Data auditing method and device and computer readable storage medium

Abstract

The invention discloses a data auditing method and device and a computer readable storage medium, and relates to the technical field of data auditing, and the method comprises the steps: determining a business type of to-be-audited data and an auditing demand of the business type when the to-be-audited data uploaded by a user is received; configuring corresponding auditing elements based on the auditing demand, and defining an auditing rule and a data source of each auditing element; identifying the to-be-audited data, and extracting to-be-audited data of the to-be-audited data; and based on the auditing rule and the structured data in the data source, auditing the to-be-audited data. Through the steps, the auditing efficiency and accuracy of the data can be improved.

Description

Technical Field

[0001] The present application relates to a specific technical field of data review, and in particular to a data review method, device and computer-readable storage medium. Background Art

[0002] In leasing and lending platforms, users need to upload personal information according to business requirements, which will be reviewed by back-end staff. However, with the continuous expansion of business scenarios, the amount of data for review materials and the corresponding review standards have also increased dramatically. Manual review methods are difficult to cope with the review requirements of large-scale and diverse data, and cannot conduct flexible and efficient data review according to different business scenarios.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a data review method, device and computer-readable storage medium, aiming to solve the technical problem that manual review is difficult to cope with the review requirements of large-scale review data and diverse data, and cannot perform flexible and efficient data review according to different business scenarios.

[0005] To achieve the above purpose, the present application proposes a data review method, which includes:

[0006] Upon receiving the pending review materials uploaded by the user, determining the business type of the pending review materials and the review requirements of the business type;

[0007] Configure corresponding audit elements based on the audit requirements, and define audit rules and data sources for each audit element;

[0008] Identify the document to be reviewed, and extract the data to be reviewed of the document to be reviewed;

[0009] The data to be reviewed is reviewed based on the review rules and the structured data in the data source.

[0010] In one embodiment, the step of determining the business type of the to-be-audited document and the audit requirements of the business type includes:

[0011] Obtaining business process information corresponding to the materials to be reviewed;

[0012] Determine the business type of the document to be reviewed based on the business process information;

[0013] The audit requirements are determined according to the pre-stored business audit requirement correspondence.

[0014] In one embodiment, the step of configuring the corresponding audit elements based on the audit requirements and defining the audit rules and data sources for each of the audit elements includes:

[0015] Based on the audit requirements, determine the types of materials that the audited materials should include and the audit items corresponding to the audited materials;

[0016] Based on the data type and the audit item, matching target audit elements based on predefined audit elements;

[0017] Based on the mapping relationship of the target audit elements, the audit rules and data sources of each audit element are set.

[0018] In one embodiment, before the step of determining the business type of the to-be-audited document and the audit requirements of the business type, the step further includes:

[0019] In response to the configuration instructions triggered by the configuration page, obtain the audit element configuration information, audit material type, custom audit items and audit rules input by the auditor;

[0020] Based on the audit element configuration information, a mapping relationship between the audit element and the audit material type, the custom audit item, and the audit rule is established;

[0021] In response to a save instruction triggered by the configuration page, the audit element is saved.

[0022] In one embodiment, the step of identifying the document to be reviewed and extracting the data to be reviewed of the document to be reviewed includes:

[0023] Converting the to-be-reviewed document into a document in a preset format, and identifying text content therein based on the document in the preset format;

[0024] Performing word segmentation on the text content, and identifying corresponding entity types based on the processed text content;

[0025] Extract the data to be reviewed corresponding to the entity type.

[0026] In one embodiment, the step of reviewing the data to be reviewed based on the review rules and the structured data in the data source includes:

[0027] Associating and comparing the data to be reviewed with corresponding structured data;

[0028] If the data to be reviewed conforms to the review rules or the structured data, the data to be reviewed is marked as passed;

[0029] If the data to be reviewed does not comply with the review rules or the structured data, the data to be reviewed is marked as failed.

[0030] In one embodiment, after the step of reviewing the data to be reviewed based on the review rules and the structured data in the data source, the method further includes:

[0031] Output the audit results and display them based on the front-end display interface;

[0032] Based on the audit results, determine the audit materials that have not passed the audit and generate corresponding prompt information;

[0033] Feedback the prompt information to the reviewer.

[0034] In one embodiment, before the step of determining the business type of the to-be-audited document and the audit requirements of the business type, the step further includes:

[0035] Obtain the hash value corresponding to the information to be reviewed;

[0036] Based on the hash value, determining whether the to-be-reviewed material is a duplicate uploaded material;

[0037] If the data to be reviewed is the repeatedly uploaded data, identifying the character content of the data to be reviewed;

[0038] The character contents are deduplicated and aggregated.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a data review device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data review method as described above.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the data review method as described above are implemented.

[0041] The embodiment of the present application provides a document review method. When receiving the document to be reviewed uploaded by the user, the business type of the document to be reviewed and the review requirements of the business type are determined, the corresponding review elements are configured based on the review requirements, and the review rules and data sources of each review element are defined, the document to be reviewed is identified, and the data to be reviewed of the document to be reviewed is extracted, and the data to be reviewed is reviewed based on the review rules and the structured data in the data source. An automated process of reviewing the data to be reviewed and outputting the review results based on the review elements, data sources and review rules can be implemented, thereby improving the review efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 A flowchart of the first embodiment of the application document review method is provided;

[0045] Figure 2 A flowchart of the second embodiment of the application document review method is provided;

[0046] Figure 3 A flowchart of the third embodiment of the application document review method is provided;

[0047] Figure 4 This is a schematic diagram of the interface displaying the review results of this application materials review method;

[0048] Figure 5 This is a schematic diagram of the configuration interface for the review elements of this application materials review method;

[0049] Figure 6 This is the first schematic diagram of the configuration interface for reviewing materials for this application material review method;

[0050] Figure 7 This is the second schematic diagram of the configuration interface for reviewing materials for this application material review method;

[0051] Figure 8 Schematic diagram of the device structure of the hardware operating environment involved in the data audit method in the embodiment of the present application.

[0052] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solutions of the embodiments of this application are:

[0056] In this embodiment, for the convenience of description, the following description is made with the identification material review device as the execution subject.

[0057] In leasing and lending platforms, users need to upload personal information according to business requirements, which will be reviewed by back-end staff. However, with the continuous expansion of business scenarios, the amount of data for review materials and the corresponding review standards have also increased dramatically. Manual review methods are difficult to cope with the review requirements of large-scale and diverse data, and cannot conduct flexible and efficient data review according to different business scenarios.

[0058] The present application provides a solution, which determines the business type of the material to be reviewed and the review requirements of the business type when receiving the material to be reviewed uploaded by the user, configures the corresponding review elements based on the review requirements, defines the review rules and data sources of each review element, identifies the material to be reviewed, extracts the data to be reviewed of the material to be reviewed, and reviews the data to be reviewed based on the review rules and the structured data in the data source.

[0059] It can be seen from the above embodiments that the present application supports the review of custom audit rules, data sources, key information that should be extracted from the materials to be reviewed, etc. When receiving the materials to be reviewed uploaded by the user, it is possible to implement an automated process based on the audit elements, data sources and audit rules to review the data to be reviewed and output the audit results, thereby improving the audit efficiency and accuracy.

[0060] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a data review device, etc. The following takes the data review device as an example to illustrate this embodiment and the following embodiments.

[0061] Based on this, the present application embodiment provides a data review method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the application document review method.

[0062] In this embodiment, the document review method includes steps S10 to S40:

[0063] Step S10: upon receiving the documents to be reviewed uploaded by the user, determining the business type of the documents to be reviewed and the review requirements of the business type.

[0064] In this embodiment, for scenarios such as online vehicle leasing or lending, users need to upload identity documents, personal information, contact information, proof of assets, proof of income, etc. The system collects the attachment information uploaded by the user through an external application programming interface (Application Programming Interface, API) or application (application, APP) or personal computer (Personal Computer, PC) end operation portal. When receiving the pending materials uploaded by the user, the pending materials uploaded by the user are classified, such as identity card, driver's license, vehicle registration certificate, vehicle photo, etc.

[0065] In a feasible implementation, in order to realize the automatic classification of the documents to be reviewed, image classification technology can be used to identify and classify the types of documents to be processed uploaded by users through computer vision technology, such as ID card photos, driver's license photos, vehicle registration photos and vehicle photos, so as to improve the efficiency and accuracy of information processing. Furthermore, image data sets corresponding to various types of documents to be reviewed can be pre-built, and these images can be processed in a unified format and size, and the diversity of samples can be increased through data enhancement technologies such as rotation and cropping. According to the task requirements, a suitable deep learning model is selected, such as ResNet (a model name), Inception (a model name), etc., and the model is trained using the data sets corresponding to the labeled types of documents to be reviewed, so that the model can recognize different types of documents to be reviewed. In addition, when the audit business adds a new type of document to be reviewed, the transfer learning technology is used to fine-tune the pre-trained model to adapt to the new classification task. The trained model is integrated into the server, and an API interface is developed to receive the pictures uploaded by users and provide classification results.

[0066] Parse the documents to be reviewed in each category and extract key information, such as name, ID number, date of birth, etc. Based on the key information obtained from the analysis, combined with business rules and preset conditions, determine the business type of the document.

[0067] Optionally, the business type and business requirements can also be determined based on the business process triggered when the user submits the materials to be reviewed. When the user initiates a specific business process on the platform, such as submitting a vehicle rental application or a loan application, the system will record the user's operation and trigger the corresponding process. Further, the information is matched with a specific business type according to the business process triggered by the user and the type of information. The system determines the corresponding review requirements based on the business type matching results. In a feasible implementation, a business process model can be established in advance, including various business types and corresponding review requirements, and the review materials, review steps and review standards involved in each business type can be set. At the same time, the rules for business type matching must be determined, and based on the business type matching rules, a rule engine is constructed to automatically match the information uploaded by the user with the specific business type. The rule engine can use a special rule engine software, or it can implement a set of rule matching logic through programming. According to the specific business process triggered by the user and the type of information, the matching rules are formulated. For example, if the user triggers the vehicle rental application process and uploads a driver's license and a vehicle photo, the uploaded information can be matched to the business type of "vehicle rental". For example, for a rental scenario, it may be necessary to review a driver's license and vehicle registration certificate; for a loan scenario, it may be necessary to review proof of income and a credit report. Furthermore, according to the type of business, the corresponding audit requirements are determined, including the specific information that needs to be reviewed, the audit standards and the audit process. These requirements can be pre-defined and managed in the business process model, that is, each business type is associated with its corresponding audit requirements, and a mapping table or database of business type-audit requirements is established for storage, ensuring that the system can quickly determine the corresponding audit requirements based on the business type. For example, when the system determines that the business type submitted by the user is "vehicle rental", the rule engine can determine the type of information and audit standards that need to be reviewed based on the pre-defined mapping relationship. It is understandable that the audit elements of the document can be pre-defined by the auditor, including the key information that needs to be extracted from each document,

[0068] In this embodiment, through the above steps, the system can match the results according to the business type and determine the corresponding audit requirements. Such a system can help automate the audit process, improve audit efficiency, reduce manual intervention, and ensure the accuracy and applicability of the audit.

[0069] Step S20: Configure corresponding audit elements based on the audit requirements, and define audit rules and data sources for each audit element.

[0070] In this embodiment, the audit elements refer to the multiple audit items corresponding to the validity of the materials to be audited. For example, the audit elements of identity cards and driver's licenses may include the validity period of the certificates, age, identity information, etc.; the audit elements of asset certification materials may include the validity period of asset documents, asset evaluation, asset sources, etc. The audit requirements of different business types correspond to different audit elements. For example, type A business needs to verify that the age of the identity card is greater than 18 years old, while type B business does not need to verify that the age of the identity card is greater than 18 years old. When the audit requirements of the current business type are determined, the audit content also needs to be configured, including matching the corresponding audit elements, defining the audit rules and data sources for each audit element.

[0071] In a feasible implementation, the audit elements and audit rules of each attachment in different business types are pre-defined by the auditor, that is, the judgment and comparison conditions of each audit element, such as whether the age is greater than 18 years old or greater than 20 years old, can be customized. For more complex comparison situations, auditors can also define multiple conditions and set the audit relationship between multiple conditions, such as passing only when all conditions are met or passing only when any one condition is met. In addition, the data source can also be pre-defined by the auditor. The data source is used to review whether the content in the audit materials is consistent with the information recorded in the system, that is, to compare the key data in the document with the structured data recorded in the system. The system will establish a mapping relationship with the business type based on the audit elements, audit rules and data sources pre-defined by the auditor, including the business type name, fields to be audited, data format, value range, business logic, etc.

[0072] Furthermore, when configuring audit elements based on audit requirements, the system matches the pre-configured business type according to the identification results of the file type, and obtains the audit content and audit rules corresponding to the business type. For the matched business type, the system can automatically obtain the audit content corresponding to the to-be-audited materials from the mapping relationship between the pre-defined business type and the audit content rules, and automatically set the corresponding audit elements, including the fields to be audited, data format, value range, business logic, etc. At the same time, the corresponding audit rules will be automatically set based on the matched business type.

[0073] In this embodiment, by customizing audit elements, audit rules and data sources, the system can dynamically identify the content that needs to be audited for each business when receiving the materials to be audited uploaded by the user, and automatically set it, which saves manpower and improves audit efficiency.

[0074] Step S30: Identify the document to be reviewed, and extract the data to be reviewed of the document to be reviewed.

[0075] In this embodiment, before the audited materials are audited, it is necessary to identify the audited materials and extract the audited data to be audited therefrom. As a feasible implementation method, during the processing, the audited materials can be converted into preset format documents that can be processed by OCR (Optical Character Recognition), such as images and scanned documents. The text in the image or scanned document is extracted using the selected OCR engine or with the help of a third-party OCR tool, and the text output by the OCR is cleaned and preprocessed to remove possible noise, erroneous characters or format problems to obtain the processed text content. In a feasible implementation method, the auditor needs to predefine the key information to be used for each attachment as a subsequent parameter to the transmission OCR recognition interface. For each type of attachment, a parameter template is created, including the name, location, format, etc. of the key information to be extracted, and these parameters are stored in JSON or other structured data formats. The created parameter template is used as input, the OCR interface is integrated, and the OCR recognition service is called. When calling the interface, the corresponding parameter template is passed to guide the OCR engine to identify and extract the key text content of the audited materials.

[0076] Furthermore, NLP (Natural Language Processing) technology is used to perform entity recognition on the cleaned text content to identify the entity type to which the data to be reviewed belongs, such as name, address, date, etc. According to the specific structure or rules of the data to be reviewed, corresponding rules or models are written to extract the data to be reviewed. During extraction, the cleaned text is segmented and divided into a sequence of words or phrases. The pre-trained entity recognition model is used to identify the entities in the text sequence after segmentation and determine the entity type to which it belongs. Entity types may include names of people, places, and names of organizations, etc. The results of entity recognition are processed and parsed to extract the identified entities and their corresponding entity types. This part of the content will be verified as data to be reviewed to ensure its accuracy and consistency. The extracted data to be reviewed is saved or output to a suitable format, such as a database, a spreadsheet, or an API interface, for subsequent review and analysis. Optionally, entity types and entities can be further sorted and screened according to business needs, such as using a machine learning model to classify entities, or defining rules to filter specific types of entities.

[0077] In this embodiment, by utilizing OCR and NLP for processing, it can help realize the digitization, automated processing and in-depth analysis of text information, improve work efficiency, reduce labor costs, and facilitate efficient review of the data to be reviewed in subsequent processes.

[0078] Step S40: review the data to be reviewed based on the review rules and the structured data in the data source.

[0079] In this embodiment, the extracted data to be reviewed needs to be further compared with the structured data in the data source, and the review rules are used to verify whether the data to be reviewed is compliant. If the data to be reviewed is consistent with the structured data or the review rules, it is marked as passed; if the data to be reviewed is inconsistent with the structured data or the review rules and does not meet the review rules, it is marked as failed.

[0080] Further, as a feasible implementation method, program logic is written in advance according to the audit rules for automated auditing, and operations such as data parsing, rule matching, and exception handling are converted into programs that can be automatically executed. When the audit rules are compared with the structured data in the data source, the written audit logic is used to automatically audit the data to be audited. Optionally, in another feasible implementation method, the rule engine can also be used to convert the audit rules into a form that the rule engine can understand and execute, including information such as the coding, configuration or definition conditions, actions, and priorities of the rules. For example, the value range of a certain field, the occurrence of keywords in the text, and the results of numerical calculations are specified. The audit rules are input through the visual interface or programming interface of the rule engine and configured according to the pre-defined audit rules. In addition, the structured data source to be audited needs to be integrated into the rule engine to ensure that the rule engine can access and process the data to be audited. The rule engine will match and execute the data to be audited according to the defined audit rules. When the data meets a certain rule, the rule engine will trigger the corresponding action. When performing data audit, the data that meets the audit rules is marked as passed. Data that does not conform to the rules will be marked as failed, and the reasons for failure, location information, and recommended repair methods will be determined.

[0081] In the subsequent process, the results will be reviewed and referenced. Figure 4 , the audit results will be output and displayed through the display interface, with the data that passed and failed the audit marked respectively. In addition, for the data that failed the audit, corresponding prompt information can be generated and fed back to the corresponding auditor, who will manually proofread the audited data. The results of the manual proofreading audit will be displayed in the manual proofreading column of the display interface. For data that failed the system audit, it can be automatically submitted to the auditor for review, and the operator can verify the data according to the marked information in the audit results. It is understandable that the audit results will also be recorded and saved, including the passed data and the failed data and related audit information, for future tracing and analysis.

[0082] Based on the above steps, when each business reaches the designated review node, the system will automatically match all documents that need to be reviewed, identify the documents in batches, and compare and verify the identified information with the information in the system. If the verification passes, it will be marked as passed, and if the verification fails, it will be marked as failed. The review results can be intuitively displayed on the review page.

[0083] In this embodiment, through the above steps, an automated process of reviewing the data to be reviewed and outputting the review results based on the review elements, data sources and review rules can be implemented, thereby improving the review efficiency and accuracy.

[0084] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 Before step S10, the document review method further includes the following steps:

[0085] Step S50: In response to the configuration instruction triggered by the configuration page, the audit element configuration information, audit material type, custom audit items and audit rules input by the auditor are obtained.

[0086] Step S60: Based on the audit element configuration information, a mapping relationship between the audit element and the audit material type, the user-defined audit item, and the audit rule is established.

[0087] Step S70: In response to a save instruction triggered by the configuration page, save the audit elements.

[0088] In this embodiment, the system supports auditors to customize the content, audit elements, audit rules and data sources of the audit materials to be audited. Auditors can enumerate all documents that need to be audited and customize the key information that needs to be extracted from each document. For example, if the ID card is a document that needs to be audited, the ID card can be defined first, and then the key information required in the ID card can be defined, including name, ID number, ID validity period, etc. Similarly, auditors can customize the judgment and comparison conditions for each audit element, and each audit element can be customized to adapt to the scenario. In addition, users can also customize the data source to compare the data to be audited in the document with the structured data recorded in the system.

[0089] Furthermore, as a feasible implementation method, a user interface or form is designed to allow auditors to input audit document types, custom audit items of audit elements, and audit rules. Taking the user interface as an example, when the configuration page receives a configuration instruction triggered by the user (such as clicking a new button), the configuration interface responds and receives relevant information such as audit element configuration information, audit document types, custom audit items, and audit rules written by the auditor. Based on the configuration information entered by the auditor, the system will establish a mapping relationship between the audit element and the audit document type, custom audit items, and the audit rules. When the auditor triggers the save instruction again, the system will save the audit elements created this time and their mapping relationships. Figure 5 In the audit element configuration interface, auditors can add or delete audit elements. The configuration content includes audit element name, verification method, verification element code, business rule description, etc. The audit rules are set based on business needs, regulatory requirements or other standards. The rules can include data format, range, logical relationship, etc. For example, specify the valid range of a numeric field from a certain value to a certain value, or specify the occurrence of specific keywords in the text. Figure 6 When the user defines the audit data, the auditor can click the "Add" button in the upper left corner to add a new audit data type. The audit data can be the front and back of the ID card, commercial insurance policy, car purchase invoice, etc. Each audit data has its own data list code and data list name. At the same time, the auditor can set whether to perform ORC recognition on the audit data, whether to convert it to an image, and match field information. Take the vehicle invoice as an example, refer to Figure 7 After clicking the matching field of the vehicle invoice, the field configuration interface appears. In this interface, the auditor can set the key information to be extracted from the vehicle invoice, such as the invoice status, the name of the purchaser, the purchaser's ID number, etc. These key information are the content that needs to be reviewed. Similarly, for other types of audit materials, this information may include but is not limited to the business type name, the field to be reviewed, the data format, the value range, the business logic, etc. Through the input content of the auditor, the mapping relationship between the type of material to be reviewed, the custom audit item and the audit rule is established and saved in the database. The mapping relationship can be realized through an association table or other methods to ensure that different audit material types in different business types correspond to corresponding custom audit items and audit rules. The configured audit elements, audit rules, data sources and the mapping relationship between each other are applied through programming or special audit tools. When the user uploads the material to be reviewed, the system can automatically match and review according to the business type.

[0090] In this embodiment, the above steps can realize the function of establishing a mapping relationship between the audit material type, custom audit items and audit rules input by the business personnel, and creating and saving them as audit elements. In this way, the audit element information can be flexibly managed and used to meet the custom audit requirements under different business needs.

[0091] Based on the first and / or second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above description, and will not be described in detail later. Figure 3 Before step S10, the document review method further includes the following steps:

[0092] Step S80: Obtain the hash value corresponding to the document to be reviewed.

[0093] Step S90: Based on the hash value, determine whether the to-be-reviewed document is a duplicate uploaded document;

[0094] Step S100: If the document to be reviewed is the repeatedly uploaded document, identify the character content of the document to be reviewed.

[0095] Step S110, de-duplicate and aggregate the character contents.

[0096] In this embodiment, in actual application scenarios, users sometimes upload the audit information repeatedly.

[0097] In this embodiment, for the situation where users repeatedly upload materials to be reviewed, the present application also provides an automatic deduplication solution to automatically identify duplicate documents of the materials to be reviewed so as not to affect the review results. When a file is uploaded, it is often accompanied by the generation of a hash value. The hash value can be used to determine whether the materials to be reviewed are duplicate uploaded materials. If they are duplicate uploaded materials, the character content therein will be identified, and duplicate removal and aggregation will be performed on them. For the scenario where multiple copies of the same file are uploaded, when the system receives the materials to be reviewed uploaded by the user, the system will read the corresponding hash value of the materials to be reviewed, and determine whether they are the same file based on the hash value of the file. If the hash values ​​of multiple files are the same, it means that multiple copies of the same type of file have been uploaded. At this time, the system background will only recognize the file once. For the scenario where the same type of file is uploaded multiple times, the hash values ​​of the files before and after the upload are inconsistent, so the system will recognize it multiple times. At this time, the recognition results will be deduplicated, and the same content will only be retained once. For the scenario where different files are transferred multiple times, it is usually because the wrong file was uploaded. In this case, each file will be identified. After the identification is completed, all the identification results will be deduplicated and summarized. Then, according to the actual situation, how to configure the verification rule is determined. For example, for the review of identity cards, if a Zhang San's ID card is uploaded and a Li Si's attachment is uploaded, the result of the name keyword is "Zhang San Li Si". In order to increase the fault tolerance space, the review rule can be configured in the review element as a text inclusion relationship, that is, if the recognition result "Zhang San Li Si" contains the word "Zhang San", it means that the rule has been reviewed and approved.

[0098] Furthermore, in a feasible implementation, a business table for file management is pre-designed. The table contains fields such as file name, file storage path, storage directory, file size, and hash value of the file. With this information, the system can quickly locate and retrieve files. When the file is uploaded, the front end will first calculate the hash value of the file and send this value to the server together with the file. The server provides a query interface for checking whether the hash value of the uploaded file already exists in the database. If the hash value already exists, it means that the file has been uploaded. At this time, only the uploaded file is identified, and a record pointing to the original file is added to the database. When identifying and deduplicating, check whether there is the same identification result in the database. If it exists, it is skipped, and if it does not exist, it is added to the database. It should be noted that once the file is successfully uploaded, the system will add or update the corresponding record in the file management table. This includes information such as the hash value, file name, storage path, etc. of the file. In this way, the next time the same file is uploaded, the system can quickly identify and reuse the existing records.

[0099] In this embodiment, by adding an automatic duplicate elimination mechanism, the fault tolerance can be improved to a certain extent for the scenario where users repeatedly upload review materials, ensuring that the final recognition result meets expectations and satisfies business requirements.

[0100] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the material review method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0101] The present application provides a data review device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data review method in the above-mentioned embodiment 1.

[0102] Reference below Figure 8 , which shows a schematic diagram of the structure of a data review device suitable for implementing the embodiment of the present application. The data review device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 8 The document review device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0103] like Figure 8As shown, the data audit device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the data audit device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the data audit device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a data audit device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0104] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0105] The document review device provided by the present application adopts the document review method in the above embodiment to solve the technical problem of document review. Compared with the prior art, the beneficial effects of the document review device provided by the present application are the same as the beneficial effects of the document review method provided by the above embodiment, and the other technical features in the document review device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0106] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0107] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0108] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the data review method in the above-mentioned embodiment.

[0109] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0110] The computer-readable storage medium may be included in the data review device; or may exist independently without being assembled into the data review device.

[0111] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the data review device, the data review device:

[0112] Upon receiving the pending review materials uploaded by the user, determining the business type of the pending review materials and the review requirements of the business type;

[0113] Configure corresponding audit elements based on the audit requirements, and define audit rules and data sources for each audit element;

[0114] Identify the document to be reviewed, and extract the data to be reviewed of the document to be reviewed;

[0115] The data to be reviewed is reviewed based on the review rules and the structured data in the data source.

[0116] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0117] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0118] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0119] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned data review method, and can solve the technical problem that the manual review method is difficult to cope with the review requirements of large-scale review data and diverse data, and cannot perform flexible and efficient data review according to different business scenarios. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the data review method provided by the above-mentioned embodiment, and will not be repeated here.

[0120] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A data review method, characterized in that: The method includes: Upon receiving the pending review materials uploaded by the user, determining the business type of the pending review materials and the review requirements of the business type; Configure corresponding audit elements based on the audit requirements, and define audit rules and data sources for each audit element; Identify the document to be reviewed, and extract the data to be reviewed of the document to be reviewed; The data to be reviewed is reviewed based on the review rules and the structured data in the data source.

2. The method according to claim 1, characterized in that The step of determining the business type of the to-be-audited document and the audit requirements of the business type includes: Obtaining business process information corresponding to the materials to be reviewed; Determine the business type of the document to be reviewed based on the business process information; The audit requirements are determined according to the pre-stored business audit requirement correspondence.

3. The method according to claim 1, characterized in that The steps of configuring the corresponding audit elements based on the audit requirements and defining the audit rules and data sources for each of the audit elements include: Based on the audit requirements, determine the types of materials that the audited materials should include and the audit items corresponding to the audited materials; Based on the data type and the audit item, matching target audit elements based on predefined audit elements; Based on the mapping relationship of the target audit elements, the audit rules and data sources of each audit element are set.

4. The method according to claim 1, characterized in that Before the step of determining the business type of the to-be-audited document and the audit requirements of the business type, the method further includes: In response to the configuration instructions triggered by the configuration page, obtain the audit element configuration information, audit material type, custom audit items and audit rules input by the auditor; Based on the audit element configuration information, a mapping relationship between the audit element and the audit material type, the custom audit item, and the audit rule is established; In response to a save instruction triggered by the configuration page, the audit element is saved.

5. The method according to claim 1, characterized in that The step of identifying the document to be reviewed and extracting the data to be reviewed of the document to be reviewed includes: Converting the to-be-reviewed document into a document in a preset format, and identifying text content therein based on the document in the preset format; Performing word segmentation on the text content, and identifying corresponding entity types based on the processed text content; Extract the data to be reviewed corresponding to the entity type.

6. The method according to claim 1, characterized in that The step of reviewing the data to be reviewed based on the review rules and the structured data in the data source includes: Associating and comparing the data to be reviewed with corresponding structured data; If the data to be reviewed conforms to the review rules or the structured data, the data to be reviewed is marked as passed; If the data to be reviewed does not comply with the review rules or the structured data, the data to be reviewed is marked as failed.

7. The method according to claim 1, characterized in that After the step of reviewing the data to be reviewed based on the review rules and the structured data in the data source, the method further includes: Output the audit results and display them based on the front-end display interface; Based on the audit results, determine the audit materials that have not passed the audit and generate corresponding prompt information; Feedback the prompt information to the reviewer.

8. The method according to claim 1, characterized in that Before the step of determining the business type of the to-be-audited document and the audit requirements of the business type, the method further includes: Obtain the hash value corresponding to the information to be reviewed; Based on the hash value, determining whether the to-be-reviewed material is a duplicate uploaded material; If the data to be reviewed is the repeatedly uploaded data, identifying the character content of the data to be reviewed; The character contents are deduplicated and aggregated.

9. A data review device, characterized in that: The document review device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the document review method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the data review method according to any one of claims 1 to 8 are implemented.

Images