Automatic file quality inspection method, device and equipment, medium and product

Abstract

The invention belongs to the technical field of office automation, and particularly relates to an automatic file quality inspection method, device and equipment, a medium and a product. The method comprises the following steps: acquiring an archive to be subjected to quality inspection, wherein the archive to be subjected to quality inspection comprises electronic archive metadata and an electronic archive image; determining an archive management type according to the quality inspection subject item list; according to the archive management type, obtaining a verification rule corresponding to the archive management type according to an archive verification directory; according to the archive checking catalog, extracting key contents required by checking from the electronic archive metadata and the electronic archive image; and verifying the key content according to a verification rule. Based on the method, automatic quality inspection of the electronic file metadata and the electronic file images is achieved, and meanwhile the method is easy to expand and high in universality.

Description

Technical Field

[0001] The present invention belongs to the field of office automation technology, and in particular relates to an automated file quality inspection method, device, equipment, medium and product. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Digital transformation has put forward new requirements for archive management, namely, to achieve automation, intelligence and efficiency of archive management. At present, archives usually include metadata and images. Metadata is filled in manually or obtained based on image recognition of attachments. Images are usually attached to archives. For example, personal archives include scanned copies of ID cards and household registration books.

[0004] Although some automated quality inspection tools have been proposed, these tools are usually specialized for a certain type of archive. Since the format, content structure and importance assessment criteria of each archive type are different, it is difficult for automated quality inspection tools to adapt to the quality inspection needs of multiple archive types at the same time, resulting in the inability to give full play to the advantages of automated tools. At the same time, customized adjustments increase the cost of use and maintenance. With the deepening of digital transformation, the content and form of archive management are also constantly changing. New archive types emerge in an endless stream, which puts higher requirements on the flexibility and scalability of quality inspection tools. Summary of the invention

[0005] In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides an automated archive quality inspection method, device, equipment, medium and product. By constructing a quality inspection subject list and an archive verification catalog, automatic screening of items to be verified is achieved. At the same time, it is easy to expand and the method is highly versatile.

[0006] To achieve the above object, the first aspect of the present invention provides an automated file quality inspection method, comprising the following steps:

[0007] Acquire the files to be inspected, wherein the files to be inspected include electronic file metadata and electronic file images;

[0008] Based on the electronic archive metadata, the subject identifier and the business item identifier are obtained, and the archive management type is determined according to the quality inspection subject item list; the quality inspection subject item list includes the correspondence between the subject type, the subject unique identifier, the business item identifier and the archive management type;

[0009] According to the file management type, obtaining the verification rules corresponding to the file management type according to the file verification directory; the file verification directory includes multiple file management types and corresponding verification rules;

[0010] According to the archive verification catalog, extract key contents required for verification from the electronic archive metadata and the electronic archive image respectively;

[0011] According to the verification rules, the key contents are verified.

[0012] A second aspect of the present invention provides an automated file quality inspection device, comprising:

[0013] The file acquisition module for quality inspection is configured to acquire the file for quality inspection, wherein the file for quality inspection includes electronic file metadata and electronic file images;

[0014] The archive management type confirmation module is configured to obtain the subject identifier and the business item identifier based on the electronic archive metadata, and determine the archive management type according to the quality inspection subject item list; the quality inspection subject item list includes the correspondence between the subject type, the subject unique identifier, the business item identifier and the archive management type;

[0015] A verification rule acquisition module is configured to acquire, according to the archive management type, the verification rule corresponding to the archive management type according to the archive verification directory; the archive verification directory includes multiple archive management types and corresponding verification rules;

[0016] A key information extraction module is configured to extract key contents required for verification from the electronic archive metadata and the electronic archive image respectively according to the archive verification catalog;

[0017] The automated quality inspection module is configured to verify the key content according to the verification rules.

[0018] A third aspect of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the method described.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the program implements the method described when executed by a processor.

[0020] A fifth aspect of the present invention provides a computer program product, which implements the method when running on one or more processors.

[0021] One or more of the above technical solutions realize automatic screening of items to be checked in archives by constructing a list of quality inspection subjects and an archive verification catalog, thereby improving the efficiency and accuracy of quality inspection, and being able to conduct quality inspection of electronic materials during the process and quality inspection of electronic archives afterwards. At the same time, the list of quality inspection subjects and the archive verification catalog can be flexibly expanded according to different archive management requirements, and can be adapted to the quality inspection of more types of archives without changing the quality inspection process. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0023] Figure 1 It is an overall flow chart of the automatic quality inspection method of archives in an embodiment of the present invention;

[0024] Figure 2 Schematic diagram of key links of the automated quality inspection method for archives in an embodiment of the present invention;

[0025] Figure 3 This is a diagram of the overall functional architecture of the automatic file quality inspection device in an embodiment of the present invention;

[0026] Figure 4 This is a functional architecture diagram of some modules of the automated archive quality inspection device in an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0028] In the description of the embodiments of the present application, the term “including” and similar terms should be understood as open inclusion, that is, “including but not limited to.” The term “based on” should be understood as “based at least in part on.”

[0029] One or more embodiments of the present invention provide an automated quality inspection method for archives, which is applied to an archive management system. The archive management system can be deployed on a client, or on a local server, a cloud server, etc., and can realize batch automated quality inspection. As an example, it can be implemented based on the RPA (Robotic Process Automation) automation processing tool, and RPA can be used to automate repetitive and regularized tasks. The data for quality inspection in the method includes electronic archive metadata and electronic archive images, wherein the electronic archive metadata is structured data in the system, and the electronic archive images are usually attached to the metadata and are unstructured data. As an example, some basic information metadata in the electronic archive metadata is shown in Table 1.

[0030] Table 1 Basic information metadata

[0031]

[0032]

[0033]

[0034]

[0035]

[0036] Pre-build a list of quality inspection items and a file verification catalog.

[0037] The quality inspection subject item list is used to record the correspondence between different quality inspection subjects, business item identifiers, and file management types. For example, the file management type corresponding to the "unit insurance registration" business item is "unit insurance registration materials". At the same time, the subject unique identifier clarifies the operation object of this automated quality inspection task, such as "unit A" and "unit B". As shown in Table 2.

[0038] Table 2 List of quality inspection items

[0039]

[0040] The archive verification catalog is used to record the metadata fields, corresponding image elements, and verification rules corresponding to different archive management types, as shown in Table 3.

[0041] Table 3 Archives verification directory

[0042]

[0043]

[0044] like Figure 1 and Figure 2 As shown, the method comprises the following steps:

[0045] Step 1: Obtain the files to be inspected, which include electronic file metadata and electronic file images;

[0046] Step 2: Obtain the subject identification and business matter identification based on the electronic archive metadata, and determine the archive management type according to the quality inspection subject matter list.

[0047] Step 3: According to the file management type, obtain the verification rules corresponding to the file management type according to the file verification directory;

[0048] Step 4: extracting key contents required for verification from the electronic archive metadata and the electronic archive image respectively according to the archive verification catalog;

[0049] Step 5: Verify the key content according to the verification rules.

[0050] Based on the above method, the automatic quality inspection of archives can be realized, which improves the efficiency of archive management and greatly improves work efficiency without manual intervention. At the same time, the automated process can be carried out continuously without being affected by human factors, ensuring the consistency and accuracy of quality inspection.

[0051] In step 1, the file to be inspected is a newly archived file. The method can be executed when the newly archived file is received, or a quality inspection cycle can be set to automatically inspect the newly archived multiple files at set intervals. By running the quality inspection process regularly, the automatic quality inspection of the newly archived files is realized without manual intervention, which greatly improves work efficiency and ensures the real-time update and dynamic management of the files.

[0052] In step 2, the quality inspection subject item list is the outline of the automated task execution, and the quality inspection of the corresponding electronic files is carried out in sequence according to the subject and the subject's business items.

[0053] In step 4, the archive verification directory also includes metadata fields corresponding to each archive management type and their corresponding image elements; based on the archive verification directory, the content corresponding to the metadata fields to be verified for the archive to be inspected, as well as the corresponding image elements and element contents are extracted. Extracting key information based on the archive verification directory ensures the accuracy and integrity of the data.

[0054] Extracting the corresponding image elements and element contents includes: performing text detection and recognition on the electronic file image based on text detection and recognition technology; searching for the image elements and element contents to be extracted in the recognized text contents. For example, when extracting the unit name from the business license, first search for the element "unit name" and then search for the corresponding element contents, such as a company.

[0055] More specifically, after the text detection and recognition of the electronic archive image based on the text detection and recognition technology, key fields such as subject information (person, unit, organization), amount, location, time and other information are extracted based on the entity recognition technology, and the text is deeply semantically understood based on the natural language processing technology to ensure the accuracy and completeness of the extracted information. The extracted information is then formatted and standardized to facilitate subsequent data processing and comparison. The above steps can be executed after the electronic archive image is successfully uploaded. When the automated quality inspection method is executed for the archive, the image elements and element contents to be extracted are searched from the formatted file.

[0056] The text detection and recognition technology includes two parts: text area detection and text recognition.

[0057] As an example, the text area detection adopts a target detection method based on deep learning, and realizes accurate detection of text areas by training a network model. Specifically, two mainstream detection frameworks are adopted: one is a two-stage method, such as Faster R-CNN, which has high detection accuracy; the other is a one-stage method, such as the YOLO series, which has a faster detection speed while maintaining high accuracy.

[0058] For horizontal text detection, algorithms suitable for horizontal text boxes, such as CTPN, are used to accurately detect regular quadrilateral text areas. For tilted text detection, algorithms suitable for irregular quadrilateral text areas, such as EAST and Seglink, are used to improve recognition accuracy by detecting tilted text boxes and performing text correction.

[0059] The text recognition adopts a text recognition method based on a classification model to recognize the detected text area. For fixed-length text, a multi-digit number classification algorithm is used to recognize each character as an independent unit; for variable-length text, a CNN+RNN / LSTM / GRU+CTC architecture is used to realize the recognition of text of any length.

[0060] During the text recognition process, the detected single-line text image can also be preprocessed, such as using RadonHough transform and other methods to perform text correction to improve the recognition accuracy.

[0061] As an example, the text recognition adopts OCR technology, and the image is preprocessed before recognition, including denoising, binarization, tilt correction and other steps to improve the accuracy of text recognition. In addition, it supports the recognition of multiple languages ​​and character sets, thereby meeting the conversion requirements of different language files.

[0062] In step 5, the verification of the key content mainly includes format checking, data comparison and logic verification.

[0063] Among them, format check is to check the authenticity of electronic file images based on preset rules, such as the authenticity of application materials, and judge whether it is an ID card, household register, social security card, business license, pension insurance manual, professional qualification certificate, academic degree certificate, etc. Based on the judgment that the electronic file image meets the authenticity requirements, data comparison and logic verification are carried out.

[0064] Data comparison is to compare the key content extracted from the electronic archive metadata and the electronic archive image to determine whether the content is consistent, such as whether the name of the reporting entity is consistent, whether the ID number or unit number is consistent, etc. Logical verification is to verify the data based on preset rules and logic, such as checking whether the archive belongs to the entity, the business, and whether the key information set by the rules is complete and accurate. Taking the verification of employee wages and contribution bases in the "social insurance premium collection and verification materials" as an example, first determine whether the employees in the declaration form match the current employees of the unit, then verify whether the contribution base of each employee is between 60% and 300% (bottom and top) of the social average wage, and finally verify whether the contribution base is consistent with the employee's salary. This item allows inconsistency but records the verification results.

[0065] If data anomalies are found after quality inspection, the anomalies will be reminded, for example, the data anomalies found will be recorded and pushed for manual processing in the form of to-do items. The to-do items may include an error information list, which includes error types, error data, etc., to facilitate users to carry out targeted processing. The data anomalies may be caused by text extraction or recognition errors, or there may be errors in the data itself. In the case of recognition errors, users can manually intervene and correct them, and can manually modify the text of the recognition error and supplement the missing information.

[0066] After each automated quality inspection process is executed, a quality inspection report can be generated based on the verification results.

[0067] The above automated quality inspection method follows the preset verification rules, avoiding errors and omissions that may be caused by manual operation. The application of OCR recognition module and information extraction module ensures the accurate extraction of key information and reduces the error rate of data entry. At the same time, it can assist in the validity and key data verification of electronic materials, ensuring the smooth operation of business.

[0068] It can be understood that the quality inspection subject list and the archive verification catalog can be flexibly adjusted according to different archive management needs, and the types of archives that can be quality inspected can be easily expanded, making the quality inspection process easy to expand and customize.

[0069] Based on the above method, one or more embodiments of the present invention further provide an automatic file quality inspection device, such as Figure 3 and Figure 4 As shown, the device comprises:

[0070] The file acquisition module for quality inspection is configured to acquire the file for quality inspection, wherein the file for quality inspection includes electronic file metadata and electronic file images;

[0071] The archive management type confirmation module is configured to obtain the subject identification and the business matter identification based on the electronic archive metadata, and determine the archive management type according to the quality inspection subject matter list;

[0072] A verification rule acquisition module is configured to acquire, according to the archive management type and the archive verification directory, the verification rule corresponding to the archive management type;

[0073] A key information extraction module is configured to extract key contents required for verification from the electronic archive metadata and the electronic archive image respectively according to the archive verification catalog;

[0074] The automated quality inspection module is configured to verify the key content according to the verification rules.

[0075] The system further comprises:

[0076] The quality inspection result output module is configured to output the verification items and verification results. The quality inspection result output module can display the quality inspection results to the user in a visual manner such as charts and tables, and provide a detailed list of error information, so that the user can quickly understand the quality inspection situation. The error information list includes error type, error data, etc. In addition, a quality inspection report can also be generated. The report format can be selected according to the user's needs. The file format such as PDF and Excel is convenient for users to save and view.

[0077] The manual intervention and correction module is configured to provide manual intervention and correction functions for the error information list. In the case of recognition errors, users can manually intervene and correct them, such as manually modifying the text of the recognition error, supplementing the missing information, etc. The results of manual intervention and correction are saved to the system, and the database and quality inspection report are updated to ensure the accuracy and completeness of the data.

[0078] The operating environment of the above method or device includes a server side and a client side.

[0079] 1. Server construction and configuration

[0080] Hardware preparation: Prepare server hardware equipment.

[0081] Operating system installation: Install a stable and reliable operating system on the server.

[0082] Database deployment: Configure and deploy a relational database.

[0083] Software environment construction: install programming language environment (Java), database connector, and deep learning framework.

[0084] Application service deployment: deploy the module for acquiring files to be inspected, the module for confirming the file management type, the module for acquiring verification rules, the module for extracting key information, and the module for automated quality inspection on the server and configure them.

[0085] Interface configuration: configure the interfaces between modules, including database interface, API interface, and test connectivity.

[0086] Security settings: Configure network security policies, including firewall rules, encrypted communications, etc., to protect server and data security.

[0087] 2. Install the client on the terminal computer for file quality inspection

[0088] Software distribution: Package the client software and distribute it to the business operation terminal computers.

[0089] Installation and configuration: The user installs the client software on the archive quality inspection terminal computer and configures it according to the prompts, including server address, login credentials, etc.

[0090] 3. Overall system operation and maintenance

[0091] Daily operation: Ensure the normal operation of server-side and terminal client software, and monitor server performance and network status.

[0092] User support: Provide user support services, including question answering, operation guidance, troubleshooting, etc.

[0093] Data backup: Regularly back up data and configuration information on the server to ensure data security.

[0094] Software Update: Update server and client software in a timely manner according to business needs and technological development, and fix security vulnerabilities and defects.

[0095] Performance optimization: Regularly evaluate system performance, adjust system configuration, optimize code, etc. based on the evaluation results to improve system performance.

[0096] Fault handling: For any faults that occur, handle them in a timely manner and record the fault log for subsequent analysis and improvement.

[0097] Version management: Perform version management on server and client software, and record functional changes, modification records, and other information of each version.

[0098] One or more embodiments of the present invention further provide an electronic device that can be used to implement the automatic file quality inspection method in the above embodiments. The electronic device includes one or more processors, one or more memories coupled to the processors, and a communication module coupled to the processors.

[0099] The memory may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, at least one of the following: read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, hard disk, compact disc (CD), digital video disc (DVD) or other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, at least one of the following: random access memory (RAM), or other volatile memories that do not last during the duration of a power outage. The computer program may be stored in the ROM. When the processor executes the computer program, the above-mentioned automated quality inspection method for archives is implemented.

[0100] In some embodiments, the program may be tangibly contained in a computer-readable medium, which may be included in a device (such as in a memory) or other storage device accessible by the device. The program may be loaded from the computer-readable medium to the RAM for execution. The computer-readable medium may include any type of tangible non-volatile memory, such as ROM, EPROM, flash memory, hard disk, and the computer-readable storage medium stores a computer program, which implements the above-mentioned automated archive quality inspection method when executed by a processor.

[0101] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a server or terminal, the process or function described in the embodiment of the present application is generated in whole or in part. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a server or terminal or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (such as a floppy disk, a hard disk and a tape, etc.), an optical medium (such as a digital video disk (digital video disk, DVD), etc.), or a semiconductor medium (such as a solid-state hard disk, etc.).

[0102] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.

[0103] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A method for automated quality inspection of archives, characterized in that: The following steps are involved: Acquire the files to be inspected, wherein the files to be inspected include electronic file metadata and electronic file images; Based on the electronic archive metadata, the subject identifier and the business item identifier are obtained, and the archive management type is determined according to the quality inspection subject item list; the quality inspection subject item list includes the correspondence between the subject type, the subject unique identifier, the business item identifier and the archive management type; According to the file management type, obtaining the verification rules corresponding to the file management type according to the file verification directory; the file verification directory includes multiple file management types and corresponding verification rules; According to the archive verification catalog, extract key contents required for verification from the electronic archive metadata and the electronic archive image respectively; According to the verification rules, the key contents are verified.

2. The automated file quality inspection method according to claim 1, characterized in that: Based on the set quality inspection cycle, new archived files are periodically retrieved as the files to be inspected for automated quality inspection.

3. The automated file quality inspection method according to claim 1, characterized in that: The archive verification catalog includes metadata fields corresponding to each type of archive management and its corresponding image elements; based on the archive verification catalog, the content corresponding to the metadata fields to be verified for the archive to be quality inspected, as well as the corresponding image elements and element contents are extracted.

4. The automated file quality inspection method according to claim 3, characterized in that: Extracting the corresponding image elements and element contents includes: performing text detection and recognition on the electronic file image based on text detection and recognition technology; and searching for the image elements and element contents to be extracted in the recognized text contents.

5. The automated file quality inspection method according to claim 4, characterized in that: The text detection adopts a target detection method based on deep learning, and the deep learning model includes a model suitable for horizontal text box and inclined text box detection.

6. The automated file quality inspection method according to claim 1, characterized in that: Verification of the key content includes format checking, data comparison and logic verification.

7. An automated file quality inspection device, characterized in that: include: The file acquisition module for quality inspection is configured to acquire the file for quality inspection, wherein the file for quality inspection includes electronic file metadata and electronic file images; The archive management type confirmation module is configured to obtain the subject identifier and the business item identifier based on the electronic archive metadata, and determine the archive management type according to the quality inspection subject item list; the quality inspection subject item list includes the correspondence between the subject type, the subject unique identifier, the business item identifier and the archive management type; A verification rule acquisition module is configured to acquire, according to the archive management type, the verification rule corresponding to the archive management type according to the archive verification directory; the archive verification directory includes multiple archive management types and corresponding verification rules; A key information extraction module is configured to extract key contents required for verification from the electronic archive metadata and the electronic archive image respectively according to the archive verification catalog; The automated quality inspection module is configured to verify the key content according to the verification rules.

8. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that When the computer program product is run on one or more processors, the method according to any one of claims 1 to 6 is implemented.

Images