Document management method and device and storage medium

Abstract

The invention discloses a document management method and device and a storage medium, and the method comprises the steps: determining a corresponding document recognition model according to the document type of a to-be-recognized document; identifying one or more pieces of data information in the to-be-identified document through the document identification model; determining a corresponding preset keyword comparison table according to the document type of the to-be-identified document; wherein the preset keyword comparison table is used for storing standard field information corresponding to different data information, and the standard field information refers to a field identifier corresponding to a storage position of the corresponding data information in a target information management system; and according to the preset keyword comparison table, writing the one or more pieces of data information into a target information management system according to the corresponding standard field information. Through the scheme, the to-be-identified document is automatically written into the target information management system and converted into the data which can be executed and operated by the target information management system.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to, but are not limited to, the field of data processing technology, and in particular, to a document management method, device, and storage medium. Background Art

[0002] Traditional laboratory document management systems provide services such as document classification, document approval and release, document issuance and archiving, document change, recycling, disposal and destruction, document review and novelty search, etc., focusing on the process management of the entire cycle of laboratory documents and the management of the documents themselves.

[0003] Traditional laboratory document management systems only digitize documents, but do not integrate with LIMS (Laboratory Information Management System, an information management system that combines database-based information technology with laboratory management needs) to automatically convert them into executable and actionable data. They are unable to efficiently utilize document content (for example, they require manual identification, entry, maintenance, and application of documents, resulting in a disproportionate workload and output), which in turn makes it impossible for LIMS to play a central control role in digital laboratories. Summary of the invention

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The present invention provides a document management method, device and storage medium, which can solve the technical problems of low conversion efficiency and high labor cost in traditional laboratory file management systems when converting documents into data that can be executed and operated by laboratory information management systems.

[0006] An embodiment of the present disclosure provides a document management method, comprising: determining a corresponding document recognition model according to a document type of a document to be recognized; recognizing one or more data information in the document to be recognized through the document recognition model; determining a corresponding preset keyword comparison table according to the document type of the document to be recognized; wherein the preset keyword comparison table is used to store standard field information corresponding to different data information, and the standard field information refers to a field identifier corresponding to a storage location of the corresponding data information in a target information management system; and writing the one or more data information into the target information management system according to the corresponding standard field information according to the preset keyword comparison table.

[0007] An embodiment of the present disclosure further provides a document management device, comprising: a memory and a processor; the memory is used to store a program for document management; the processor is used to read the program for document management and execute the document management method as described in any embodiment of the present disclosure.

[0008] An embodiment of the present disclosure further provides a non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, can implement the document management method as described in any embodiment of the present disclosure.

[0009] Compared with the related art, the document management method, device and storage medium provided by the embodiment of the present disclosure can realize the management of documents by determining the corresponding document recognition model and preset keyword comparison table according to the document type of the document to be recognized, and using the model to recognize the data information in the document to be recognized, and writing the data information into the target information management system according to the preset keyword comparison table. The solution realizes the automatic writing of the document to be recognized into the target information management system and converting it into executable and operable data of the target information management system through the coordinated use of the document recognition model and the preset keyword comparison table.

[0010] Compared with traditional laboratory document management methods, this solution does not require manual document identification, nor does it require identification results to be entered into the target information management system one by one. It greatly improves the efficiency of converting documents into executable and actionable data for the target information management system, and solves the technical problems of low conversion efficiency and high labor costs when converting documents into executable and actionable data for the target information management system.

[0011] Other features and advantages of the embodiments of the present application will be described in the subsequent description, and partly become apparent from the description, or can be understood by implementing the embodiments of the present application. The purpose and other advantages of the embodiments of the present application can be achieved and obtained by the structures specifically pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings are used to provide an understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0013] Figure 1 This is a flowchart of a document management method according to an embodiment of the present disclosure; Figure 2 A schematic diagram of a document to be identified according to an embodiment of the present disclosure; Figure 3 This is a specific flow chart of a document management method according to an embodiment of the present disclosure; Figure 4 FIG. 4 is a schematic diagram of a document management device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0014] The present application describes multiple embodiments, but the description is exemplary rather than restrictive, and it is obvious to those skilled in the art that there may be more embodiments and implementations within the scope of the embodiments described in the present application. Although many possible feature combinations are shown in the drawings and discussed in the specific embodiments, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with any other feature or element in any other embodiment, or may replace any other feature or element in any other embodiment.

[0015] The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in the present application may also be combined with any conventional features or elements to form a unique invention scheme. Any features or elements of any embodiment may also be combined with features or elements from other invention schemes to form another unique invention scheme. Therefore, it should be understood that any feature shown and / or discussed in the present application may be implemented individually or in any appropriate combination. Therefore, except for the limitations made according to the attached claims and their equivalents, the embodiments are not subject to other restrictions. In addition, various modifications and changes may be made within the scope of protection of the attached claims.

[0016] In addition, when describing representative embodiments, the specification may have presented the method and / or process as a specific sequence of steps. However, to the extent that the method or process does not rely on the specific order of the steps described herein, the method or process should not be limited to the steps of the specific order described. As will be understood by those of ordinary skill in the art, other sequences of steps are also possible. Therefore, the specific sequence of the steps set forth in the specification should not be interpreted as a limitation to the claims. In addition, the claims for the method and / or process should not be limited to the steps of performing them in the order written, and those skilled in the art can easily understand that these sequences can be changed and still remain within the spirit and scope of the embodiments of the present application.

[0017] Traditional laboratory document management systems have the following problems: (1) Laboratory file system management focuses on file archiving, permission control, auditing, and content indexing, but cannot directly apply file content; (2) Script-based file collection requires parsing graph content according to fixed templates and Java scripts. The collected text content is very limited, there is no self-learning function, the application scope is limited, and the maintenance cost is high; (3) The connection between the file management system and LIMS is manual, and manual conversion of file contents consumes a lot of manpower and time. For example, the conversion of traditional laboratory files to LIMS requires manual identification of documents such as test methods, commission contracts, and implementation standards, and the identification results are entered into LIMS one by one, which consumes a lot of manpower and time.

[0018] To this end, an embodiment of the present disclosure provides a document management method, such as Figure 1 As shown, the following steps may be included: Step S110: determining a corresponding document recognition model according to the document type of the document to be recognized; Step S120: identifying one or more data information in the document to be identified by using the document identification model; Step S130: Determine a corresponding preset keyword comparison table according to the document type of the document to be identified; wherein the preset keyword comparison table is used to store standard field information corresponding to different data information, and the standard field information refers to the field identifier corresponding to the storage location of the corresponding data information in the target information management system; illustratively, the standard field information can be a standard field or information or identification ID information in the system, and there is no limitation on this; Step S140: According to the preset keyword comparison table, the one or more data information are written into the target information management system according to the corresponding standard field information.

[0019] Exemplarily, the target information management system may be a laboratory information management system LIMS.

[0020] The document management method of this embodiment determines the corresponding document recognition model and preset keyword comparison table according to the document type of the document to be recognized, recognizes the data information in the document to be recognized by the model, and writes the data information into the target information management system according to the preset keyword comparison table to achieve document management. This solution realizes the automatic writing of the document to be recognized into the target information management system and converts it into executable and operable data of the target information management system through the coordinated use of the document recognition model and the preset keyword comparison table.

[0021] Compared with traditional laboratory document management methods, this solution does not require manual document identification, nor does it require the identification results to be entered into the target information management system one by one. It greatly improves the efficiency of converting documents into executable and actionable data for the target information management system, and solves the problem of "low conversion efficiency and high labor costs when converting documents into executable and actionable data for the target information management system".

[0022] In an exemplary embodiment of the present disclosure, the document types may include: inspection plan, entrustment contract, quality standard, inspection method, inspection report, instrument diagram, equipment manual.

[0023] In an exemplary embodiment of the present disclosure, before determining the corresponding document recognition model according to the document type of the document to be recognized, the method further includes: receiving the document to be recognized and the document type corresponding to the document to be recognized uploaded by a user; Before determining the corresponding preset keyword comparison table according to the document type of the document to be identified, the method further includes: confirming whether the document type of the document to be identified is correct according to the keywords in the identified data information.

[0024] Exemplarily, when the document type of the document to be identified confirmed based on the keywords in the identified data information is inconsistent with the document type selected by the user when uploading the document to be identified, the document type of the document to be identified confirmed based on the keywords in the identified data information shall prevail; or, when there is an inconsistency, a prompt may be given for the user to confirm the document type.

[0025] The document management method of this embodiment, before determining the preset keyword comparison table corresponding to the document to be identified, will further confirm the document type of the document to be identified based on the keywords in the identified data information to ensure the correctness of the document type and the selected preset keyword comparison table, thereby further ensuring the correctness of the document to be identified being written into the target management system.

[0026] In an exemplary embodiment of the present disclosure, the step of writing the one or more data information into the target information management system according to the corresponding standard field information according to the preset keyword comparison table includes: According to the preset keyword comparison table, respectively search for the standard field information corresponding to each piece of data information; Write each piece of data information into the target information management system according to the corresponding standard field information; After all data information is written, a document record of the document to be identified in the target information management system is generated; illustratively, each document record corresponds to a unique identification information.

[0027] The document management method of this embodiment searches for the standard field information corresponding to each piece of data information according to a preset keyword comparison table, and then writes each piece of data information into the target information management system according to the found standard field information, and finally realizes that all data information identified by the document to be identified is written into the target information management system, which means that the document to be identified is converted into data that can be executed and operated by the target information management system.

[0028] In an exemplary embodiment of the present disclosure, after generating a document record of the document to be identified in the target information management system, the method may further include: applying the document record to a corresponding application function module in the target management system.

[0029] In the document management method of this embodiment, since the data information is a keyword comparison table determined according to the document type, and then written into the target management system according to the keyword comparison table, and the document type corresponds to the corresponding application function module in the target information management system, the corresponding application function module of the target management system can directly use the written data information. In other words, the document management method of this embodiment realizes the conversion of the data information of the document to be identified into executable and operable data of the target information management system for direct use by the corresponding application function module.

[0030] In an exemplary embodiment of the present disclosure, the target information management system stores one or more preset information query tables; before writing each piece of data information into the target information management system, the method further includes: For each piece of data information, determine whether the data information has a corresponding preset information query table; When the data information has a corresponding preset information query table: query the preset information query table for supplementary data information corresponding to the data information; and update the data information according to the found supplementary data information.

[0031] The document management method of this embodiment can supplement the data information in the document to be identified through the preset information query table stored in the target information management system, so as to refine and supplement the data information in the document to be identified and store it in the target management system, and then generate a more complete and detailed technical solution based on the stored information.

[0032] In an example of this embodiment, the document type includes an inspection plan type, the data information includes material information, and the preset information query table includes a material management system table; querying the supplementary data information corresponding to the data information from the preset information query table includes: Query material status information, material type and historical data information corresponding to the material information from the material management system table; Determine the applicable materials for the inspection plan in the current document based on the material status information, material type and historical data information; The applicable materials shall be used as the supplementary data information.

[0033] For example, the data information can be located and identified according to the feature identifier from the document to be identified (for example, the feature identifier corresponding to the applicable scope can be identified). Figure 2 The text corresponding to the scope of application in the document is "applicable to the admission inspection and verification of sugar / Tina powder soup purchased by our company"; for example, according to the "characteristic identification corresponding to the inspection plan", Figure 2 The first inspection plan in the document is the inspection plan for "sugar"), combined with the material status information, material type and historical data information of all materials in the material management system table, query the applicable materials of the material information identified by the document to be identified.

[0034] For example, Figure 2 For example, the material information refers to "white sugar", and the applicable scope information identified from the document is "factory inspection and verification". Based on this, it can be judged that the inspection plan corresponding to the document uses "raw and auxiliary material testing". Then, the existing materials with "material status information" of "raw and auxiliary materials" and "material type" of "white sugar" can be queried from the MTL table (that is, the purchased white sugar to be used, including various batches and various manufacturers). Among them, the existing materials are obtained based on historical purchase information. That is, based on the material status information, material type and historical data information, Figure 2 Documentation of the inspection plan for the material to which it applies.

[0035] In an exemplary embodiment of the present disclosure, after identifying one or more data information in the document to be identified, the method further includes: Generate a data table according to the data information and display it to the user; Correct the data information of the corresponding cell in the data table according to the correction content input by the user, and generate a correction record; wherein the correction record includes: correction content, modifier, and modification time; The corrected data information is used as updated data information.

[0036] In an example of this embodiment, after writing the one or more data information into the target information management system according to the corresponding standard field information, the method further includes: Generate a manual correction log of the document to be identified based on the correction record of the current document to be identified; Use the current document to be recognized as the source document; The source document and the manual correction log are uploaded to a target information management system.

[0037] The document management method of this embodiment supports users to correct the identified content and generate correction records, thereby ensuring the accuracy of the information written into the target management system and tracing the modifications to ensure that the modifications can be traced.

[0038] In an example of this embodiment, identifying one or more data information in the document to be identified includes: when there is unidentifiable content, marking the unidentifiable content.

[0039] For example, it can be marked in the form of highlights, descriptions, and other annotations (for example, unrecognizable text and images are marked in yellow as a reminder) to prepare for manual review and correction in subsequent steps.

[0040] In an exemplary embodiment of the present disclosure, different types of documents correspond to different document recognition models; different document recognition models are trained respectively through the following processes: The document recognition model is trained by taking a large number of sample documents of the document type corresponding to the current document recognition model as input and the predetermined text in the sample documents as output until the recognition result meets the preset requirements. For example, if the accuracy of the document recognition model during recognition reaches the preset minimum accuracy, it is considered that the recognition model meets the preset requirements, and the document recognition model training is completed at this time.

[0041] The predetermined text may be text marked with a feature identifier, and the feature identifier may be different types of identifiers respectively set for specific parts of different types of documents.

[0042] In summary, the document management method of this embodiment can realize document digitization, and the recognized and converted text is applied to the target management system after processing and proofreading, thereby reducing operating costs, improving utilization efficiency and management efficiency, and avoiding information bias caused by manual conversion during the recognition process.

[0043] The following is a complete example of the application of the disclosed document management method to laboratory document management. Figure 3 As shown, the following steps may be included: Step S310: For each type of document, a corresponding document recognition model (also referred to as a parsing template) is trained respectively.

[0044] This step may include: using a large number of sample documents of the document type corresponding to the current document recognition model as input and text in the sample documents as output, training the document recognition model until the recognition result meets the preset requirements. For example, if the accuracy of the document recognition model during recognition reaches a preset minimum accuracy, it is considered that the recognition model meets the preset requirements, and the document recognition model training is completed at this time.

[0045] For example, AI recognition technology can be used to identify the classification and content of laboratory documents, and AI can be continuously trained through different types of sample documents and application scenarios to improve the recognition accuracy.

[0046] Step S320: Identify the data information in the document to be identified by using the trained document recognition model. If there is unrecognizable content, mark the unrecognizable content. For example, you can highlight notes, explanations, etc. to prepare for manual review and correction in subsequent steps.

[0047] Exemplarily, the process may include the following steps S321 to S323: Step S321: receiving the uploaded document to be identified and the selected document type of the document to be identified.

[0048] Exemplarily, supported document formats to be recognized may include: .pdf, .doc, .docx, .xsl, .xlsx, .csv, .png, and .jpg.

[0049] Exemplarily, the documents to be identified may be classified by content, including: inspection plan, commission contract, quality standard, inspection method, inspection report, instrument diagram, equipment manual, etc.

[0050] It should be noted that the document management method of this embodiment supports batch uploading of documents and also supports version control of uploaded documents.

[0051] Step S322: pre-processing the document to be recognized, wherein the pre-processing may include one or more of the following: binarization, noise removal, and tilt correction.

[0052] Step S323: Select a corresponding document recognition model according to the document type of the document to be recognized, and recognize the data information in the document to be recognized through the model.

[0053] Step S330: Manually calibrate the identified data information and generate a manual calibration log.

[0054] Exemplarily, the process may include the following steps S331 to S334: Step S331: Generate a data table based on the data information and display it to the user.

[0055] Step S332: Correct the data information of the corresponding cell in the data table according to the correction content input by the user, and generate a correction record; wherein the correction record includes: correction content, modifier, and modification time.

[0056] Step S333: Generate a manual correction log of the document to be identified based on the correction record of the document to be identified.

[0057] Step S334: Use the corrected data information as updated data information (data information used in subsequent steps).

[0058] Step S340: According to the preset keyword comparison table, the standard field information corresponding to each piece of data information is searched respectively, and the data information is imported into LIMS according to the found standard field information. The standard field information refers to the field identifier corresponding to the storage location of the corresponding data information in the target information management system.

[0059] Exemplarily, this step may include the following sub-steps S341 to S345: Step S341: confirm the document type of the document to be identified selected by the user according to the keywords in the data information. For example, taking the document in the following figure as an example, the document type of the document can be determined as "inspection plan" according to the keywords such as "our company", "sugar / starch sugar", "factory inspection and verification" contained in the identified data information.

[0060] It should be noted that when the document type of the document to be identified confirmed based on the keywords in the data information is inconsistent with the document type selected by the user when uploading the document to be identified, the document type of the document to be identified confirmed based on the keywords in the data information shall prevail; or, when there is inconsistency, a prompt may be given for the user to confirm the document type.

[0061] Step S342: Determine the corresponding preset keyword comparison table according to the document type of the document to be identified. Figure 2 Taking the document as an example, you can select the corresponding preset inspection plan keyword comparison table.

[0062] Step S343: According to the preset inspection plan keyword comparison table, the standard field information corresponding to each piece of data information in the data table is searched respectively (ie, the standard field information in the LIMS system).

[0063] For example, Figure 2 For example, based on the keywords contained in the identified data information, it can be confirmed that the materials applicable to the document include "white sugar", and then the standard field information corresponding to "white sugar" can be confirmed.

[0064] Step S344: for the data information that needs to be supplemented, the supplementary data information corresponding to the data information is searched from the preset information query table, and the data information is updated according to the supplementary data information found.

[0065] For example, Figure 2For example, if the identified "white sugar" needs additional content, the preset information query table can be a material management system (MTL) table. At this time, according to the material name "white sugar", the materials that match the name of "white sugar" (such as white sugar from different batches, white sugar from different manufacturers) and their corresponding MDMID (Material Data Management ID) can be queried from the MTL table.

[0066] Step S345: Write each piece of data information into LIMS according to the corresponding standard field information. For data information that needs to be supplemented, the data information here refers to the supplemented and updated data information.

[0067] For example, Figure 2 Taking the document as an example, the preset inspection plan keyword comparison table may include fields such as "material name", "sampling quantity", and "inspection items". Taking sugar / starch sugar as an example, the data information "white sugar, edible glucose" in the data table corresponds to "material name", "50 grams" corresponds to "sampling quantity", "label identification, sensory indicators, amylase" corresponds to "inspection items", and each inspection item corresponds to "frequency, scope of use and result application" (other corresponding relationships are not listed one by one), and finally combined with the static data table and related structures of the laboratory information management system, the corresponding supplementary data information is found, and then the identified data information and supplementary data information are imported into the LIMS system according to the above correspondence, and an inspection plan in the LIMS system (i.e., sugar / starch sugar inspection plan) is generated.

[0068] Step S350: Upload the source document and manual correction log to the LIMS system and save them for traceability. The source document refers to the original document to be identified.

[0069] It should be noted that since the preset keyword comparison table is determined according to the document type, and the document type corresponds to the corresponding functional module in LIMS, the standard field information determined according to the preset keyword comparison table corresponds to the data of the application functional module of the LIMS system. Therefore, after the data information in the data table is imported into LIMS through the corresponding standard field information, data matching can be achieved with the application functional module of the LIMS system for use by the corresponding application functional module.

[0070] At this point, the document to be identified is converted into data that can be executed and operated by the LIMS system, and the LIMS system can directly apply the data stored in itself.

[0071] In summary, the laboratory file management method of this embodiment has the following advantages: Ease of use: It is easy to use and does not increase the learning cost of the staff. For example, since the laboratory file management method of this embodiment can automatically identify documents and write them into the LIMS system, the staff only needs to review them based on their experience during the whole process without performing other operations. Therefore, the file management system constructed by the laboratory file management method of this embodiment does not increase the learning cost of the staff and is easy to use.

[0072] Sustainability: The system function design is easy to adjust and is applicable to more than 99% of laboratory files. For example, since the file management method of this embodiment trains different document recognition models according to different types of files, when the content of a certain type of file changes or a new file type is added, it is only necessary to retrain the corresponding document recognition model, and other types of document recognition models do not need to be changed. Therefore, the document management method of this embodiment realizes the relative independence of different types of files, is easier to adjust functions, and has good scalability.

[0073] Traceability: Collect original documents, automatically process data, and manually calibrate, leaving traces of each step for archiving.

[0074] Self-learning: It can learn the file reading method independently to reduce the manual calibration rate.

[0075] An embodiment of the present disclosure also provides a document management device. Figure 4 , including: memory and processor; The memory is used to store a program for document management; The processor is used to read the program for document management and execute the document management method as described in any embodiment of the present disclosure.

[0076] The processor of the above-mentioned embodiment of the present disclosure may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP for short), a microprocessor, etc., or other conventional processors, etc.; the processor may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), discrete logic or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or other equivalent integrated or discrete logic circuits, or a combination of the above devices. That is, the processor of the above-mentioned embodiment may be any processing device or device combination that implements the various methods, steps and logic block diagrams disclosed in the embodiment of the present disclosure. If the embodiment of the present disclosure is partially implemented in software, the instructions for the software may be stored in a suitable non-volatile computer-readable storage medium, and one or more processors may be used to execute the instructions in hardware to implement the method of the embodiment of the present disclosure. The term "processor" used herein may refer to the above-mentioned structure or any other structure suitable for implementing the technology described herein.

[0077] An embodiment of the present disclosure further provides a non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, can implement the document management method as described in any embodiment of the present disclosure.

[0078] In summary, the present invention provides a document management method, device and storage medium. Through this solution, laboratory documents can be digitized, and the recognized and converted texts can be applied to the laboratory information management system after processing and proofreading, thereby reducing the laboratory's operating costs, improving the LIMS usage efficiency and laboratory management efficiency, and avoiding information deviation caused by manual conversion during the recognition process.

[0079] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term "computer storage medium" includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

Claims

1. A document management method, characterized in that: include: Determine a corresponding document recognition model according to the document type of the document to be recognized; Identify one or more data information in the document to be identified by using the document identification model; Determine a corresponding preset keyword comparison table according to the document type of the document to be identified; wherein the preset keyword comparison table is used to store standard field information corresponding to different data information, and the standard field information refers to the field identifier corresponding to the storage location of the corresponding data information in the target information management system; According to the preset keyword comparison table, the one or more data information are written into the target information management system according to the corresponding standard field information.

2. The document management method according to claim 1, characterized in that: Before determining the corresponding document recognition model according to the document type of the document to be recognized, the method further includes: receiving the document to be recognized and the document type corresponding to the document to be recognized uploaded by a user; Before determining the corresponding preset keyword comparison table according to the document type of the document to be identified, the method further includes: confirming whether the document type of the document to be identified is correct according to the keywords in the identified data information.

3. The document management method according to claim 1, characterized in that: The step of writing the one or more data information into the target information management system according to the corresponding standard field information according to the preset keyword comparison table includes: According to the preset keyword comparison table, respectively search for the standard field information corresponding to each piece of data information; Write each piece of data information into the target information management system according to the corresponding standard field information; After all data information is written, a document record of the document to be identified in the target information management system is generated.

4. The document management method according to claim 3, characterized in that: The target information management system stores one or more preset information query tables; before writing each piece of data information into the target information management system, the method further includes: For each piece of data information, determine whether the data information has a corresponding preset information query table; When the data information has a corresponding preset information query table: query the preset information query table for supplementary data information corresponding to the data information; and update the data information according to the found supplementary data information.

5. The document management method according to claim 4, characterized in that: The document type includes an inspection plan type, the data information includes material information, and the preset information query table includes a material management system table; The querying of the supplementary data information corresponding to the data information from the preset information query table includes: Query material status information, material type and historical data information corresponding to the material information from the material management system table; Determine the applicable materials for the inspection plan in the current document based on the material status information, material type and historical data information; The applicable materials shall be used as the supplementary data information.

6. The document management method according to claim 1, characterized in that: After identifying one or more data information in the document to be identified, the method further includes: Generate a data table according to the data information and display it to the user; Correct the data information of the corresponding cell in the data table according to the correction content input by the user, and generate a correction record; wherein the correction record includes: correction content, modifier, and modification time; The corrected data information is used as updated data information.

7. The document management method according to claim 6, characterized in that: After writing the one or more data information into the target information management system according to the corresponding standard field information, the method further includes: Generate a manual correction log of the document to be identified based on the correction record of the current document to be identified; Use the current document to be identified as the source document; The source document and the manual correction log are uploaded to a target information management system.

8. The document management method according to claim 1, characterized in that: Different document types correspond to different document recognition models; different document recognition models are trained through the following processes: The document recognition model is trained by taking a large number of sample documents of a document type corresponding to the current document recognition model as input and taking predetermined text in the sample documents as output until the recognition result meets the preset requirements.

9. A document management device, comprising: A memory and a processor; characterized in that: The memory is used to store a program for document management; The processor is used to read the program for document management and execute the document management method according to any one of claims 1 to 8.

10. A non-transitory computer-readable storage medium storing a computer program, wherein: When the computer program is executed by a processor, it can implement the document management method as claimed in any one of claims 1 to 8.

Images