those skilled in the art will realize that the technical solutions of the present application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be used. In other cases, well-known methods, devices, implementations or operations are not shown or described in detail in order to avoid obscuring various aspects of the present application.

The block diagrams shown in the drawings are merely functional entities, and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in the form of software, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor devices and/or microcontroller devices. entity.

The flowchart shown in the drawings is only an exemplary description, and does not necessarily include all contents and operations/steps, nor does it have to be performed in the described order. For example, some operations/steps can be decomposed, and some operations/steps can be combined or partially combined, so the actual execution order may be changed according to actual conditions.

As shown in FIG. 1, the system architecture may include a client (as shown in FIG. 1, one or more of the smart phone 101, the tablet computer 102, and the portable computer 103, of course, it may also be a desktop computer, etc.), a network 104 And server 105. The network 104 is a medium used to provide a communication link between the client and the server 105. The network 104 may include various connection types, such as wired communication links, wireless communication links, and so on.

It should be understood that the numbers of clients, networks, and servers in FIG. 1 are merely illustrative. There can be any number of clients, networks, and servers according to implementation needs. For example, the server 105 may be a server cluster composed of multiple servers. The user can use the client to interact with the server 105 through the network 104 to receive or send messages, etc. The server 105 can be a server that provides various services, such as a server that provides a data verification service.

Taking the execution subject as the client as an example, the client obtains the business type of the target business and the image files that need to be verified by the target business; determines the file type of the image file according to the image file, and determines the need according to the business type and the file type of the image file The file type of the target verification file to be verified, and the data source identification of the target verification file and the file identification of the target verification file are determined according to the image file, where the target verification file is the file for verifying the image file; Input the business type and the file type of the image file to the pre-trained first machine learning model, and output the first field name that needs to be verified in the image file corresponding to the file type. The pre-trained first machine learning model contains There are business types, image file file types, and image files that need to be verified by the sample data training of the first field name; the file type of the input image file, the business type, the file type of the target verification file, and the first field name In the pre-trained second machine learning model, the output is obtained in the target verification file to verify the field value data in the first field name. The pre-trained second machine learning model contains the business The type, the file type of the target verification file and the sample data of the second field name in the target verification file that verify the field value data in the first field name are obtained by training, and the field value data in the second field name is used for Verify the field value data in the first field name, and obtain the field value data in the first field name according to the first field name, and obtain it according to the data source information of the target verification file and the file identification of the target verification file Target verification file; verify the field value data in the first field name based on the field value data in the second field name in the target verification file.

Through the pre-trained first machine learning model, it is possible to quickly determine the first field name in each image file that needs to be verified according to the business type of the target business and the image file that needs to be verified. The field value data in other field names that do not need to be verified are verified; the second machine learning model can be used to verify the file type of the image file, the business type, the file type of the target file, and the first field through the pre-trained second machine learning model Determine the name of the second field in the target verification file that needs to be verified against the field value data in the first field name, so as to quickly and accurately determine the verification file that needs to be verified and the verification file that needs to be verified. The field value data in one field name is effectively checked for the field value data in the second field name. While ensuring the accuracy of the verification result, it realizes the rapid and accurate verification of each image file; in addition, in this In the solution, even in the scenario of business types and multiple image files, only the training data of the pre-trained machine learning model needs to be adjusted, so that the solution can adapt to more complex business scenarios, and then achieve the target business Each image file to be verified is quickly and accurately verified.

It should be noted that the data verification method provided in the embodiments of the present application is generally executed by the client, and correspondingly, the data verification device is generally set in the client. However, in other embodiments of the present application, the server 105 may also have similar functions as the client, so as to execute the solution of the data verification method provided in the embodiments of the present application. The implementation details of the technical solutions of the embodiments of the present application will be described in detail below.

Referring to FIG. 2, FIG. 2 is a flowchart of a data verification method shown in an exemplary embodiment of this application. The execution subject of the data verification method in this embodiment is the client, as shown in FIG. 1 It may include the following steps S210 to S260, which are described in detail as follows.

In step S210, the service type of the target service and the image file that needs to be verified for the target service are obtained.

In one embodiment, the target business refers to a specific business that the user can handle. For example, in a loan scenario, different business types such as insurance policy loan, mortgage loan, and personal housing loan can be used. The image file that needs to be verified by the target business is used as the image file that needs to be verified when the user enters the business. For example, when handling a specific business, the user can enter the type of business handled and the image file that needs to be verified through the virtual button provided on the business handling page of the client. It is understandable that the number of image files can be One or more, the number of image files can be determined according to the actual needs of handling the business.

In step S220, the file type of the image file is determined according to the image file, the file type of the target verification file that needs to be verified is determined according to the service type and the file type of the image file, and the file type of the target verification file to be verified is determined according to the The image file determines the data source identification of the target verification file and the file identification of the target verification file, wherein the target verification file is a file for verifying the image file.

In one embodiment, the file type of the image file refers to the file type determined after the image file is recognized. In a non-business scenario, the file types of image files are different. For example, in a loan scenario, the file types of image files can be ID cards, insurance policies, real estate certificates, mortgage contracts, etc. When determining the file type of the image file, the file type can be determined based on the character data contained in the image file.

Referring to FIG. 3, FIG. 3 is a specific flowchart of step S220 of the data verification method shown in an exemplary embodiment of the application. Step S220 may include step S310 to step S320, which are described in detail as follows.

Step S310: Perform OCR character recognition on the image file to obtain recognized text information.

In one embodiment, when the file type of the image file is determined according to the image file, the image file may be subjected to OCR character recognition to obtain the recognized text information. The recognized text information refers to the recognition of all character data in the image file The character data collection obtained afterwards. Among them, the character data set includes the character string corresponding to each field name in the image file and the character string corresponding to the field value data in each field name. For example, in a loan scenario, if the image file that needs to be verified is an insurance policy image, in the character data set after OCR character recognition is performed on the policy image file, the character string corresponding to the field name is "Insured Name", "Insurance amount", "Insurance company name", "Insurance policy number", etc., and the field value data in the field name of "Insurant name" corresponds to the string "Zhang San", and the value in the field name "Insurance amount" The string corresponding to the field value data can be "10000.00", the string corresponding to the field value data in the field name "Insurance Company Name" can be "Ping An Insurance Company of China", the string in the field name "Insurance No." The character string corresponding to the field value data can be "5485426232".

Step S320: Determine the file type of the image file according to the key field name included in the recognized text information.

In one embodiment, since the field names contained in different file types may have differences, the image files can be classified based on the key field names with differences, so as to determine the file type of the image file. For example, in a loan scenario, for a certain image file, if the recognized text information after recognizing the image file contains "name of applicant", "name of insurance company", "policy number" and "type of insurance". The four key field names can determine the file type of the image file as the insurance policy. It should be pointed out that the key field name generally identifies the specific field name in the image file. The specific field name can be one or multiple. The number of specific field names can be determined according to the actual classification situation. .

Please continue to refer to FIG. 2. In this embodiment, the verification file is a file for verifying the character data contained in the image file, where the file type of the verification file is the same as the file type and service type of the image file. There is a mapping relationship between the two. After obtaining the file type of the image file, when determining the file type of the verification file for verifying the image file, it can be based on the file type of the obtained image file, as well as the file type of the verification file and the file of the image file. The mapping relationship between the type and the service type determines the file type of the verification file used to verify the image file.

For example, in the insurance policy loan business in the loan scenario, the image files that need to be verified include the insurance policy image file, the ID card image file, and the loan note image file input by the user. When determining the verification file for verifying each image file, for the policy image file input by the user in the policy loan business, it can be determined according to the mapping relationship that the real policy file of the insurance company needs to be used to perform the verification on the policy image file input by the user. Verification; for the ID card image file input by the user in the insurance policy loan business, according to the mapping relationship, it can be determined that the ID card image file needs to be verified by calling the ID card file stored by the Ministry of Public Security; for the insurance policy loan business by the user input According to the mapping relationship, it can be determined that part of the character data in the real insurance policy file of the insurance company needs to be used to verify the loan note image file.

In one embodiment, the data source identification may specifically be the identification information of the external data server or the local data server storing the verification file, and the file identification of the verification file is used as the unique identification information for identifying the verification file, such as a data ticket number. . In order to obtain the verification file for verification, it is also necessary to determine the data source identification of the verification file and the file identification of the verification file. Specifically, the data source identification and verification of the verification file can be determined according to the character data in the image file. The file ID of the file.

For example, in the policy loan business of the loan scenario, for the policy image file input by the user in the policy loan business, since the verification file for verifying the policy image file is also the policy file, in order to obtain the policy file for verification, OCR character recognition can be performed on the policy image file input by the user to obtain the recognized text information, where the recognized text information includes all the character data in the policy image file, and the recognized text information contains the "insurance company name" The field value data "Ping An Insurance Company of China" in this field name is used as the data source identification of the policy document to be verified, and the field value data "5485426232" in the field name of the recognized text information "insurance policy number" is used as The document identification of the insurance policy document to be verified, thereby facilitating the acquisition of the insurance policy document to be verified according to the data source identification and the document identification of the insurance policy document.

In step S230, input the service type and the file type of the image file into the pre-trained first machine learning model, and output the first field name that needs to be verified in the image file corresponding to the file type The pre-trained first machine learning model is obtained by training the sample data including the service type, the file type of the image file, and the name of the first field in the image file that needs to be verified.

In one embodiment, the first field is the name of the field in the image file that needs to be verified for the field value data in the field name. It should be pointed out that when handling different services, the image file type There will be differences in the field names that need to be verified in files and image files. There is an association between the field names that need to be verified in image files, the type of business handled and the file type of the image file. For example, in the policy loan business in the loan scenario, when the business handled is the policy loan business and the image file input by the user is an ID card image file, the first field that needs to be verified on the ID card image file is named "name" And "ID number", that is, only the field value data in the two first field names of "name" and "ID number" need to be verified.

When handling a certain type of target business, in order to determine the first field name that needs to be verified in each image file input by the user, the business type of the target business that needs to be processed and the file of each image file input by the user can be The type is input into the pre-trained first machine learning model, and the first field name that needs to be verified in each image file input by the user is determined. It should be pointed out that the field names that need to be verified can be all the field names contained in the image file, and of course, they can also be part of the field names contained in the image file.

Referring to FIG. 4, FIG. 4 is a flowchart of a data verification method shown in an exemplary embodiment of this application, which may include steps S410 to S420, which are described in detail as follows.

In step S410, the training set sample data used for training the first machine learning model to be trained is obtained, and each piece of sample data in the training set sample data includes the business type, the file type of the image file, and the image file. The name of the first field to be checked.

In one embodiment, the pre-trained first machine learning model is obtained by training the machine learning model through training sample data. Among them, the first machine learning model may be a CNN (Convolutional Neural Network, convolutional neural network) model, or may also be a deep neural network model.

The specific training process of the first machine learning model is as follows: Obtain the training set sample data used for training. Each piece of sample data in the training set sample data includes the business type of the existing target business, and the existing target business needs to be verified. The file type of each image file and the name of the first field that needs to be verified in each image file.

In step S420, the first machine learning model to be trained is trained using the training set sample data to obtain the first machine learning model after training.

The first machine learning model is trained based on the acquired training set sample data to obtain the trained first machine learning model.

Referring to FIG. 5, FIG. 5 is a flowchart of a data verification method shown in an exemplary embodiment of this application, which may include steps S510 to S530, which are described in detail as follows.

In step S510, obtain test set sample data used for verifying the trained first machine learning model, and each piece of sample data in the test set sample data includes the business type, the file type of the image file, and the image file The name of the first field to be checked in.

In order to determine whether the first machine learning model meets the expected demand, the trained first machine learning model can also be verified through test sample data. Specifically, the test set sample data can be obtained. Each piece of sample data in the test set sample data also includes the business type of the existing target business, the file type of each image file that needs to be verified by the existing target business, and each image file The name of the first field to be checked in.

In step S520, the service type of each sample data and the file type of the image file of the test set sample data are input to the first machine learning model after training, and the first machine learning model that needs to be verified is outputted from the predicted image file. A field name.

Input the business type and file type into the trained first machine learning model, and get the predicted field name of the image file under the file type that needs to be verified; determine the known file type in the training set sample data Whether the field names that need to be verified in the image file under the file type are consistent with the predicted field names that need to be verified in the image file under the file type, the first machine training model that has been trained is verified.

In step S530, if the first field name in the image file in the test set sample data that needs to be verified is the same as the first field name in the predicted image file that needs to be verified, the number of sample data pieces is all the same. If the proportion of the total number of sample data in the test set sample data exceeds a predetermined proportion threshold, the trained first machine learning model is identified as the pre-trained first machine learning model.

If in the training set sample data, it is known that the field names that need to be verified in the image files under this file type are the same as the predicted field names in the image files under this file type. The number of sample data pieces If the proportion of the number of sample data in the training set sample data exceeds the predetermined proportion threshold, the verification has passed, otherwise, the verification has not passed, and the first machine learning model needs to continue to be trained until the verification passes.

Please also continue to refer to FIG. 2. In step S240, input the file type of the image file, the service type, the file type of the target verification file, and the first field name to the pre-trained second machine learning In the model, the second field name for verifying the field value data in the first field name in the target verification file is output, and the pre-trained second machine learning model contains business types, The file type of the target verification file and the sample data of the second field name in the target verification file for verifying the field value data in the first field name are obtained by training, and the field value data in the second field name is used for Verify the field value data in the first field name.

For the field value data in the first field name that needs to be verified in a certain image file input by the user, it needs to be verified by the field value data in the second field name in the target verification file.

Due to different business types, different file types of image files, different file types of target verification files, or different first field names corresponding to the field value data in the image files that need to be verified, the target verification will be caused. There will be differences in the name of the second field that needs to be verified in the verification file. In order to quickly determine the name of the second field that needs to be verified in the target verification file, you can enter the file type of the image file, the business type, the file type of the target verification file, and the first field name to the pre-trained second machine learning In the model, output the second field name that is used to verify the field value data in the first field name in the target verification file, so that the field value data in the second field name can be used to compare the field in the first field name. Value data is checked.

For example, in the insurance policy loan business of the loan scenario, when verifying the image file of the loan note, the first field name corresponding to the value data of each field in the image file of the loan note that needs to be verified includes "lender name" and "loan" Personal ID” and “Lender’s mobile phone number”. Since the target verification file that needs to be verified on the loan note image file is the insurance policy, the second field name used to verify the field value data in the first field name in the insurance policy includes "insurant name", " "Insured's ID card" and "Insured's mobile phone number". Among them, the field value data in the second field name of "Insurant Name" is used to verify the field value data in the first field name of "Lender Name", and the second field name of "Insurant ID card" The field value data in the "Lender ID" is used to verify the field value data in the first field name, and the field value data in the second field name "Insured’s mobile phone number" The field value data in the first field name of "phone number" is checked.

The second machine learning model may be a CNN (Convolutional Neural Network, convolutional neural network) model or a deep neural network model. The sample data for training of the second machine learning model includes the business type, the file type of the verification file, and the sample data of the second field name that is used to verify the field value data in the first field name in the verification data. The field value data in the second field name is used to verify the field value data in the first field name. Since the training process of the pre-trained second machine learning model is similar to the pre-trained first machine learning model, we will not repeat it .

In step S250, the field value data in the first field name is obtained according to the first field name, and the data source information of the target check file and the file identifier of the target check file are obtained. Target verification file;

In one embodiment, in determining each first field name that needs to be verified in the image file, the field value data in the first field name that needs to be verified can be obtained according to the corresponding character data in the first field name image file , As the field value data for verification.

After obtaining the data source information and file identifier of the target verification file, the target server that needs to obtain the target verification file can be determined according to the data source information of the target verification file, and the target server can be obtained from the server storing the target verification file according to the file identifier. The required target verification file.

In step S260, the field value data in the first field name is verified based on the field value data in the second field name in the target verification file.

In one embodiment, after obtaining the field value data in the first field name that needs to be verified in the image file and the field value data in the second field name in the target verification file, it will be checked according to the target The field value data in the second field name of the image file is verified against the field value data in the first field name that needs to be verified. Based on the field value data in the second field name in the target verification file, verify the field value data in the first field name that needs to be verified in the image file to ensure that it can be accurate for each image file Local verification improves the accuracy of verification; in addition, verification is only performed on the field value data in the first field name that needs to be verified in the image file, and it can also avoid all field names contained in the image file. The field value data in are all verified, which improves the efficiency of verification.

It can be seen from the above that the pre-trained first machine learning model can quickly determine the name of the first field in each image file that needs to be verified according to the business type of the target business and the image file that needs to be verified, and then you can Avoid verifying the field value data in other field names in the image file that does not need to be verified; the second machine learning model can be used to verify the file according to the file type, business type, and target of the image file through the pre-trained second machine learning model The type and the first field name determine the second field name in the target verification file that needs to be verified for the field value data in the first field name, so as to quickly and accurately determine the verification file that needs to be verified and the verification The field value data in the second field name that needs to be effectively checked for the field value data in the first field name in the file, while ensuring the accuracy of the verification result, realizes the rapid and accurate verification of each image file In addition, in this solution, even in the context of business types and multiple image files, only the training data of the pre-trained machine learning model needs to be adjusted, so that the solution can adapt to more complex business scenarios, and then Achieve quick and accurate verification of each image file to be verified in the target business.

In one embodiment, after step S250, it may further include the step of: obtaining field value data in the second field name in the target verification file and verifying the field value data in the first field name. The verification result of, displays the verification result.

When the verification result is displayed, the verification result can be imported into the corresponding display document template according to the text type of the verification file and the corresponding relationship between the file type of the image text input by the user and the display document template to generate Display documents for display to facilitate and more intuitively view the corresponding verification results.

Referring to FIG. 6, FIG. 6 is a block diagram of a data verification device shown in an exemplary embodiment of the present application. The data verification device 600 may be integrated in the above-mentioned client, and may specifically include a first acquiring unit 610 and a second acquiring unit 610. An execution unit 620, a second execution unit 630, a third execution unit 640, a second acquisition unit 650, and a verification unit 660.

Wherein, the first obtaining unit 610 is used to obtain the service type of the target service and the image file for which the target service needs to be verified; the first execution unit 620 is used to determine the file type of the image file according to the image file, and Determine the file type of the target verification file to be verified according to the service type and the file type of the image file, and determine the data source identifier of the target verification file and the file identifier of the target verification file according to the image file , Wherein the target verification file is a file for verifying an image file; the second execution unit 630 is configured to input the service type and the file type of the image file into the pre-trained first machine learning model , Output to obtain the first field name that needs to be verified in the image file corresponding to the file type, and the pre-trained first machine learning model contains the business type, the file type of the image file, and the image file that needs to be checked. The sample data of the first field name for verification is obtained through training; the third execution unit 640 is used to input the file type of the image file, the service type, the file type of the target verification file, and the first field Name to the second pre-trained machine learning model, output the second field name obtained in the target verification file for verifying the field value data in the first field name, and the pre-trained second The machine learning model is obtained by training the sample data containing the business type, the file type of the target verification file, and the second field name in the target verification file that verifies the field value data in the first field name. The second The field value data in the field name is used to verify the field value data in the first field name; the second obtaining unit 650 is used to obtain the field in the first field name according to the first field name Value data, and obtain the target verification file according to the data source information of the target verification file and the file identification of the target verification file; the verification unit 660 is configured to obtain the target verification file based on the first The field value data in the second field name is verified against the field value data in the first field name.

In one embodiment, the first execution unit includes: a recognition sub-unit for performing OCR character recognition on the image file to obtain recognized text information; and an execution sub-unit for obtaining recognized text information based on the recognized text information. The field name determines the file type of the image file.

In an embodiment, the data verification device further includes: a display unit, configured to obtain a comparison of the field value data in the first field name based on the field value data in the second field name in the target verification file The verification result of data verification, the verification result is displayed.

In an embodiment, the data verification device further includes: a third acquiring unit, configured to acquire training set sample data used for training the first machine learning model to be trained, each of the training set sample data The piece of sample data includes the business type, the file type of the image file, and the name of the first field in the image file that needs to be verified; the training unit is used to train the first machine learning model to be trained through the training set sample data to obtain The first machine learning model after training.

In an embodiment, the data verification device further includes: a fourth acquiring unit configured to acquire test set sample data used to verify the trained first machine learning model, and the test set sample data Each piece of sample data includes the business type, the file type of the image file, and the name of the first field in the image file that needs to be verified; the fourth execution unit is used to convert the business type of each sample data of the test set sample data , The file type of the image file is input to the first machine learning model after training, and the first field name that needs to be verified in the predicted image file is output; the detection unit is used to determine if the image file in the test set sample data The proportion of the number of sample data items whose first field name needs to be verified and the first field name needed to be verified in the predicted image file are the same in the total number of sample data items in the test set sample data exceeds a predetermined ratio Threshold, the trained first machine learning model is identified as the pre-trained first machine learning model.

For the implementation process of the functions and roles of each module in the above-mentioned device, refer to the implementation process of the corresponding steps in the above-mentioned data-based verification method for details, which will not be repeated here.

It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments disclosed in the present application, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of a module or unit described above can be further divided into multiple modules or units to be embodied.

In addition, although the various steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that these steps must be performed in the specific order, or that all the steps shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and/or one step may be decomposed into multiple steps for execution, etc.

Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , Including several instructions to make a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) execute the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method, or a program product. Therefore, each aspect of the present application can be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to herein as "Circuit", "Module" or "System".

Referring to FIG. 7, FIG. 7 is an exemplary block diagram of an electronic device for implementing the foregoing data verification method according to an exemplary embodiment of the application. The electronic device 700 shown in FIG. 7 is only an example, and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

As shown in FIG. 7, the electronic device 700 is represented in the form of a general-purpose computing device. The components of the electronic device 700 may include, but are not limited to: the aforementioned at least one processing unit 710, the aforementioned at least one storage unit 720, and a bus 730 connecting different system components (including the storage unit 720 and the processing unit 710).

Wherein, the storage unit stores program code, and the program code can be executed by the processing unit 710, so that the processing unit 710 executes the various exemplary methods described in the “Exemplary Method” section of this specification. Steps of implementation. For example, the processing unit 710 may perform the following steps:

The storage unit 720 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 7201 and/or a cache storage unit 7202, and may further include a read-only storage unit (ROM) 7203.

The storage unit 720 may also include a program/utility tool 7204 having a set of (at least one) program module 7205. Such program module 7205 includes but is not limited to: an operating system, one or more application programs, other program modules, and program data, Each of these examples or some combination may include the implementation of a network environment.

The bus 730 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area using any bus structure among multiple bus structures. bus.

The electronic device 700 may also communicate with one or more external devices 900 (such as keyboards, pointing devices, Bluetooth devices, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 700, and/or communicate with Any device (eg, router, modem, etc.) that enables the electronic device 700 to communicate with one or more other computing devices. Such communication may be performed through an input/output (I/O) interface 740. In addition, the electronic device 700 may also communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 760. As shown in the figure, the network adapter 760 communicates with other modules of the electronic device 700 through the bus 730. It should be understood that although not shown in the figure, other hardware and/or software modules can be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.

Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , Including several instructions to make a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) execute the method according to the embodiments of the present disclosure.

In the exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided. The computer-readable storage medium may be volatile or non-volatile, and the computer-readable storage medium may be The program product of the method. The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, the one or more processors execute the following steps:

In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to make the The terminal device executes the steps according to various exemplary embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

Referring to FIG. 8, FIG. 8 is a computer-readable storage medium for implementing the above-mentioned data verification method according to an exemplary embodiment of the present application. FIG. 8 depicts a program product 800 for implementing the above method according to an embodiment of the present application, which may adopt a portable compact disk read-only memory (CD-ROM) and include program code, and may be installed on an electronic device, such as a personal computer run. However, the program product of this application is not limited to this. In this document, the readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.

The program product can use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Type programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than a readable storage medium, and the readable medium may send, propagate, or transmit a program for use by or in combination with the instruction execution system, apparatus, or device.

The program code contained on the readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

The program code used to perform the operations of the present application can be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming languages. Programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computing device, partly on the user's device, executed as an independent software package, partly on the user's computing device and partly executed on the remote computing device, or entirely on the remote computing device or server Executed on. In the case of a remote computing device, the remote computing device can be connected to a user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (for example, using Internet service providers). Business to connect via the Internet).

In another embodiment, in the data verification method provided by the present application, in order to further ensure the privacy and security of all the above-mentioned data, all the above-mentioned data can also be stored in a node of a blockchain. For example, image files, the first field name and the second field name, etc., these data can be stored in the blockchain node.

The blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

In addition, the above-mentioned drawings are merely schematic illustrations of the processing included in the method according to the exemplary embodiments of the present application, and are not intended for limitation. It is easy to understand that the processing shown in the above drawings does not indicate or limit the time sequence of these processings. In addition, it is easy to understand that these processes can be executed synchronously or asynchronously in multiple modules, for example.

Those skilled in the art will easily think of other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common knowledge or conventional technical means in the technical field that are not disclosed in the present disclosure. . The description and the embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the claims.

Claims

A data verification method, which includes:

Obtain the business type of the target business and the image files that need to be verified for the target business;

The file type of the image file is determined according to the image file, the file type of the target verification file that needs to be verified is determined according to the service type and the file type of the image file, and the target is determined according to the image file The data source identification of the verification file and the file identification of the target verification file, wherein the target verification file is a file for verifying an image file;

Input the service type and the file type of the image file into the pre-trained first machine learning model, and output the first field name that needs to be verified in the image file corresponding to the file type. The pre-training The first machine learning model of is obtained by training sample data that includes the business type, the file type of the image file, and the first field name in the image file that needs to be verified;

Input the file type of the image file, the service type, the file type of the target verification file, and the first field name to the pre-trained second machine learning model, and the output is obtained in the target verification file The second field name for verifying the field value data in the first field name in the first field name, the pre-trained second machine learning model is passed including the business type, the file type of the target verification file, and the target verification file The sample data of the second field name for verifying the field value data in the first field name is obtained by training, and the field value data in the second field name is used to compare the field value data in the first field name Check

Acquiring the field value data in the first field name according to the first field name, and acquiring the target verification file according to the data source information of the target verification file and the file identifier of the target verification file;

The field value data in the first field name is verified based on the field value data in the second field name in the target verification file.
The data verification method according to claim 1, wherein the determining the file type of the image file according to the image file comprises:

OCR character recognition is performed on the image file to obtain recognized text information;

The file type of the image file is determined according to the key field name contained in the recognized text information.
The data verification method according to claim 1, wherein after verifying the field value data in the first field name based on the field value data in the second field name in the target verification file, The method data verification method further includes:

Obtain a verification result of verifying the field value data in the first field name based on the field value data in the second field name in the target verification file, and display the verification result.
The data verification method according to claim 1, wherein the data verification method further comprises:

Obtain the training set sample data used for training the first machine learning model to be trained. Each piece of sample data in the training set sample data includes the business type, the file type of the image file, and the first image file that needs to be verified. A field name;

The first machine learning model to be trained is trained through the training set sample data to obtain the first machine learning model after training.
The data verification method according to claim 4, wherein, after the first machine learning model to be trained is trained through the training set sample data to obtain the trained first machine learning model, the method data verification Methods also include:

Obtain the test set sample data used to verify the first machine learning model after training, each piece of sample data in the test set sample data includes the business type, the file type of the image file, and the image file that needs to be verified The first field name;

Input the business type of each sample data of the test set sample data and the file type of the image file into the first machine learning model after training, and output the name of the first field that needs to be verified in the predicted image file;

If the first field name in the image file that needs to be verified in the test set sample data is consistent with the first field name in the predicted image file that needs to be verified, the number of sample data pieces in the test set sample data If the proportion of the total number of sample data exceeds the predetermined proportion threshold, the trained first machine learning model is identified as the pre-trained first machine learning model.
The data verification method according to claim 2, wherein the recognized text information includes a character data set obtained after recognizing all character data in the image file.
7. The data verification method according to claim 6, wherein the character data set includes a character string corresponding to each field name in the image file and a character string corresponding to field value data in each field name.
A data verification device, which includes:

The first acquiring unit is used to acquire the business type of the target business and the image files that the target business needs to be verified;

The first execution unit is configured to determine the file type of the image file according to the image file, and determine the file type of the target verification file that needs to be verified according to the service type and the file type of the image file, and Determining the data source identifier of the target verification file and the file identifier of the target verification file according to the image file, wherein the target verification file is a file for verifying the image file;

The second execution unit is used to input the service type and the file type of the image file into the pre-trained first machine learning model, and output the first image file that needs to be verified in the image file corresponding to the file type. Field name, the pre-trained first machine learning model is obtained by training sample data that includes the service type, the file type of the image file, and the first field name in the image file that needs to be verified;

The third execution unit is used to input the file type of the image file, the service type, the file type of the target verification file, and the first field name into the second pre-trained machine learning model, and output In the target verification file, the second field name for verifying the field value data in the first field name, and the pre-trained second machine learning model passes through the The file type and the sample data of the second field name for verifying the field value data in the first field name in the target verification file are obtained by training, and the field value data in the second field name is used to compare the first field name. The field value data in the field name is verified;

The second obtaining unit is configured to obtain the field value data in the first field name according to the first field name, and obtain according to the data source information of the target check file and the file identifier of the target check file The target verification file;

The verification unit is configured to verify the field value data in the first field name based on the field value data in the second field name in the target verification file.
An electronic device includes a memory and a processor, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the following steps:

Obtain the business type of the target business and the image files that need to be verified for the target business;

The file type of the image file is determined according to the image file, the file type of the target verification file that needs to be verified is determined according to the service type and the file type of the image file, and the target is determined according to the image file The data source identification of the verification file and the file identification of the target verification file, wherein the target verification file is a file for verifying an image file;

Input the service type and the file type of the image file into the pre-trained first machine learning model, and output the first field name that needs to be verified in the image file corresponding to the file type. The pre-training The first machine learning model of is obtained by training sample data that includes the business type, the file type of the image file, and the first field name in the image file that needs to be verified;

Input the file type of the image file, the service type, the file type of the target verification file, and the first field name to the pre-trained second machine learning model, and the output is obtained in the target verification file The second field name for verifying the field value data in the first field name in the first field name, the pre-trained second machine learning model is passed including the business type, the file type of the target verification file, and the target verification file The sample data of the second field name for verifying the field value data in the first field name is obtained by training, and the field value data in the second field name is used to compare the field value data in the first field name Check

Acquiring the field value data in the first field name according to the first field name, and acquiring the target verification file according to the data source information of the target verification file and the file identifier of the target verification file;

The field value data in the first field name is verified based on the field value data in the second field name in the target verification file.
The electronic device according to claim 9, wherein the determining the file type of the image file according to the image file comprises:

OCR character recognition is performed on the image file to obtain recognized text information;

The file type of the image file is determined according to the key field name contained in the recognized text information.
The electronic device according to claim 9, wherein, after verifying the field value data in the first field name based on the field value data in the second field name in the target verification file, the When the computer-readable instructions are executed by the processor, the processor further executes the following steps:

Obtain a verification result of verifying the field value data in the first field name based on the field value data in the second field name in the target verification file, and display the verification result.
The electronic device according to claim 9, wherein when the computer-readable instructions are executed by the processor, the processor further executes the following steps:

Obtain the training set sample data used for training the first machine learning model to be trained. Each piece of sample data in the training set sample data includes the business type, the file type of the image file, and the first image file that needs to be verified. A field name;

The first machine learning model to be trained is trained through the training set sample data to obtain the first machine learning model after training.
The electronic device according to claim 12, wherein, after the first machine learning model to be trained is trained through the training set sample data to obtain the trained first machine learning model, the computer-readable instructions are executed When the processor executes, the processor further executes the following steps:

Obtain test set sample data used to verify the first machine learning model after training, each piece of sample data in the test set sample data includes business, type, file type of the image file, and image files that need to be calibrated The name of the first field of the test;

Input the business type of each sample data of the test set sample data and the file type of the image file into the first machine learning model after training, and output the name of the first field that needs to be verified in the predicted image file;

If the first field name in the image file that needs to be verified in the test set sample data is consistent with the first field name in the predicted image file that needs to be verified, the number of sample data pieces in the test set sample data If the proportion of the total number of sample data exceeds the predetermined proportion threshold, the trained first machine learning model is identified as the pre-trained first machine learning model.
10. The electronic device according to claim 10, wherein the recognized text information includes a character data set obtained by recognizing all character data in the image file.
14. The electronic device according to claim 14, wherein the character data set includes a character string corresponding to each field name in the image file and a character string corresponding to field value data in each field name.
A storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the following steps:

Obtain the business type of the target business and the image files that need to be verified for the target business;

The file type of the image file is determined according to the image file, the file type of the target verification file that needs to be verified is determined according to the service type and the file type of the image file, and the target is determined according to the image file The data source identification of the verification file and the file identification of the target verification file, wherein the target verification file is a file for verifying an image file;

Input the service type and the file type of the image file into the pre-trained first machine learning model, and output the first field name that needs to be verified in the image file corresponding to the file type. The pre-training The first machine learning model of is obtained by training sample data that includes the business type, the file type of the image file, and the first field name in the image file that needs to be verified;

Input the file type of the image file, the service type, the file type of the target verification file, and the first field name to the pre-trained second machine learning model, and the output is obtained in the target verification file The second field name for verifying the field value data in the first field name in the first field name, the pre-trained second machine learning model is passed including the business type, the file type of the target verification file, and the target verification file The sample data of the second field name for verifying the field value data in the first field name is obtained by training, and the field value data in the second field name is used to compare the field value data in the first field name Check

Acquiring the field value data in the first field name according to the first field name, and acquiring the target verification file according to the data source information of the target verification file and the file identifier of the target verification file;

The field value data in the first field name is verified based on the field value data in the second field name in the target verification file.
The storage medium according to claim 16, wherein the determining the file type of the image file according to the image file comprises:

OCR character recognition is performed on the image file to obtain recognized text information;

The file type of the image file is determined according to the key field name contained in the recognized text information.
The storage medium according to claim 16, wherein, after verifying the field value data in the first field name based on the field value data in the second field name in the target verification file, the When the computer-readable instructions are executed by one or more processors, the one or more processors further execute the following steps:

Obtain a verification result of verifying the field value data in the first field name based on the field value data in the second field name in the target verification file, and display the verification result.
17. The storage medium according to claim 17, wherein the recognized text information includes a character data set obtained by recognizing all character data in the image file.
18. The storage medium according to claim 19, wherein the character data set includes a character string corresponding to each field name in the image file and a character string corresponding to field value data in each field name.